Vehicle detection method based on improved YOLOv3

A vehicle detection and vehicle technology, which is applied in the field of computer vision, can solve the problems of insufficient real-time performance and precision, and detection time reduction, and achieve the effect of enriching the number, improving efficiency, and ensuring accuracy

Inactive Publication Date: 2020-07-17
CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to solve the problem of insufficient real-time performance and precision of the current traffic vehicle detection method, and to design a fast vehicle recognition method that greatly reduces the detection time under the condition of ensuring the detection accuracy of the vehicle

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Vehicle detection method based on improved YOLOv3
  • Vehicle detection method based on improved YOLOv3
  • Vehicle detection method based on improved YOLOv3

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] Below in conjunction with accompanying drawing and specific embodiment, technical scheme of the present invention is described in detail:

[0061] The present invention aims to build a fast and efficient vehicle detection method, and the following are the specific implementation steps involved in the specific implementation of the present invention:

[0062] S1. Collect the original video and perform frame extraction and preprocessing to obtain an image set;

[0063] The target category to be learned in this example involves three categories: passenger car, SUV, and sedan.

[0064] Obtain real-time monitoring video of road vehicles as raw video data. The video recording involves four weathers: sunny, rainy, cloudy, and light fog; the video recording time is 8:00-18:00;

[0065] Frame images are extracted from raw video data in a timed manner as a raw image set. Get 6000 vehicle images under different weather and different time.

[0066] Noise reduction is performed ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a vehicle detection method based on improved YOLOv3. According to the method, a feature weight optimization structure SEnet is introduced into a residual structure of a featureextraction network Darknet53 in YOLOv3 to optimize features extracted by the YOLOv3; residual error module reduction is performed on the feature extraction network after the SEnet structure is introduced; and the heights and the widths of vehicle labels in a vehicle data set are clustered by adopting a k-means method so as to optimize the original YOLOv3 target detection priori box. During batchtesting, the improved YOLOv3 has a vehicle detection map of 96.49% and a detection speed of 45 graphs / second, so that the requirements of real-time performance and accuracy of traffic detection are met, and a high application value is achieved in traffic detection.

Description

technical field [0001] The invention relates to the field of computer vision and the technical field of intelligent transportation information technology, specifically, a vehicle detection and recognition method based on the improved YOLOv3 model. Background technique [0002] The traditional vehicle detection method that is currently widely used requires manual participation in feature selection and other work, which has poor generalization ability and low recognition accuracy. [0003] The YOLOv3 deep learning network consists of two networks, Darknet53 and YOLO. It learns target features through convolution and performs multi-scale fusion of features. It can automatically learn features and enhance the expressive ability of features. It is better than many machine learning methods in the field of target detection. Although it achieves higher recognition speed and recognition accuracy, it still cannot meet the real-time detection and recognition requirements of vehicles un...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06N3/04G06N3/08G06K9/62
CPCG06N3/08G06V20/46G06V20/41G06V20/584G06N3/045G06F18/23213
Inventor 叶青刘剑雄李靓
Owner CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap