Exploiting depth from single monocular images for object detection and semantic segmentation

Cao, Yuanzhouhan, Shen, Chunhua and Shen, Heng Tao (2017) Exploiting depth from single monocular images for object detection and semantic segmentation. IEEE Transactions on Image Processing, 26 2: 836-846. doi:10.1109/TIP.2016.2621673


Author Cao, Yuanzhouhan
Shen, Chunhua
Shen, Heng Tao
Title Exploiting depth from single monocular images for object detection and semantic segmentation
Journal name IEEE Transactions on Image Processing   Check publisher's open access policy
ISSN 1057-7149
1941-0042
Publication date 2017-02-01
Sub-type Article (original research)
DOI 10.1109/TIP.2016.2621673
Open Access Status Not yet assessed
Volume 26
Issue 2
Start page 836
End page 846
Total pages 11
Place of publication Piscataway, NJ, United States
Publisher Institute of Electrical and Electronics Engineers
Collection year 2018
Language eng
Abstract Augmenting RGB data with measured depth has been shown to improve the performance of a range of tasks in computer vision, including object detection and semantic segmentation. Although depth sensors such as the Microsoft Kinect have facilitated easy acquisition of such depth information, the vast majority of images used in vision tasks do not contain depth information. In this paper, we show that augmenting RGB images with estimated depth can also improve the accuracy of both object detection and semantic segmentation. Specifically, we first exploit the recent success of depth estimation from monocular images and learn a deep depth estimation model. Then, we learn deep depth features from the estimated depth and combine with RGB features for object detection and semantic segmentation. In addition, we propose an RGB-D semantic segmentation method, which applies a multi-task training scheme: Semantic label prediction and depth value regression. We test our methods on several data sets and demonstrate that incorporating information from estimated depth improves the performance of object detection and semantic segmentation remarkably.
Keyword Deep networks
Depth estimation
Object detection
Semantic segmentation
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status UQ

Document type: Journal Article
Sub-type: Article (original research)
Collections: HERDC Pre-Audit
School of Information Technology and Electrical Engineering Publications
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Tue, 28 Mar 2017, 00:20:19 EST by Web Cron on behalf of Learning and Research Services (UQ Library)