| Title | MOTrack: Real-time Configuration Adaptation for Video Analytics through Movement Tracking |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Wu, Fubao, Gao, Lixin, Zhou, Tian, Wang, Xi |
| Conference Name | 2021 IEEE Global Communications Conference (GLOBECOM) |
| Date Published | dec |
| Keywords | Costs, Deep Learning, deep video, machine learning, Metrics, Neural networks, object tracking, pubcrawl, resilience, Resiliency, Scalability, Streaming media, Switches, Traffic Control, video analytics, video stream, visual analytics |
| Abstract | Video analytics has many applications in traffic control, security monitoring, action/event analysis, etc. With the adoption of deep neural networks, the accuracy of video analytics in video streams has been greatly improved. However, deep neural networks for performing video analytics are compute-intensive. In order to reduce processing time, many systems switch to the lower frame rate or resolution. State-of-the-art switching approaches adjust configurations by profiling video clips on a large configuration space. Multiple configurations are tested periodically and the cheapest one with a desired accuracy is adopted. In this paper, we propose a method that adapts the configuration by analyzing past video analytics results instead of profiling candidate configurations. Our method adopts a lower/higher resolution or frame rate when objects move slow/fast. We train a model that automatically selects the best configuration. We evaluate our method with two real-world video analytics applications: traffic tracking and pose estimation. Compared to the periodic profiling method, our method achieves 3%-12% higher accuracy with the same resource cost and 8-17x faster with comparable accuracy. |
| DOI | 10.1109/GLOBECOM46510.2021.9685159 |
| Citation Key | wu_motrack_2021 |
MOTrack: Real-time Configuration Adaptation for Video Analytics through Movement Tracking