Machine vision-based technology for pedestrian lane assistive navigation /Tian Hongxing

By:

Tian Hongxing

Material type: Text

TextManila TUP 2023Description: [150?] o. color illustration 28 cmContent type:

Media type:

Carrier type:

LOC classification:

DIS T 185 T53 2023

Dissertation note: College of Industrial Education (CIE) Doctor of Technology (DT) Technological University of the Philippines 2023 Abstract: The eye is one of the most important human organs. It's an important biosensor for the perception of the outside world, and then a lot of people, either congenital or acquired, lose their sight and become blind. Unable to perceive the beauty of the world. According to the World Health Organization (WHO), the number of blind people in the world will increase from 43.3 million to 61 million by 2050. Due to visual impairment, they can't get the environmental information through their eyes, which brings great difficulties to their life, study and work. This paper mainly through the study of machine vision algorithm, through the visual camera to identify, collect, extract, analyze all kinds of complex information on the road, improve the recognition rate of information, has the accuracy of classification algorithm. In the context of 5G communication, technologies such as the Internet of Things, big data and supercomputers have been further developed, and artificial intelligence technology has also become one of the current hot topics. In this paper. traffic signs and other road condition information will be detected and recognized based on the YOLO v5 target detection algorithm, and the captured sign information will be recognized and analyzed with the advantage of YOLO algorithm in accuracy and real-time performance. In order to restore the real traffic scene, we prepared different shooting angles and different shooting locations as data sets. Finally, the detection and recognition of traffic signs are realized, and the algorithm is optimized to improve the recognition rate. The main work and conclusions of this paper are as follows: 1) Based on the travel needs of the blind, the existing classification algorithm and image recognition algorithm are studied, and the basic research direction is selected through theoretical learning and relevant information learning, mainly studying the image road condition information collection of the blind when walking outdoors. Through the analysis of different image acquisition network structure, the optimal scheme YOLO

Tags from this library: No tags from this library for this title. Log in to add tags.

Average rating: 0.0 (0 votes)

Holdings
Item type	Current library	Shelving location	Call number	Status	Notes	Date due	Barcode
Dissertation	TUP Manila Library	Thesis Section-2nd floor	DIS T 185 T53 2023 c.1 (Browse shelf(Opens below))	Not for loan	for room use only		DIS0002261

Browsing TUP Manila Library shelves, Shelving location: Thesis Section-2nd floor Close shelf browser (Hides shelf browser)

Previous	No cover image available	No cover image available	No cover image available	No cover image available	No cover image available	No cover image available	No cover image available
Previous	DIS T 185 S26 2021 Fabrication and property characterization of expanded perlite-based tiles for wall cladding system	DIS T 185 T33 2023 c.1 Design of intelligent refrigerator using internet-of-thing (IoT) technology	DIS T 185 T33 2023 c.2 Design of intelligent refrigerator using internet-of-thing (IoT) technology	DIS T 185 T53 2023 c.1 Machine vision-based technology for pedestrian lane assistive navigation	DIS T 185 Y36 2023 c.1 Manufacturing execution system of bluetooth speaker pen holder assembly line based on genetic algorithm	DIS T 785 Z43 2023 c.1 Microstructure evolution analysis of aeroengine turbine disk	DIS T 785 Z43 2023 c.2 Microstructure evolution analysis of aeroengine turbine disk

Dissertation

College of Industrial Education (CIE) Doctor of Technology (DT) Technological University of the Philippines 2023

The eye is one of the most important human organs. It's an important biosensor for the perception of the outside world, and then a lot of people, either congenital or acquired, lose their sight and become blind. Unable to perceive the beauty of the world. According to the World Health Organization (WHO), the number of blind people in the world will increase from 43.3 million to 61 million by 2050. Due to visual impairment, they can't get the environmental information through their eyes, which brings great difficulties to their life, study and work. This paper mainly through the study of machine vision algorithm, through the visual camera to identify, collect, extract, analyze all kinds of complex information on the road, improve the recognition rate of information, has the accuracy of classification algorithm. In the context of 5G communication, technologies such as the Internet of Things, big data and supercomputers have been further developed, and artificial intelligence technology has also become one of the current hot topics. In this paper. traffic signs and other road condition information will be detected and recognized based on the YOLO v5 target detection algorithm, and the captured sign information will be recognized and analyzed with the advantage of YOLO algorithm in accuracy and real-time performance. In order to restore the real traffic scene, we prepared different shooting angles and different shooting locations as data sets. Finally, the detection and recognition of traffic signs are realized, and the algorithm is optimized to improve the recognition rate. The main work and conclusions of this paper are as follows: 1) Based on the travel needs of the blind, the existing classification algorithm and image recognition algorithm are studied, and the basic research direction is selected through theoretical learning and relevant information learning, mainly studying the image road condition information collection of the blind when walking outdoors. Through the analysis of different image acquisition network structure, the optimal scheme YOLO

There are no comments on this title.

to post a comment.