期刊
SIGNAL IMAGE AND VIDEO PROCESSING
卷 17, 期 4, 页码 991-999出版社
SPRINGER LONDON LTD
DOI: 10.1007/s11760-022-02303-2
关键词
Convolutional neural network; Depth estimation; Monocular vision; Self-supervised algorithm
A self-supervised algorithm based on deep learning is designed to estimate the depth of the driving scene. The algorithm utilizes the video information from a monocular camera to train the depth estimation network and pose estimation network. The algorithm addresses the issues of scale inconsistency and occlusion in the driving environment using view synthesis and scale consistency loss. The results show that the algorithm achieves high accuracy on the KITTI dataset.
A self-supervised algorithm based on deep learning is designed to estimate the depth of the driving scene. The depth estimation network and pose estimation network designed based on convolutional neural network take the video information obtained by monocular camera as the input, and output the depth map of each frame of input image and the pose changes between two adjacent frames of input images, respectively. The view synthesis, that is, the image reconstruction loss between two adjacent frame images, is used as the supervision signal to train the neural network. The problem of scale inconsistency in monocular depth estimation is solved through the scale consistency loss, and the weight mask obtained from the scale inconsistency loss is used to solve the dynamic problems and the adverse effects of occluded objects in driving environment. The tests results show that the designed self-supervised depth estimation algorithm based on monocular video information shows high accuracy on the KITTI dataset and almost reaches the same level as the supervised algorithm.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据