Causal graph-based video segmentation
This work solves the need for causal and real-time video segmentation in applications like streaming or robotics, though it appears incremental as it builds on a known graph-based method.
The authors tackled the problem of causal video segmentation, where future frames are unknown, by proposing an efficient method that computes temporally consistent superpixels in real-time, addressing a gap in existing graph-based approaches.
Numerous approaches in image processing and computer vision are making use of super-pixels as a pre-processing step. Among the different methods producing such over-segmentation of an image, the graph-based approach of Felzenszwalb and Huttenlocher is broadly employed. One of its interesting properties is that the regions are computed in a greedy manner in quasi-linear time. The algorithm may be trivially extended to video segmentation by considering a video as a 3D volume, however, this can not be the case for causal segmentation, when subsequent frames are unknown. We propose an efficient video segmentation approach that computes temporally consistent pixels in a causal manner, filling the need for causal and real time applications.