東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

High-Fidelity Vehicle Detection, Pos...

Cao, Jiahe.

Linked to FindBook

Google Book

Amazon

博客來

High-Fidelity Vehicle Detection, Positioning and Tracking With Infrastructure-Based Fisheye Cameras.

Record Type:	Electronic resources : Monograph/item
Title/Author:	High-Fidelity Vehicle Detection, Positioning and Tracking With Infrastructure-Based Fisheye Cameras./
Author:	Cao, Jiahe.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2023,
Description:	84 p.
Notes:	Source: Masters Abstracts International, Volume: 85-04.
Contained By:	Masters Abstracts International85-04.
Subject:	Electrical engineering. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30312536
ISBN:	9798380602228

High-Fidelity Vehicle Detection, Positioning and Tracking With Infrastructure-Based Fisheye Cameras.
Cao, Jiahe.

High-Fidelity Vehicle Detection, Positioning and Tracking With Infrastructure-Based Fisheye Cameras. - Ann Arbor : ProQuest Dissertations & Theses, 2023 - 84 p.

Source: Masters Abstracts International, Volume: 85-04.

Thesis (M.S.)--University of California, Riverside, 2023.

With the development of the city scale, a more high-efficient traffic system is needed. Thus, the Intelligent Transport System (ITS) is proposed. This system aims to provide innovative services relating to different modes of transport and traffic management and enable users to be better informed and make safer, more coordinated, and 'smarter' use of transport networks. This thesis focuses on the detection based on Infrastructure camera sensors, especially the fisheye camera. Two different methods are designed for this problem, the first one is a traditional method based on Background Subtraction. This method is verified at the intersection of University Ave and Chicago Ave, in Riverside, California, and in the CARLA simulator. It successfully detects vehicles the whole day regardless of the illumination weather and change. At the same time, a real-world vehicle dataset is collected for the second route. Also, in the CARLA experiment, our method significantly achieves improvement in terms of MOTA (multiple object tracking accuracy) and MOTP (multiple objects tracking precision). In the most complex scenario, our method outperforms the SOTA by 6.22\\% on MOTP and 1.71 pixels on MOTA. For the second route which is deep learning, there have been many efforts to apply deep learning to fisheye camera detection, but without a solid and large-scale fisheye image dataset, the neural network always has a bad detection performance. Thus, the second method tries to create a dataset that looks like the real world but is generated in a simulator (CARLA) to dismiss this problem. A real-world style dataset with ground truth labels is generated by modified AttentionGAN. Then deep learning object detection methods could be directly trained on the generated dataset. This project adopts YOLOV5 as the detection network. The final experiment result shows the trained network is able to detect all vehicles in verify part of the generated dataset and part of vehicles in the real-world dataset.

ISBN: 9798380602228Subjects--Topical Terms:

649834
Electrical engineering.
Subjects--Index Terms:

AI generated content

High-Fidelity Vehicle Detection, Positioning and Tracking With Infrastructure-Based Fisheye Cameras.
LDR:03274nmm a2200421 4500 001 2398137
005 20240812064347.5
006 m o d
007 cr#unu||||||||
008 251215s2023 ||||||||||||||||| ||eng d
020 $a 9798380602228
035 $a (MiAaPQ)AAI30312536
035 $a AAI30312536
040 $a MiAaPQ $c MiAaPQ
100 1 $a Cao, Jiahe. $3 3768047
245 1 0 $a High-Fidelity Vehicle Detection, Positioning and Tracking With Infrastructure-Based Fisheye Cameras.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 84 p.
500 $a Source: Masters Abstracts International, Volume: 85-04.
500 $a Advisor: Barth, Matt;Wu, Guoyuan.
502 $a Thesis (M.S.)--University of California, Riverside, 2023.
520 $a With the development of the city scale, a more high-efficient traffic system is needed. Thus, the Intelligent Transport System (ITS) is proposed. This system aims to provide innovative services relating to different modes of transport and traffic management and enable users to be better informed and make safer, more coordinated, and 'smarter' use of transport networks. This thesis focuses on the detection based on Infrastructure camera sensors, especially the fisheye camera. Two different methods are designed for this problem, the first one is a traditional method based on Background Subtraction. This method is verified at the intersection of University Ave and Chicago Ave, in Riverside, California, and in the CARLA simulator. It successfully detects vehicles the whole day regardless of the illumination weather and change. At the same time, a real-world vehicle dataset is collected for the second route. Also, in the CARLA experiment, our method significantly achieves improvement in terms of MOTA (multiple object tracking accuracy) and MOTP (multiple objects tracking precision). In the most complex scenario, our method outperforms the SOTA by 6.22\\% on MOTP and 1.71 pixels on MOTA. For the second route which is deep learning, there have been many efforts to apply deep learning to fisheye camera detection, but without a solid and large-scale fisheye image dataset, the neural network always has a bad detection performance. Thus, the second method tries to create a dataset that looks like the real world but is generated in a simulator (CARLA) to dismiss this problem. A real-world style dataset with ground truth labels is generated by modified AttentionGAN. Then deep learning object detection methods could be directly trained on the generated dataset. This project adopts YOLOV5 as the detection network. The final experiment result shows the trained network is able to detect all vehicles in verify part of the generated dataset and part of vehicles in the real-world dataset.
590 $a School code: 0032.
650 4 $a Electrical engineering. $3 649834
650 4 $a Computer engineering. $3 621879
650 4 $a Automotive engineering. $3 2181195
653 $a AI generated content
653 $a Computer vision
653 $a Fisheye camera
653 $a Infrastructure sensing
653 $a Intelligent Transport System
653 $a Vehicle detection
653 $a AttentionGAN
690 $a 0544
690 $a 0464
690 $a 0800
690 $a 0540
710 2 $a University of California, Riverside. $b Electrical Engineering. $3 1669528
773 0 $t Masters Abstracts International $g 85-04.
790 $a 0032
791 $a M.S.
792 $a 2023
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30312536