Surveillance Video Parsing with Single Frame Supervision
This addresses the tedious and inefficient pixel-wise annotation problem for surveillance video parsing, offering a more practical solution for applications like security monitoring.
The paper tackles the problem of reducing annotation effort for surveillance video parsing by proposing a method that requires only one labeled frame per video, achieving superior performance over state-of-the-art methods on two datasets.
Surveillance video parsing, which segments the video frames into several labels, e.g., face, pants, left-leg, has wide applications. However,pixel-wisely annotating all frames is tedious and inefficient. In this paper, we develop a Single frame Video Parsing (SVP) method which requires only one labeled frame per video in training stage. To parse one particular frame, the video segment preceding the frame is jointly considered. SVP (1) roughly parses the frames within the video segment, (2) estimates the optical flow between frames and (3) fuses the rough parsing results warped by optical flow to produce the refined parsing result. The three components of SVP, namely frame parsing, optical flow estimation and temporal fusion are integrated in an end-to-end manner. Experimental results on two surveillance video datasets show the superiority of SVP over state-of-the-arts.