Entropy-difference based stereo error detection
This work addresses the need for reliable error detection in stereo depth estimation, which is crucial for applications like robotics and autonomous driving, though it is incremental in improving confidence measures.
The paper tackles the problem of error detection in stereo depth estimation by proposing a novel confidence measure based on entropy differences between the input image and its depth map, achieving superior performance over 17 existing measures on the Middlebury dataset.
Stereo depth estimation is error-prone; hence, effective error detection methods are desirable. Most such existing methods depend on characteristics of the stereo matching cost curve, making them unduly dependent on functional details of the matching algorithm. As a remedy, we propose a novel error detection approach based solely on the input image and its depth map. Our assumption is that, entropy of any point on an image will be significantly higher than the entropy of its corresponding point on the image's depth map. In this paper, we propose a confidence measure, Entropy-Difference (ED) for stereo depth estimates and a binary classification method to identify incorrect depths. Experiments on the Middlebury dataset show the effectiveness of our method. Our proposed stereo confidence measure outperforms 17 existing measures in all aspects except occlusion detection. Established metrics such as precision, accuracy, recall, and area-under-curve are used to demonstrate the effectiveness of our method.