Trajectory Ensemble: Multiple Persons Consensus Tracking Across Non-Overlapping Multiple Cameras Over Randomly Dropped Camera Networks

Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 56-62

Multiple person tracking over a camera network is usually performed by matching person images between adjacent cameras. It easily fails by a temporal appearance change of the persons caused by environmental illumination and observation orientation of a camera. To solve this problem, matching person images across not only adjacent cameras but also cameras multiple hops away in the camera network is effective, however, such relaxation of spatio-temporal cues also cause tracking failure due to the increase of matching candidates. To avoid the failure, we introduce "Random Camera Drop" to generate different camera networks which relax the spatio-temporal cues partially and randomly. And we integrate tracking results over the networks to a consensus tracking result by a novel concept "Trajectory Ensemble", an extension of unsupervised ensemble learning for the multiple person tracking over a camera network problem. We evaluated the framework on several virtual datasets generated from a public dataset, "Shinpuhkan 2014 dataset" and confirmed that the proposed method achieve the highest tracking results among some comparative methods.