MESD: Exploring Optical Flow Assessment on Edge of Motion Objects with Motion Edge Structure Difference
This work addresses a specific challenge in computer vision for evaluating optical flow algorithms, but it is incremental as it proposes a supplementary metric rather than a fundamental breakthrough.
The paper tackles the problem of assessing optical flow estimation errors specifically on the edges of moving objects, proposing a method called MESD that shows reasonable and discriminative assessment in experiments on four benchmarks.
The optical flow estimation has been assessed in various applications. In this paper, we propose a novel method named motion edge structure difference(MESD) to assess estimation errors of optical flow fields on edge of motion objects. We implement comparison experiments for MESD by evaluating five representative optical flow algorithms on four popular benchmarks: MPI Sintel, Middlebury, KITTI 2012 and KITTI 2015. Our experimental results demonstrate that MESD can reasonably and discriminatively assess estimation errors of optical flow fields on motion edge. The results indicate that MESD could be a supplementary metric to existing general assessment metrics for evaluating optical flow algorithms in related computer vision applications.