Author:
El Khoury Karim,Samelson Jonathan,Macq Benoît
Abstract
The extensive rise of high-definition CCTV camera footage has stimulated both the data compression and the data analysis research fields. The increased awareness of citizens to the vulnerability of their private information, creates a third challenge for the video surveillance community that also has to encompass privacy protection. In this paper, we aim to tackle those needs by proposing a deep learning-based object tracking solution via compressed domain residual frames. The goal is to be able to provide a public and privacy-friendly image representation for data analysis. In this work, we explore a scenario where the tracking is achieved directly on a restricted part of the information extracted from the compressed domain. We utilize exclusively the residual frames already generated by the video compression codec to train and test our network. This very compact representation also acts as an information filter, which limits the amount of private information leakage in a video stream. We manage to show that using residual frames for deep learning-based object tracking can be just as effective as using classical decoded frames. More precisely, the use of residual frames is particularly beneficial in simple video surveillance scenarios with non-overlapping and continuous traffic.
Reference38 articles.
1. Block Matching Algorithms for Motion Estimation;Barjatya;Final Project Paper for Spring 2004 Digital Image Processing Course at the Utah State Univ.,2004
2. Evaluating Multiple Object Tracking Performance: The clear Mot Metrics;Bernardin;EURASIP J. Image Video Process.,2008
3. Simple Online and Realtime Tracking;Bewley,2016
4. High-speed Tracking-By-Detection without Using Image Information;Bochinski,2017
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献