跳到主要导航 跳到搜索 跳到主要内容

Detection and Depth Estimation for Objects from Single Monocular Image

  • Beihang University

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

This paper addresses the problem of detecting and estimating depth for objects given a single monocular RGB image. We propose a integrative network to implement multiple tasks of detection and depth estimation at the same time and realize the rate of 6 fps. We use convolutional neural network to extract features and fully connection network to generate depth straightway and evaluate the performance of our model on KITTY. To adapt the model to multiple range scales of objects, we rectify the loss function and further improve the performance of our model.

源语言英语
主期刊名Proceedings of 2020 Chinese Intelligent Systems Conference - Volume I
编辑Yingmin Jia, Weicun Zhang, Yongling Fu
出版商Springer Science and Business Media Deutschland GmbH
27-35
页数9
ISBN(印刷版)9789811584497
DOI
出版状态已出版 - 2021
活动Chinese Intelligent Systems Conference, CISC 2020 - Shenzhen, 中国
期限: 24 10月 202025 10月 2020

出版系列

姓名Lecture Notes in Electrical Engineering
705 LNEE
ISSN(印刷版)1876-1100
ISSN(电子版)1876-1119

会议

会议Chinese Intelligent Systems Conference, CISC 2020
国家/地区中国
Shenzhen
时期24/10/2025/10/20

指纹

探究 'Detection and Depth Estimation for Objects from Single Monocular Image' 的科研主题。它们共同构成独一无二的指纹。

引用此