pROST : A Smoothed Lp-norm Robust Online Subspace Tracking Method for Realtime Background Subtraction in Video
This is an incremental improvement for real-time video analysis, particularly useful in degraded conditions like camera jitter.
The authors tackled background subtraction in video by developing pROST, a method using a smoothed Lp-norm for robust online subspace tracking, which outperforms competing approaches in scenarios with camera jitter.
An increasing number of methods for background subtraction use Robust PCA to identify sparse foreground objects. While many algorithms use the L1-norm as a convex relaxation of the ideal sparsifying function, we approach the problem with a smoothed Lp-norm and present pROST, a method for robust online subspace tracking. The algorithm is based on alternating minimization on manifolds. Implemented on a graphics processing unit it achieves realtime performance. Experimental results on a state-of-the-art benchmark for background subtraction on real-world video data indicate that the method succeeds at a broad variety of background subtraction scenarios, and it outperforms competing approaches when video quality is deteriorated by camera jitter.