Cross-view detection of crowded objects based on multi-sensor fusion

This proposal introduces a fusion detection method of color camera and LiDAR, which can achieve more ideal detection and tracking performance under limited computational resources, and explores a joint fusion detection method deployed on multiple robots, which can improve the detection performance o...

Full description

Saved in:
Bibliographic Details
Main Author: Gu, Zhipeng
Other Authors: Wang Dan Wei
Format: Thesis-Master by Coursework
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/177655
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:This proposal introduces a fusion detection method of color camera and LiDAR, which can achieve more ideal detection and tracking performance under limited computational resources, and explores a joint fusion detection method deployed on multiple robots, which can improve the detection performance of multiple robots. Traditional methods are limited by single-sensor constraints, high com putational requirements, and poor real-time performance. The proposed fusion method significantly improves detection accuracy and reliability, and solves the problem of data discrepancy and interference between sensors and robots. This approach is valuable for advancing single robots as well as multiple robots in various applications