Group‐Based Atrous Convolution Stereo Matching Network

Abstract

Stereo matching is the key technology in stereo vision. Given a pair of rectified images, stereo matching determines correspondences between the pair images and estimate depth by obtaining disparity between corresponding pixels. The current work has shown that depth estimation from a stereo pair of images can be formulated as a supervised learning task with an end-to-end frame based on convolutional neural networks (CNNs). However, 3D CNN puts a great burden on memory storage and computation, which further leads to the significantly increased computation time. To alleviate this issue, atrous convolution was proposed to reduce the number of convolutional operations via a relatively sparse receptive field. However, this sparse receptive field makes it difficult to find reliable corresponding points in fuzzy areas, e.g., occluded areas and untextured areas, owing to the loss of rich contextual information. To address this problem, we propose the Group-based Atrous Convolution Spatial Pyramid Pooling (GASPP) to robustly segment objects at multiple scales with affordable computing resources. The main feature of the GASPP module is to set convolutional layers with continuous dilation rate in each group, so that it can reduce the impact of holes introduced by atrous convolution on network performance. Moreover, we introduce a tailored cascade cost volume in a pyramid form to reduce memory, so as to meet real-time performance. The group-based atrous convolution stereo matching network is evaluated on the street scene benchmark KITTI 2015 and Scene Flow and achieves state-of-the-art performance.

Multi-Scale Aggregation Stereo Matching Network Based on Dense Grouping Atrous Convolution

“…Atrous convolution is a method of increasing the receptive field without increasing the computation or reducing the resolution of the feature map [10,11]. In atrous convolution, the receptive field refers to the size of the area mapped from the original image by pixels in the feature map output by each layer of the convolution neural network [10], and the size of the receptive field is closely related to the dilation rate.…”

“…In order to obtain a sufficiently large receptive field in the ASPP method, a sufficiently large dilation rate must be used; however, as the dilation rate increases, the network gradually loses its modeling ability. Taking this into account, the DenseASPP [10] and GASPP [11] methods combine the advantages of the parallel and cascade use of void convolutional layers to obtain larger receptive fields and denser features, and thus improve the recognition ability of the algorithm when the target proportion changes. Although the above methods increase the receptive field to a certain extent, there is not enough attention paid to the contextual information.…”

Automatic Cutting System Design of Robot Hand Based on Stereo Vision

“…e camera system is a multicamera stereo vision system [17][18][19][20][21][22][23][24][25][26][27][28][29] composed of 4 infrared cameras, which can measure the object's coordinates in 3D space. Calibration software and calibration devices are provided by the manufacturer.…”