A Depth Order Reasoning Method Based on Objects in Monocular Images

Abstract

The invention provides a depth order inference method for an object in a monocular image, which comprises the steps of extracting an over-segmentation image, acquiring over-segmentation edges, extracting shielded edge features, performing feature subspace learning, classifying the edges by using a ridge regression model, performing semi-local depth order inference and performing global depth order inference. According to the invention, shielded edges are detected through using a sparse coding based classifier, the time and the space are saved, and the calculation efficiency is improved; a new triple description operator is adopted, and shielded edge description is performed by taking an edge and angular points at two ends as a clue, thereby realizing close contact of points between edges; a kernel function ridge regression model is adopted to further acquire a most reliable edge probability graph, and the shielded edges are extracted, thereby providing enough clues for depth order inference; and the process of global depth order inference is transformed into a directed graph model through modeling, and problem solving is transformed into a problem of solving an effective path of the directed graph.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a depth order reasoning method based on objects in a monocular image. Background technique [0002] The problem of depth order reasoning for objects in monocular images has been discussed from various perspectives, such as foreground and background segmentation, depth segmentation, and occlusion recovery. The reasoning method can be briefly described as dividing the image into non-overlapping regions and then sorting these regions hierarchically according to the occlusion relationship. [0003] The detection of occluded edges plays a crucial role in the depth order inference process. The reported edge detection method: gPb-OWT-UCM, gives the probability of whether each pixel is an edge. However, due to the complex properties of natural scenes, occluded edges cannot be well preserved during image segmentation. Traditional edge cues such as T-corner and concavity are often used to...

AI Technical Summary

Problems solved by technology

Because of the fusion of multiple features, the features are very rich, but there is redundancy

Images