Visible to the public Fully Automatic, Real-Time Vehicle Tracking for Surveillance Video

TitleFully Automatic, Real-Time Vehicle Tracking for Surveillance Video
Publication TypeConference Paper
Year of Publication2017
AuthorsJin, Y., Eriksson, J.
Conference Name2017 14th Conference on Computer and Robot Vision (CRV)
KeywordsAdaptive optics, automatic object tracking system, automatic tracker initialization, Detectors, fully automatic vehicle tracking, Human Behavior, illumination conditions, image sequences, lighting, manual initialization, multiple unstable video, Noise measurement, object detection, object tracking, object tracking framework, Optical imaging, Optical variables measurement, pubcrawl, real-time vehicle tracking, real-world object variation, Resiliency, Scalability, state-of-the-art trackers, traffic engineering computing, traffic surveillance videos, video signal processing, video surveillance

We present an object tracking framework which fuses multiple unstable video-based methods and supports automatic tracker initialization and termination. To evaluate our system, we collected a large dataset of hand-annotated 5-minute traffic surveillance videos, which we are releasing to the community. To the best of our knowledge, this is the first publicly available dataset of such long videos, providing a diverse range of real-world object variation, scale change, interaction, different resolutions and illumination conditions. In our comprehensive evaluation using this dataset, we show that our automatic object tracking system often outperforms state-of-the-art trackers, even when these are provided with proper manual initialization. We also demonstrate tracking throughput improvements of 5x or more vs. the competition.

Citation Keyjin_fully_2017