Multi-Channel Convolutional Neural Network Based 3D Object Detection for Indoor Robot Environmental Perception.

Li Wang¹, Ruifeng Li², Hezi Shi³, Jingwen Sun⁴, Lijun Zhao⁵, Hock Soon Seah⁶, Chee Kwang Quah⁷, Budianto Tandianus⁸

¹State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin 150001, China. 15b908017@hit.edu.cn.

²State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin 150001, China. lrf100@hit.edu.cn.

³EON Reality Pte Ltd, Singapore 138567, Singapore. hezi.shi@eonreality.com.

⁴State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin 150001, China. 18S008061@stu.hit.edu.cn.

⁵State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin 150001, China. zhaolj@hit.edu.cn.

⁶School of Computer Science and Engineering, Nanyang Technological University, Singapore 639798, Singapore. ashsseah@ntu.edu.sg.

⁷ST Electronics (Training & Simulation Systems) Pte Ltd, Singapore 567714, Singapore. quah.cheekwang@stee.stengg.com.

⁸ST Engineering-NTU Corporate Laboratory, School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 637335, Singapore. btandianus@ntu.edu.sg.

PubMed PMC DOI PDF

Abstract

Environmental perception is a vital feature for service robots when working in an indoor environment for a long time. The general 3D reconstruction is a low-level geometric information description that cannot convey semantics. In contrast, higher level perception similar to humans requires more abstract concepts, such as objects and scenes. Moreover, the 2D object detection based on images always…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Mentioned Companies

EON Reality
affiliation

Other Funding

National Natural Science Foundation of China(61673136)
Self-Planned Task of State Key Laboratory of Robotics and System (HIT)(NO. SKLRS201715A, NO. SKLRS201609B)
the Foundation for Innovative Research Groups of the National Natural Science Foundation of China(No.51521003)
the ST Engineering-NTU Corporate Lab through the NRF corporate lab@ university scheme(SRP4)
the China Scholarship Council(201706120137)

Keywords

3D object detectionenvironmental perceptionindoor robotmulti-channel CNN

Article Info

PMID: 30795507
PMCID: PMC6412344
DOI: 10.3390/s19040893
Received: January 4, 2019
Accepted: February 14, 2019

How to Cite

Wang L et al. Multi-Channel Convolutional Neural Network Based 3D Object Detection for Indoor Robot Environmental Perception. Sensors (Basel)2019;19(4) doi:10.3390/s19040893

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.