Monocular Depth-Ordering Reasoning with Occlusion Edge Detection and Couple Layers Inference

Abstract

A depth-ordering reasoning approach first provides novel occlusion edge detection, generating precise same-layer relationship judgment and producing reliable region proposals for the depth-ordering inference. Specifically, a novel sparsity-induced regression model learns a discriminative feature subspace. In addition, kernel ridge regression assigns the occlusion label for each edge. The kernel trick guarantees linearly separable edges in a rich, high-dimensional feature space. Secondly, a couple layers inference approach infers the final depth order. In the semilocal layer, a novel triple descriptor judges the foreground relationship. In the global layer, the inference is executed by finding a valid path on a directed graph model. The proposed approach is validated on the Cornell depth-order and NYU 2 datasets.