An adaptive network fusing light detection and ranging height-sliced bird’s-eye view and vision for place recognition

Place recognition, a fundamental component of robotic perception, aims to identify previously visited locations within an environment. In this study, we present a novel global descriptor that uses height-sliced Bird’s Eye View (BEV) from Light Detection and Ranging (LiDAR) and vision images, to faci...

Full description

Saved in:
Bibliographic Details
Main Authors: ZHENG, Rui, JIANG, Zuo, YE, Yibin, REN, Yang, ZENG, Hui, LI, Junwei, ZHANG, Zhiyuan
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2024
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/9310
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-10310
record_format dspace
spelling sg-smu-ink.sis_research-103102024-09-21T15:24:02Z An adaptive network fusing light detection and ranging height-sliced bird’s-eye view and vision for place recognition ZHENG, Rui JIANG, Zuo YE, Yibin REN, Yang ZENG, Hui LI, Junwei ZHANG, Zhiyuan Place recognition, a fundamental component of robotic perception, aims to identify previously visited locations within an environment. In this study, we present a novel global descriptor that uses height-sliced Bird’s Eye View (BEV) from Light Detection and Ranging (LiDAR) and vision images, to facilitate high-recall place recognition in autonomous driving field. Our descriptor generation network, incorporates an adaptive weights generation branch to learn weights of visual and LiDAR features, enhancing its adaptability to different environments. The generated descriptor exhibits excellent yaw-invariance. The entire network is trained using a self-designed quadruplet loss, which discriminates inter-class boundaries and alleviates overfitting to one particular modality. We evaluate our approach on three benchmarks derived from two public datasets and achieve optimal performance on these evaluation sets. Our approach demonstrates excellent generalization ability and efficient runtime, which are indicative of its practical viability in real-world scenarios. For those interested in applying this Artificial Intelligence contribution to engineering, the implementation of our approach can be found at: https://github.com/Bryan-ZhengRui/LocFuse 2024-09-05T07:00:00Z text https://ink.library.smu.edu.sg/sis_research/9310 info:doi/10.1016/j.engappai.2024.109230 Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Multi-modal place recognition Deep learning method Sensor fusion Autonomous driving Artificial Intelligence and Robotics Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Multi-modal place recognition
Deep learning method
Sensor fusion Autonomous driving
Artificial Intelligence and Robotics
Graphics and Human Computer Interfaces
spellingShingle Multi-modal place recognition
Deep learning method
Sensor fusion Autonomous driving
Artificial Intelligence and Robotics
Graphics and Human Computer Interfaces
ZHENG, Rui
JIANG, Zuo
YE, Yibin
REN, Yang
ZENG, Hui
LI, Junwei
ZHANG, Zhiyuan
An adaptive network fusing light detection and ranging height-sliced bird’s-eye view and vision for place recognition
description Place recognition, a fundamental component of robotic perception, aims to identify previously visited locations within an environment. In this study, we present a novel global descriptor that uses height-sliced Bird’s Eye View (BEV) from Light Detection and Ranging (LiDAR) and vision images, to facilitate high-recall place recognition in autonomous driving field. Our descriptor generation network, incorporates an adaptive weights generation branch to learn weights of visual and LiDAR features, enhancing its adaptability to different environments. The generated descriptor exhibits excellent yaw-invariance. The entire network is trained using a self-designed quadruplet loss, which discriminates inter-class boundaries and alleviates overfitting to one particular modality. We evaluate our approach on three benchmarks derived from two public datasets and achieve optimal performance on these evaluation sets. Our approach demonstrates excellent generalization ability and efficient runtime, which are indicative of its practical viability in real-world scenarios. For those interested in applying this Artificial Intelligence contribution to engineering, the implementation of our approach can be found at: https://github.com/Bryan-ZhengRui/LocFuse
format text
author ZHENG, Rui
JIANG, Zuo
YE, Yibin
REN, Yang
ZENG, Hui
LI, Junwei
ZHANG, Zhiyuan
author_facet ZHENG, Rui
JIANG, Zuo
YE, Yibin
REN, Yang
ZENG, Hui
LI, Junwei
ZHANG, Zhiyuan
author_sort ZHENG, Rui
title An adaptive network fusing light detection and ranging height-sliced bird’s-eye view and vision for place recognition
title_short An adaptive network fusing light detection and ranging height-sliced bird’s-eye view and vision for place recognition
title_full An adaptive network fusing light detection and ranging height-sliced bird’s-eye view and vision for place recognition
title_fullStr An adaptive network fusing light detection and ranging height-sliced bird’s-eye view and vision for place recognition
title_full_unstemmed An adaptive network fusing light detection and ranging height-sliced bird’s-eye view and vision for place recognition
title_sort adaptive network fusing light detection and ranging height-sliced bird’s-eye view and vision for place recognition
publisher Institutional Knowledge at Singapore Management University
publishDate 2024
url https://ink.library.smu.edu.sg/sis_research/9310
_version_ 1814047877346885632