Visible to the public Video Surveillance 2015Conflict Detection Enabled

SoS Newsletter- Advanced Book Block

SoS Logo

Video Surveillance 2015

Video surveillance is a fast growing area of public security. With it have come policy issues related to privacy. Technical issues and opportunities have also arisen, including the potential to use advanced methods to provide positive identification, abnormal behaviors in crowds, intruder detection, and information fusion with other data. The research presented here came from multiple conferences and publications and was offered in 2015.

Boyer, M.; Veigl, S., "Privacy Preserving Video Surveillance Infrastructure with Particular Regard to Modular Video Analytics," in Imaging for Crime Prevention and Detection (ICDP-15), 6th International Conference on, pp. 1-5, 15-17 July 2015. doi: 10.1049/ic.2015.0120

Abstract: The demand for modular video analytics in surveillance systems is steadily growing as it offers significant advantages when flexibility and/or scalability in terms of computational performance are required. At the same time, the utilization of modular systems raises many questions with regard to ensuring the right for privacy, justice and freedom of citizens when developing and operating surveillance infrastructure. Both, surveillance infrastructure as well as the rights of citizens concerning their personal data are subject to constant change. The socio-ethical nature of individual rights (e.g. the varying perception of such rights) has to be considered too. Last but not least, a concept of accountability (i.e. accountability-by-design) has to be established. Our contribution demonstrates how a set of simple and individually harmless algorithmic modules can be used to obtain sensitive personal information out of surveillance video footage. Trying to solve this challenge solely by technical means (i.e. for individual components) is not expedient and will hardly lead to a successful solution: The functionality of a combination of primitive algorithms can exceed the abilities of the sum of the parts by magnitudes. Strict adherence to the privacy-by-design paradigm for each individual component in order to guarantee privacy preservation for the whole system is not sufficient either. Our solution tackles this challenge on a higher, comprehensive level considering the entire life cycle of surveillance systems, ideally starting with the planning and design phase. It supports the development and ensures that privacy aspects are continuously reviewed whilst the audited system is in operation or maintenance. This indicates another difficulty in connection with the ever-changing nature of the parties being in charge of privacy concerns over the lifetime of surveillance systems. We will present a solution being applied to a surveillance system including modular video analytic- using the example of a specific video surveillance scenario.

Keywords: data privacy; video surveillance; harmless algorithmic modules; modular video analytics; primitive algorithms; privacy preserving video surveillance infrastructure; privacy-by-design paradigm; socio-ethical nature; Distributed Systems; Modular Design; Privacy Protection; Visual Analytics; Visual Surveillance (ID#: 15-8013)


Bonetto, M.; Korshunov, P.; Ramponi, G.; Ebrahimi, T., "Privacy in Mini-Drone Based Video Surveillance," in Automatic Face and Gesture Recognition (FG), 2015 11th IEEE International Conference and Workshops on, vol. 04, pp. 1-6, 4-8 May 2015. doi: 10.1109/FG.2015.7285023

Abstract: Mini-drones are increasingly used in video surveillance. Their areal mobility and ability to carry video cameras provide new perspectives in visual surveillance which can impact privacy in ways that have not been considered in a typical surveillance scenario. To better understand and analyze them, we have created a publicly available video dataset of typical drone-based surveillance sequences in a car parking. Using the sequences from this dataset, we have assessed five privacy protection filters via a crowdsourcing evaluation. We asked crowdsourcing workers several privacy- and surveillance-related questions to determine the tradeoff between intelligibility of the scene and privacy, and we present conclusions of this evaluation in this paper.

Keywords: autonomous aerial vehicles; image filtering; image sequences; video surveillance; car parking; crowdsourcing evaluation; drone based surveillance sequence; minidrone based video surveillance privacy; privacy protection filter; publicly available video dataset; Crowdsourcing; Data privacy; Licenses; Privacy; Surveillance; Vehicles; Visualization; Mini-drones; crowdsourcing evaluation; dataset; privacy; video surveillance (ID#: 15-8014)


Ma, X.; Zeng, W.; Yang, L.; Zou, D.; Jin, H., "Lossless ROI Privacy Protection of H.264/AVC Compressed Surveillance Videos," in Emerging Topics in Computing, IEEE Transactions on , vol. PP, no.99, pp.1-1, 06 August 2015. doi: 10.1109/TETC.2015.2460462

Abstract: Privacy becomes one of the major concerns of video surveillance systems especially in cloud-based systems. Privacy protection of surveillance videos aims to protect privacy information without hampering normal video surveillance tasks. ROI (Region-Of-Interest) privacy protection is more practical compared to the whole video encryption approaches. However, one common drawback of virtually all current ROI privacy protection methods is that the original compressed surveillance video recorded in the camera is permanently distorted by the privacy protection process, due to the quantization in the re-encoding process. Thus the integrity of the original compressed surveillance video captured by the camera is destroyed. This is unacceptable for some application scenarios such as video forensics for investigations and video authentication for law enforcement, et al. In this paper, we introduce a new paradigm for privacy protection in surveillance videos, referred to as lossless privacy region protection, which has the property that the distortion introduced by the protection of the privacy data can be completely removed from the protected videos by authorized users. We demonstrate the concept of lossless privacy region protection through a proposed scheme applied on H.264/AVC compressed videos.

Keywords: Cameras; Encryption; Privacy; Surveillance; Video coding; Videos; H.264/AVC; inter-frame drift error; intra-frame drift error; lossless; privacy protection; video surveillance (ID#: 15-8015)


Birnstill, P.; Daoyuan Ren; Beyerer, J., "A User Study on Anonymization Techniques for Smart Video Surveillance," in Advanced Video and Signal Based Surveillance (AVSS), 2015 12th IEEE International Conference on, pp. 1-6, 25-28 Aug. 2015. doi: 10.1109/AVSS.2015.7301805

Abstract: A key mechanism of privacy-aware smart video surveillance is anonymization of video data. We conducted a user study with a response of 103 participants in order to investigate which pixel operations are suitable for protecting persons' identities while, at the same time, allowing a human operator to recognize persons' activities i.e., preserving the utility of the video data. Regarding the activities in the data set, namely stealing, fighting, and dropping a bag, our data does not approve the common hypothesis that privacy and utility of video data are necessarily trade-off.

Keywords: data privacy; video surveillance; anonymization techniques; privacy-aware smart video surveillance; video data; Color; Image color analysis; Image edge detection; Privacy; Shape; Video recording; Video surveillance (ID#: 15-8016)


Ma, X.; Yang, L.; Xiang, Y.; Zeng, W.; Zou, D.; Jin, H., "Fully Reversible Privacy Region Protection for Cloud Video Surveillance," in Cloud Computing, IEEE Transactions on , vol. PP, no.99, pp.1-1, 18 August 2015. doi: 10.1109/TCC.2015.2469651

Abstract: Privacy becomes one of the major concerns of cloud-based multimedia applications such as cloud video surveillance. Privacy protection of surveillance videos aims to protect privacy information without hampering normal processing tasks of the cloud. Privacy Region Protection only protects the privacy region while keeping the non-privacy region visually intact to facilitate processing in the cloud. However, full reversibility, i.e. the complete recovery of the original video which is critical to digital investigation and law enforcement has not been properly addressed in privacy region protection. In this paper, we introduce fully reversible privacy region protection into cloud video surveillance and propose a novel fully reversible privacy protection method for H.264/AVC compressed video. All the operations are performed in the compressed domain and avoid lossy re-encoding, so the original H.264/AVC compressed video can be fully recovered. To our best knowledge, the proposed scheme is the first fully reversible one for privacy region protection. Experimental results and performance comparison demonstrate the effectiveness and efficiency of the proposed approach.

Keywords: Cameras; Cloud computing; Discrete cosine transforms; Entropy; Privacy; Video coding; Video surveillance; Cloud-based multimedia application; full reversibility; intra-frame drift error; privacy protection (ID#: 15-8017)


Ribaric, S.; Pavesic, N., "An Overview of Face De-Identification in Still Images and Videos," in Automatic Face and Gesture Recognition (FG), 2015 11th IEEE International Conference and Workshops on, vol. 04, pp. 1-6, 4-8 May 2015. doi: 10.1109/FG.2015.7285017

Abstract: Face-based identification is used in various application scenarios - from identification of a person based on still images in passport or identity card, to identification based on face images captured by a surveillance system without the cooperation of the person. In many application scenarios, especially in video surveillance, privacy can be compromised. One of the approaches to the preservation of privacy is de-identification, where de-identification is the process of concealing or removing personal identifiers, or replacing them with surrogate personal identifiers in personal information, captured in a multimedia content, in order to prevent the disclosure and use of data for purposes unrelated to the purpose for which the information was originally obtained. This paper presents a survey of approaches, methods and solutions for face de-identification in still images and videos.

Keywords: face recognition; video surveillance; face de-identification; identity card; multimedia content; passport; personal information; still images; still videos; surrogate personal identifiers; video surveillance; Cameras; Face; Face detection; Privacy; Real-time systems; Surveillance; Videos (ID#: 15-8018)


Michael, K., "Sousveillance: Implications for Privacy, Security, Trust, and the Law.," in Consumer Electronics Magazine, IEEE, vol. 4, no. 2, pp. 92-94, April 2015. doi: 10.1109/MCE.2015.2393006

Abstract: Point of view has its foundations in film. It usually depicts a scene through the eyes of a character. Body-worn video-recording technologies now mean that a wearer can shoot film from a first-person perspective of another subject or object in his or her immediate field of view (FOV). The term sousveillance has been defined by Steve Mann to denote a recording done from a portable device such as a head-mounted display (HMD) unit in which the wearer is a participant in the activity. Some people call it inverse surveillance because it is the opposite of a camera that is wall mounted and fixed.

Keywords: video recording; video surveillance; FOV; HMD unit; body worn video recording technologies; head mounted display; immediate field of view; portable device; privacy; security; shoot film; sousveillance; trust; Cameras; Computer security; Consumer electronics; Privacy; Surveillance; Trust management; Video recording (ID#: 15-8019)


Babiceanu, R.F.; Bojda, P.; Seker, R.; Alghumgham, M.A., "An Onboard UAS Visual Privacy Guard System," in Integrated Communication, Navigation, and Surveillance Conference (ICNS), 2015, pp. J1-1-J1-8, 21-23 April 2015. doi: 10.1109/ICNSURV.2015.7121232

Abstract: The application areas of Unmanned Aircraft Systems (UAS) are vast. The ever-increasing deployment of UAS is pushed further by advancements and cost effectiveness. It is not uncommon to come across makeshift UAS composed of off-the-shelf components that can be purchased from electronics stores. These components/systems are so easy to obtain and assemble to make homemade UAS, which then can be used by anyone for any purpose seen fit. This paper introduces the first of a set of privacy preserving measures and techniques for UAS applications. The system conceptual design will have a few versions, which the authors will apply in different setting in the subsequent research activities. For the sake of presenting the UAS Visual Privacy Guard system, the authors will use news reporting as an application.

Keywords: autonomous aerial vehicles; data privacy; video surveillance; UAS visual privacy guard system; image processing; unmanned aircraft system; video surveillance; Algorithm design and analysis; Cameras; Lenses; Object recognition; Privacy; Surveillance; Videos (ID#: 15-8020)


Nawaz, T.; Ferryman, J., "An Annotation-Free Method for Evaluating Privacy Protection Techniques in Videos," in Advanced Video and Signal Based Surveillance (AVSS), 2015 12th IEEE International Conference on, pp. 1-6, 25-28 Aug. 2015. doi: 10.1109/AVSS.2015.7301800

Abstract: While several privacy protection techniques are presented in the literature, they are not complemented with an established objective evaluation method for their assessment and comparison. This paper proposes an annotation-free evaluation method that assesses the two key aspects of privacy protection that are privacy and utility. Unlike some existing methods, the proposed method does not rely on the use of subjective judgements and does not assume a specific target type in the image data. The privacy aspect is quantified as an appearance similarity and the utility aspect is measured as a structural similarity between the original raw image data and the privacy-protected image data. We performed an extensive experimentation using six challenging datasets (including two new ones) to demonstrate the effectiveness of the evaluation method by providing a performance comparison of four state-of-the-art privacy protection techniques.

Keywords: data privacy; video surveillance; annotation-free evaluation method; appearance similarity; image data; original raw image data; privacy protection techniques evaluation; video processing; Blanking; Data privacy; Image quality; Positron emission tomography; Privacy; Vehicles; Videos (ID#: 15-8021)


Loughlin, M.; Adnane, A., "Privacy and Trust in Smart Camera Sensor Networks," in Availability, Reliability and Security (ARES), 2015 10th International Conference on, pp. 244-248, 24-27 Aug. 2015. doi: 10.1109/ARES.2015.31

Abstract: The emerging technologies of Smart Camera Sensor Networks (SCSN) are being driven by the social need for security assurance and analytical information. SCSN are deployed for protection and for surveillance tracking of potential criminals. A smart camera sensor does not just capture visual and audio information but covers the whole electromagnetic spectrum. It constitutes of intelligent onboard processor, autonomous communication interfaces, memory and has the ability to execute algorithms. The rapid deployment of smart camera sensors with ubiquitous imaging access causes security and privacy issues for the captured data and its metadata, as well as the need for trust and cooperation between the smart camera sensors. The intelligence growth in this technology requires adequate information security with capable privacy and trust protocols to prevent malicious content attacks. This paper presents, first, a clear definition of SCSN. It addresses current methodologies with perspectives in privacy and trust protection, and proposes a multi-layer security approach. The proposed approach highlights the need for a public key infrastructure layer in association with a Reputation-Based Cooperation mechanism.

Keywords: cameras; cryptographic protocols; data privacy; meta data; public key cryptography; video surveillance; analytical information; autonomous communication interfaces; captured data; information security; intelligent onboard processor; metadata; multilayer security approach; potential criminals; privacy issues; privacy protection; public key infrastructure layer; reputation-based cooperation mechanism; security assurance; security issues; smart camera sensor network; surveillance tracking; trust protection; trust protocols; ubiquitous imaging access; Data privacy; Metadata; Privacy; Security; Smart cameras; Technological innovation; Privacy; Smart Camera Sensor; Trust based reputation (ID#: 15-8022)


Wai Lam Hoo; Miron, A.; Badii, A.; Chee Seng Chan, "Skin-Based Privacy Filter for Surveillance Systems," in Systems, Signals and Image Processing (IWSSIP), 2015 International Conference on, pp. 269-272, 10-12 Sept. 2015. doi: 10.1109/IWSSIP.2015.7314228

Abstract: With surveillance monitoring becoming widely available with the emergence of high resolution cameras, privacy concerns have been raised. One way to achieve privacy protection is by employing a privacy preserving device that can protect persons' identity, but still provide sufficient information to detect anomalous events if necessary. The skin region is important as a Personally Identifying Information (PII) that needs to be obscured if privacy is to be protected. Thus, this paper presents skin detection techniques to conceal privacy sensitive information. However, state-of-the-art skin detection methods suffer from various problems when deployed in a surveillance system. Accordingly, we propose a solution whereby we first find a set of candidate Regions-of-Interest (RoI) and then apply skin detection to the RoI thus found so as to locate the skin. By using this strategy, skin regions can be well delineated to allow targeted privacy filtering without covering the non-RoI parts.

Keywords: image recognition; video surveillance; PII; personally identifying information; privacy sensitive information; regions-of-interest; skin detection; skin-based privacy filter; surveillance system; Cameras; Detection algorithms; Detectors; Privacy; Skin; Surveillance; Visualization; privacy protection systems; skin detection; surveillance (ID#: 15-8023)


Aronoff, J.S.; Simske, S.J.; Rolia, J., "Classification of Patient Movement Events Captured with a 6-Axis Inertial Sensor," in Electrical and Computer Engineering (CCECE), 2015 IEEE 28th Canadian Conference on, pp. 784-791, 3-6 May 2015. doi: 10.1109/CCECE.2015.7129374

Abstract: Patient monitoring is an important part of the overall treatment plan for hospital in-patients. However, monitoring is often time consuming for hospital staff. Staff must either remain in a patient's room, check in on the patient with frequent intervals or remotely monitor the patient via video surveillance. Constant monitoring may be disruptive to the patient as he or she attempts to rest. Furthermore, all of these methods may be considered intrusive to the patient's privacy and time-consuming for hospital staff which may result in increased medical costs. To mitigate these issues, we propose an alternate method of patient monitoring wherein a high-sensitivity 6-axis accelerometer is attached to the patient's hospital bed. Using frequency-series analysis, we can extract relevant patterns for patient movement and train a classifier to identify movement patterns of the patient. Automated monitoring of the patient's movement frees up time for hospital staff. The system can be configured to immediately notify staff when certain events are detected, thereby directing resources to where they are needed most. Event identification accuracy of 90% for a 12-class problem space was achieved.

Keywords: accelerometers; inertial systems; patient monitoring; patient treatment; pattern classification; sensors;6-axis inertial sensor; automated patient monitoring method; frequency-series analysis; high-sensitivity 6-axis accelerometer; hospital in-patients; hospital staff; patient hospital bed; patient movement event classification; patient privacy; patient treatment plan; video surveillance; Accelerometers; Accuracy; Discrete Fourier transforms; Hospitals; Monitoring; Training; Training data (ID#: 15-8024)


Yuan Cao; Le Zhang; Zalivaka, S.S.; Chip-Hong Chang; Shoushun Chen, "CMOS Image Sensor Based Physical Unclonable Function for Coherent Sensor-Level Authentication," in Circuits and Systems I: Regular Papers, IEEE Transactions on, vol. 62, no. 11, pp. 2629-2640, Nov. 2015. doi: 10.1109/TCSI.2015.2476318

Abstract: In the applications of biometric authentication and video surveillance, the image sensor is expected to provide certain degree of trust and resiliency. This paper presents a new low-cost CMOS image sensor based physical unclonable function (PUF) targeting a variety of security, privacy and trusted protocols that involves image sensor as a trusted entity. The proposed PUF exploits the intrinsic imperfection during the image sensor manufacturing process to generate unique and reliable digital signatures. The proposed differential readout stabilizes the response bits extracted from the random fixed pattern noises of selected pixel pairs determined by the applied challenge against supply voltage and temperature variations. The threshold of difference can be tightened to winnow out more unstable response bits from the challenge-response space offered by modern image sensors to enhance the reliability under harsher operating conditions and loosened to improve its resiliency against masquerade attacks in routine operating environment. The proposed design can be classified as a weak PUF which is resilient to modeling attacks, with direct access to its challenge-response pair restricted by the linear feedback shift register. Our experiments on the reset voltages extracted from a 64 x 64 image sensor fabricated in 180 nm 3.3 V CMOS technology demonstrated that robust and reliable challenge-response pairs can be generated with a uniqueness of 49.37% and a reliability of 99.80% under temperature variations of 15 ~ 115 degC and supply voltage variations of 3 ~ 3.6 V.

Keywords: CMOS image sensors; data privacy; integrated circuit noise; integrated circuit reliability; protocols; readout electronics; CMOS image sensor; PUF; biometric authentication; coherent sensor-level authentication; differential readout stability; digital signature; linear feedback shift register; physical unclonable function; random fixed pattern noise; reliability; reset voltage extraction; response bit extraction; security; size 180 nm; temperature 15 degC to 115 degC; trusted protocol; video surveillance; voltage 3 V to 3.6 V; Authentication; CMOS image sensors; Cameras; Noise; Reliability; Threshold voltage; CMOS image sensor; device authentication; physical unclonable function; process variation; random number generator; trusted integrated circuits (ID#: 15-8025)


Jaime, Francisco; Mana, Antonio; Ma, Zhendong; Wagner, Christian; Hovie, Daniel; Bossuet, Mathias, "Building a Privacy Accountable Surveillance System," in Model-Driven Engineering and Software Development (MODELSWARD), 2015 3rd International Conference on, pp. 646-654, 9-11 Feb. 2015. Doi: (not provided)

Abstract: This paper presents a sample surveillance use-case based on a video archive search scenario. Privacy and accountability concerns related to video surveillance systems are identified and described here, thus assessing the impact on privacy of this type of systems. Then, after a description of the scenario, we produce the design for this particular context using the SALT methodology developed by the PARIS project. This methodology follows the privacy-by-design approach and ensures that privacy and accountability concerns are properly taken into account for the system under development. This kind of development entails a series of advantages, not only from the point of view of the subject under surveillance, but also for the other system stakeholders.

Keywords: Cameras; Context; Data privacy; Law; Privacy; S urveillance; System analysis and design; Accountability; Methodology; Privacy; Process; SALT; Scenario; Surveillance (ID#: 15-8026)


Dantcheva, A.; Elia, P.; Ross, A., "What Else Does Your Biometric Data Reveal? A Survey on Soft Biometrics;" in Information Forensics and Security, IEEE Transactions on, vol. PP, no.99, pp.1-1, 22 September 2015. doi: 10.1109/TIFS.2015.2480381

Abstract: Recent research has explored the possibility of extracting ancillary information from primary biometric traits, viz., face, fingerprints, hand geometry and iris. This ancillary information includes personal attributes such as gender, age, ethnicity, hair color, height, weight, etc. Such attributes are known as soft biometrics and have applications in surveillance and indexing biometric databases. These attributes can be used in a fusion framework to improve the matching accuracy of a primary biometric system (e.g., fusing face with gender information), or can be used to generate qualitative descriptions of an individual (e.g., ?young Asian female with dark eyes and brown hair?). The latter is particularly useful in bridging the semantic gap between human and machine descriptions of biometric data. In this paper, we provide an overview of soft biometrics and discuss some of the techniques that have been proposed to extract them from image and video data. We also introduce a taxonomy for organizing and classifying soft biometric attributes, and enumerate the strengths and limitations of these attributes in the context of an operational biometric system. Finally, we discuss open research problems in this field. This survey is intended for researchers and practitioners in the field of biometrics.

Keywords: Accuracy; Bioinformatics; Data mining; Face; Feature extraction; Hair; Iris recognition; Age; Biometrics; Computer Vision; Cosmetics; Ethnicity; Gender; Privacy; Race; Semantics; Soft biometrics; Visual Attributes (ID#: 15-8027)


Jiang, R.; Bouridane, A.; Crookes, D.; Celebi, M.E.; Wei, Hua-Liang, "Privacy-Protected Facial Biometric Verification via Fuzzy Forest Learning," in Fuzzy Systems, IEEE Transactions on , vol. PP, no.99, pp.1-1, October 2015. doi: 10.1109/TFUZZ.2015.2486803

Abstract: Although visual surveillance has emerged as an effective technology for public security, privacy has become an issue of great concern in the transmission and distribution of surveillance videos. For example, personal facial images should not be browsed without permission. To cope with this issue, face image scrambling has emerged as a simple solution for privacy- related applications. Consequently, online facial biometric verification needs to be carried out in the scrambled domain thus bringing a new challenge to face classification. In this paper, we investigate face verification issues in the scrambled domain and propose a novel scheme to handle this challenge. In our proposed method, to make feature extraction from scrambled face images robust, a biased random subspace sampling scheme is applied to construct fuzzy decision trees from randomly selected features, and fuzzy forest decision using fuzzy memberships is then obtained from combining all fuzzy tree decisions. In our experiment, we first estimated the optimal parameters for the construction of the random forest, and then applied the optimized model to the benchmark tests using three publically available face datasets. The experimental results validated that our proposed scheme can robustly cope with the challenging tests in the scrambled domain, and achieved an improved accuracy over all tests, making our method a promising candidate for the emerging privacy-related facial biometric applications.

Keywords: Face; Face recognition; Security; Surveillance; Transforms; Vegetation; Videos; Facial biometrics; chaotic pattern; ensemble learning; face scrambling; fuzzy random forest; privacy (ID#: 15-8028)


Yufeng Wang; Latif, Waqas; Tan, Chiu C.; Yifan Zhang, "Security and Privacy for Body Cameras Used in Law Enforcement," in Communications and Network Security (CNS), 2015 IEEE Conference on, pp.173-181, 28-30 Sept. 2015. doi: 10.1109/CNS.2015.7346826

Abstract: The move towards deploying body cameras for law enforcement personnel makes the security and privacy of these body cameras a pressing problem. Body cameras record police interactions with the public, mainly to provide evidence of potential malicious police actions. However, since these body cameras are deployed and maintained by the police departments themselves, there is lack of trust in the integrity of the footage. Furthermore, the pervasive use of body cameras increases the surveillance of general public, causing a loss of privacy. This paper presents a system that protects the integrity of the body camera videos, as well as protect public privacy. Our approach integrates computer vision techniques onto a resource constrained body camera system, and our evaluation indicates that our approach is feasible to be applied on body cameras.

Keywords: Cameras; Cryptography; Law enforcement; Privacy; Surveillance; Videos (ID#: 15-8029)


Vezzani, R.; Lombardi, M.; Cucchiara, R., "Automatic Configuration and Calibration of Modular Sensing Floors," in Advanced Video and Signal Based Surveillance (AVSS), 2015 12th IEEE International Conference on, pp. 1-6, 25-28 Aug. 2015. doi: 10.1109/AVSS.2015.7301799

Abstract: Sensing floors are becoming an emerging solution for many privacy-compliant and large area surveillance systems. Many research and even commercial technologies have been proposed in the last years. Similarly to distributed camera networks, the problem of calibration is crucial, specially when installed in wide areas. This paper addresses the general problem of automatic calibration and configuration of modular and scalable sensing floors. Working on training data only, the system automatically finds the spatial placement of each sensor module and estimates threshold parameters needed for people detection. Tests on several training sequences captured with a commercial sensing floor are provided to validate the method.

Keywords: calibration; sensor placement; surveillance; wireless sensor networks; distributed camera networks; large area surveillance systems; modular sensing floor calibration; people detection; privacy-compliant systems; sensing floors; sensor placement; Calibration; Ceramics; Floors; Layout; Maximum likelihood detection; Sensors (ID#: 15-8030)


Cunha, P.; Moura, D.C., "A Scalable and Privacy Preserving Approach for Counting Pedestrians in Urban Environment," in Advanced Video and Signal Based Surveillance (AVSS), 2015 12th IEEE International Conference on, pp. 1-6, 25-28 Aug. 2015. doi: 10.1109/AVSS.2015.7301806
Abstract: Understanding the flow of pedestrians in a city is of paramount importance for urban planning. In this paper, we propose a new approach to pedestrian counting based on using low-cost single-board computers that perform all the video analysis locally. This approach has several advantages: i) the impact on the server-side is minimal when the number of devices is increased, ii) communication requirements are low, and iii) people privacy is assured. A foreground detection algorithm based on keypoint detectors is here proposed to handle the low and unsteady frame rates expected under low-spec hardware. Given a single frame, the algorithm delivers a mask of blobs of potential interest. Several image descriptors are extracted for estimating the number of people. A prototype based on the Raspberry Pi platform was built and installed in a pedestrian street of a mid-size city running the proposed method. Experiments were performed both on data from the prototype and on a public dataset. Results show counting accuracy comparable to related work, while achieving frame rates of ~5 frames per second when running on the Raspberry Pi. We conclude that the proposed system is able to deliver frame rates compatible with typical people counting applications at a low cost while assuring privacy and scalability.

Keywords: computer vision; feature extraction; microcomputers; pedestrians; town and country planning; video signal processing; Raspberry Pi platform; foreground detection algorithm; keypoint detectors; low-cost single-board computers; low-spec hardware; pedestrian counting approach; privacy preserving approach; unsteady frame rates; urban environment; urban planning; video analysis; Cameras; Cities and towns; Detectors; Feature extraction; Privacy; Prototypes; Training (ID#: 15-8031)

Bor-Jeng Chen; Medioni, G., "Motion Propagation Detection Association for Multi-Target Tracking in Wide Area Aerial Surveillance," in Advanced Video and Signal Based Surveillance (AVSS), 2015 12th IEEE International Conference on, pp. 1-6, 25-28 Aug. 2015. doi: 10.1109/AVSS.2015.7301766

Abstract: We propose a novel approach to track multiple targets with weak appearance in low frame rate wide area aerial videos. In real world scenarios, non-linear motion such as sharp turns after slowing down or U-shape trajectories occur. Performing accurate matching without introducing undesired trajectories is very challenging. To tackle various motion patterns, we sequentially optimizing an objective function and propagating motion information at each time step in a sliding temporal window. We show how to exploit an optimal short track (tracklet) for each detection in the first frame of each window using dynamic programming. Tracklets obtained in the window are then associated with existing tracks iteratively to form final tracks. We reduce false alarms in background subtraction motion detection with the aid of optical flow. Our system is tested on two challenging datasets. The quantitative evaluation on a long annotated aerial video sequence shows that the proposed approach outperforms state-of-the-art detection and tracking methods in all common axes of evaluation metrics.

Keywords: dynamic programming; motion estimation; target tracking; aerial video sequence; background subtraction motion detection; dynamic programming; motion propagation detection association; multi-target tracking; optimal short track; propagating motion information; sliding temporal window; wide area aerial surveillance; Linear programming; Optimization; Target tracking; Trajectory; Vehicles; Videos (ID#: 15-8032)


Solera, F.; Calderara, S.; Cucchiara, R., "Towards the Evaluation of Reproducible Robustness in Tracking-by-Detection," in Advanced Video and Signal Based Surveillance (AVSS), 2015 12th IEEE International Conference on, pp. 1-6, 25-28 Aug. 2015. doi: 10.1109/AVSS.2015.7301755

Abstract: Conventional experiments on MTT are built upon the belief that fixing the detections to different trackers is sufficient to obtain a fair comparison. In this work we argue how the true behavior of a tracker is exposed when evaluated by varying the input detections rather than by fixing them. We propose a systematic and reproducible protocol and a MATLAB toolbox for generating synthetic data starting from ground truth detections, a proper set of metrics to understand and compare trackers peculiarities and respective visualization solutions.

Keywords: object detection; object tracking; Matlab toolbox; ground truth detection; input detection; reproducible protocol; reproducible robustness; synthetic data generation; systematic protocol; tracking-by-detection; Detectors; Protocols; Robustness; Target tracking; Trajectory (ID#: 15-8033)


Jain, S.; Pilli, E.S.; Govil, M.C.; Rao, D.V., "Performance Evaluation of Congestion-Aware Routing Protocols for Underwater Sensor Networks with Multimedia Data," in Underwater Technology (UT), 2015 IEEE, pp. 1-6, 23-25 Feb. 2015. doi: 10.1109/UT.2015.7108271

Abstract: Performance advancements in acoustic communication technology have fostered to provide technical platform for numerous interdisciplinary applications ranging from bathymetry, hydrographic surveys, disaster prevention, to tactical surveillance over underwater sensor networks (UWSN). Supporting real-time data transmission over error-prone UWSN is increasingly important as these networks become more widely deployed. Existing UWSN routing protocols caters the requirements of non-real time applications where as delay sensitive applications requires solutions that can improve efficiency and reliability, often dynamically throughout the event detection and data transmission session. Congestion control is vital to achieve a high throughput and a long network lifetime. In particular, it is important for a routing protocol to provide congestion control by incorporating metrics like throughput, delay, packet loss ratio, etc. This paper presents a comparative analysis of UWSN routing protocols over real time multimedia data, using H.265/HEVC encoded video sequences. The aim of this study is to extend the in-built support in UWSN routing protocols for transmission of real time data traffic. The applicability of congestion control protocols in UW framework has been explored and the performance characteristics of the protocols have been studied under different multimedia load conditions with varying mobility. This methodology has been illustrated using the case studies in the military and ocean monitoring domains.

Keywords: routing protocols; telecommunication congestion control; telecommunication traffic; underwater acoustic communication; H.265 HEVC encoded video sequences; UWSN routing protocols; acoustic communication technology; congestion control protocols; congestion-aware routing protocols; delay sensitive applications; multimedia data; real time data traffic; underwater sensor networks; Delays; Distributed Bragg reflectors; Multimedia communication; Routing protocols; Streaming media; Wireless sensor networks; Aqua-Sim; Congestion Aware protocols; Congestion protocols; Multimedia traffic; Simulation; UWSN (ID#: 15-8034)


Sharma, L.; Yadav, D.K.; Bharti, S.K., "An Improved Method for Visual Surveillance using Background Subtraction Technique," in Signal Processing and Integrated Networks (SPIN), 2015 2nd International Conference on, pp. 421-426, 19-20 Feb. 2015. doi: 10.1109/SPIN.2015.7095253

Abstract: Moving object detection is an important research area in computer vision. It deals with detecting instances of moving objects of various classes (such as humans, animals, buildings, or vehicles) in digital images and frame sequences for increasing needs of security and surveillance in public or private areas. In this work, proposed improvement enhances the existing model by using some image processing techniques in order to improve detection quality and compared against existing model using metrics like error analysis, precision, recall, f-measure and accuracy. In the existing work, robust estimators were used in order to model an efficient background and then a fast test was used to classify foreground pixel. There were problem of noisy pixels (false detection) due to environmental changes like waving tree leaves, rippling water and lighting effects. The, proposed improvement overcomes the problem of false detection and enhances the detection quality.

Keywords: error analysis; object detection; video surveillance; background subtraction technique; detection quality; false detection; foreground pixel; image processing technique; lighting effect; metrics like error analysis; noisy pixel; rippling water; robust estimator; visual surveillance; waving tree leaves; Accuracy; Adaptation models; Lighting; Object detection; Signal processing; Surveillance; Visualization; Background Modeling; Background Subtraction; Hole filling; Morphological Operator; Moving Object Detection (ID#: 15-8035)


Gardzinski, P.; Kowalak, K.; Kaminski, L.; Mackowiak, S., "Crowd Density Estimation Based on Voxel Model in Multi-View Surveillance Systems," in Systems, Signals and Image Processing (IWSSIP), 2015 International Conference on, pp. 216-219, 10-12 Sept. 2015. doi: 10.1109/IWSSIP.2015.7314215

Abstract: In this paper, a novel crowd density estimation method based on voxel modeling in multi-view surveillance systems is presented. The approach proposed in this paper is based on human silhouette modeling with an anthropometric cylinder. The performance of crowd density estimation was analyzed on two multi-view sequences datasets. For this propose PETS 2006 and PETS 2009 were used. Performance of the proposed approach has been evaluated for two metrics: people counting and crowd classification.

Keywords: image classification; image sequences; video signal processing; video surveillance; PETS 2006;PETS 2009;anthropometric cylinder; crowd classification; crowd density estimation method; human silhouette modeling; multiview sequences datasets; multiview surveillance systems; people counting; voxel modeling; Calibration; Cameras; Chebyshev approximation; Conferences; Estimation; Positron emission tomography; Surveillance; Crowd density estimation; Multi-view; Voxel modeling (ID#: 15-8036)


Soumya, T.; Thampi, S.M., "Day Color Transfer Based Night Video Enhancement for Surveillance System," in Signal Processing, Informatics, Communication and Energy Systems (SPICES), 2015 IEEE International Conference on, pp. 1-5, 19-21 Feb. 2015. doi: 10.1109/SPICES.2015.7091556

Abstract: A dark video captured during night surveillance is insufficient to recognize an action. In order to perform various video analysis operations, a night time video enhancement approach is required. A daytime coloring approach is proposed to improve the visual perception of night video. The day image is down sampled and its color features are applied to the night fusion video. The experimental results are compared with context enhancement fusion methods and objective metrics are used to evaluate the performance of the algorithm. The quality measures show that edge pixel strength and contrast of the surveillance videos are enhanced compared to other methods.

Keywords: image colour analysis; image fusion; video signal processing; video surveillance; visual perception; action recognition; color features; context enhancement fusion methods; dark video capturing; day color transfer; day image; daytime coloring approach; edge pixel contrast; edge pixel strength; night fusion video; night time video enhancement; objective metrics; performance evaluation; surveillance system; video analysis operations; visual perception improvement; Histograms; Image color analysis; Lighting; Mathematical model; Streaming media; Surveillance; Visualization; Color Transfer; Night video Surveillance; Video Enhancement (ID#: 15-8037)



Articles listed on these pages have been found on publicly available internet pages and are cited with links to those pages. Some of the information included herein has been reprinted with permission from the authors or data repositories. Direct any requests via Email to for removal of the links or modifications to specific citations. Please include the ID# of the specific citation in your correspondence.