KLI

A Lightweight Attention Fusion Module for Multi-sensor 3-D Object Detection

Metadata Downloads
Abstract
With the rapid development of autonomous vehicles, three-dimensional (3D) object detection has become more important, whose purpose is to perceive the size and accurate location of objects in the real world. Many kinds of LiDAR-camera-based 3D object detectors have been developed with two heavy neural networks to extract view-specific features, while a LiDAR-camera-based 3D detector runs very slow about 10 frames per second (FPS). To tackle this issue, this paper first presents an accuracy and efficiency multiple-sensor framework with an early-fusion method to exploit both LiDAR and camera data for fast 3D object detection. Moreover, we also present a lightweight attention fusion module to further improve the performance of our proposed framework. Massive experiments evaluated on the KITTI benchmark suite show that the proposed approach outperforms state-of-the-art LiDAR-camera-based methods on the three classes in 3D performance. Additionally, the proposed model runs at 23 frames per second (FPS), which is almost 2×?faster than state-of-the-art fusion methods for LiDAR and camera.
Author(s)
문리화Ting-Yue Xu조강현
Issued Date
2021
Type
Article
Keyword
Early-fusion methodLiDAR and cameraMultiple sensorThree-dimensional object detection
DOI
10.1007/978-3-030-84522-3_65
URI
https://oak.ulsan.ac.kr/handle/2021.oak/9161
https://ulsan-primo.hosted.exlibrisgroup.com/primo-explore/fulldisplay?docid=TN_cdi_springer_books_10_1007_978_3_030_84522_3_65&context=PC&vid=ULSAN&lang=ko_KR&search_scope=default_scope&adaptor=primo_central_multiple_fe&tab=default_tab&query=any,contains,A%20Lightweight%20Attention%20Fusion%20Module%20for%20Multi-sensor%203-D%20Object%20Detection&offset=0&pcAvailability=true
Publisher
Lecture Notes in Computer Science
Location
스위스
Language
영어
ISSN
0302-9743
Citation Volume
12836
Citation Number
1
Citation Start Page
802
Citation End Page
815
Appears in Collections:
Engineering > IT Convergence
Authorize & License
  • Authorize공개
Files in This Item:
  • There are no files associated with this item.

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.