GS-SSD traffic large-scale scene vehicle target rapid detection method

A detection method and technology for large scenes, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as failure to achieve good results and insufficient detection speed, and achieve network model parameters simplification and small size. Target detection effect, improvement of detection accuracy and detection speed

Pending Publication Date: 2020-12-15
XIAN UNIV OF TECH
View PDF1 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it failed to achieve a good detection effect on small target detection, and its detection speed is not enough to apply to the actual target detection scene to be solved urgently

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
  • GS-SSD traffic large-scale scene vehicle target rapid detection method
  • GS-SSD traffic large-scale scene vehicle target rapid detection method
  • GS-SSD traffic large-scale scene vehicle target rapid detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0045] The present invention provides a GS-SSD rapid vehicle target detection method in a large traffic scene, such as figure 1 As shown, it specifically includes the following steps:

[0046] Step 1: First, train and screen out the optimal Gabor convolution kernel group and place it in the shallow VGG16 network. Second, use SIP (semantic interpolation) to map the high-level semantic information in the deep layer of the feature map to the shallow layer of the feature map. Finally, in the Caffe environment Next build a new GS-SSD network model;

[0047] Step 1 is specifically implemented according to the following steps:

[0048] Step 1.1, replace the low-level convolution kernel group of the VGG16 network: first, use the VGG16 network as the basic network model of SSD, and secondly, construct a two-dimensional Gabor filter convolution kerne...

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 GS-SSD traffic large-scale scene vehicle target rapid detection method comprising the following steps: 1, training and screening an optimal Gabor convolution kernel group, placing the optimal Gabor convolution kernel group in a shallow VGG16 network, using SIP to map advanced semantic information of a feature map deep layer to a feature map shallow layer, and finally building a novel GS-SSD network model in a Caffe environment; step 2, acquiring a training and testing image data set required for establishing a novel GS-SSD network model; 3, training and testing the built novel GS-SSD network model in the Caffe environment; and step 4, carrying out frame sampling on a video collected by a traffic intersection camera, inputting the obtained image into the tested novel GS-SSD network, carrying out target detection on the obtained image by using the tested novel GS-SSD network model, and finally outputting a detection result. The method is high in precision and detection speed.

Description

technical field [0001] The invention belongs to the technical field of image processing of computer vision, and in particular relates to a GS-SSD rapid detection method for a vehicle target in a large traffic scene. Background technique [0002] ATMS (Advanced Transport Management Systems) is the core subsystem of Intelligent Transport Systems (ITS). Its main function is to automatically identify the degree of traffic congestion in the current urban road traffic network, induce urban road traffic flow in real time, quickly respond to and respond to road traffic emergencies, and realize intelligent control of urban road traffic operation status. The prerequisite for the realization of the ATMS function is to collect and identify road traffic status information in real time and accurately. [0003] Target detection has made important progress in recent years. In addition to the traditional manual design of features for classification target detection, the current mainstream a...

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
IPC IPC(8): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/54G06V10/454G06V2201/08G06V2201/07G06N3/045G06F18/24G06F18/214
Inventor 缪亚林张顺姬怡纯程文芳
Owner XIAN UNIV OF TECH
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