Object Detection and Semantic Segmentation Methods for RGB-D Images Using Deep Convolutional Networks

Abstract

The invention discloses an object detection and semantic segmentation method of an RGB-D image based on a deep convolutional network, and belongs to the field of deep learning and machine vision. In the technical solution adopted in this method, Faster-RCNN is used to replace the original slow RCNN. Faster-RCNN not only has a fast speed in extracting features by using GPU, but also can generate regional schemes in the network at the same time, which can realize the whole training process is end-to-end At the same time, FCN is used to perform semantic segmentation of RGB-D images. FCN uses GPU and deep convolutional network to quickly extract deep features of images, and uses deconvolution operations to fuse deep features and shallow features of image convolution. The local semantic information of the image is integrated into the global semantic information.

Description

technical field [0001] The invention belongs to the field of deep learning and machine vision, and in particular relates to an object detection and semantic segmentation method including RGB-D images, which has a very wide range of applications in real scenes, such as detecting and tracking pedestrians in surveillance videos, UAV navigation, automatic driving, etc. Background technique [0002] Object detection and semantic segmentation are two important research fields of computer vision. Object detection is mainly used to detect the position and category of objects in the image. There are two main tasks in object detection. One is to find out the region scheme of the object (Region Proposals), the regional scheme is a pre-selected frame, which represents the approximate position of an object in the image; the second is to classify the objects in the pre-selected frame. The problem solved by semantic segmentation is to assign the correct label to each pixel of the image. S...

AI Technical Summary

Problems solved by technology

In the process of semantic segmentation, the superpixel-based depth features (globe-centered pose) and geometric features (size, shape) use support vector machines to predict the category labels of superpixels, but this method is very slow and uses multi-scale combination The method of grouping generates a regional plan is a very slow process, using slow and redundant RCNN, training is divided into multiple pipeline stages, and calculating the characteristics of superpixels is a complex and slow process

Images