Pedestrian detection method and system based on dynamic grouping convolution

A technology of pedestrian detection and convolution, applied in the field of neural networks, to achieve the effect of improving efficiency, increasing computing speed, and improving computing efficiency

Pending Publication Date: 2022-08-09
SHANDONG INSPUR SCI RES INST CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical task of the present invention is to provide a pedestrian detection method and system based on dynamic group convolution to solve the problem of how to use group convolution to realize pedestrian detection and effectively improve the efficiency of pedestrian detection

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
  • Pedestrian detection method and system based on dynamic grouping convolution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] This embodiment provides a pedestrian detection method based on dynamic grouping convolution, and the method is as follows:

[0056] S1. Obtain the behavioral data set, use the grouped convolution to construct the target detection network structure, and complete the initial training while retaining the original neural network structure; among them, the behavioral data set is collected according to the usage scene, and then uses manual annotation or intelligent annotation to obtain labels , complete the establishment of the data set; or use the public data set after screening to obtain and use; the pedestrian features included in the behavioral data set include the obvious features of the face, the characteristics of clothing and the corresponding features that need to be extracted according to the actual scene; the obvious features of the face include glasses; Clothing features including colour and style;

[0057] S2. Use the saliency score generator to calculate the sc...

Embodiment 2

[0080] This embodiment provides a pedestrian detection system based on dynamic grouping convolution, the system includes:

[0081] The building module is used to obtain the behavioral data set, use the grouped convolution to construct the target detection network structure, and complete the initial training while retaining the original neural network structure; among them, the behavioral data set is collected according to the usage scene, and then uses manual annotation or intelligent Label and obtain labels to complete the establishment of the data set; or use the public data set for screening and use; the pedestrian features included in the behavioral data set include obvious facial features, dressing features and corresponding features that need to be extracted according to the actual scene; obvious facial features including eyeglasses; clothing features including colour and style;

[0082] The sorting module is used to calculate the scores for the input channel and the out...

Embodiment 3

[0093] This embodiment also provides an electronic device, including: a memory and a processor;

[0094] Wherein, the memory stores computer execution instructions;

[0095] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the method for pedestrian detection based on dynamic group convolution in any embodiment of the present invention.

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 pedestrian detection method and system based on dynamic grouping convolution, belongs to the technical field of neural networks, and aims to solve the technical problem of how to realize pedestrian detection by utilizing grouping convolution and effectively improve the pedestrian detection efficiency. A target detection network architecture is constructed by using packet convolution, and initial training is completed while an original neural network structure is reserved; calculating scores of the input channel and the output channel by using a significance score generator, and sorting according to a sequence from high to low; setting a threshold value, and screening an input channel corresponding to the output channel; replacing the last 1 * 1 point-by-point convolutional layer in each inverted residual block by using a channel selector; training the target detection network architecture again by using the pedestrian data to obtain a reasoning model; and deploying the inference model at a side end, and identifying and judging a target acquired in real time.

Description

technical field [0001] The invention relates to the technical field of neural networks, in particular to a pedestrian detection method and system based on dynamic grouping convolution. Background technique [0002] In recent years, a variety of target detection networks have emerged in the field of deep learning, which have excellent performance in many aspects such as model size, inference speed, and recognition accuracy. Object detection is mostly used in the field of video surveillance and tracking. With the development of edge computing, mobile devices are usually required to have certain intelligent detection capabilities, which are limited by the storage resources and computing resources of the device. Inference speed and detection accuracy. Deeper and wider deep convolutional neural networks can achieve better performance, which leads to the design of a large number of huge and complex models. In order to reduce the complexity of the model and ensure the accuracy of...

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): G06V40/10G06V40/16G06V40/18G06V10/80G06V10/82G06N5/04G06N3/04G06N3/08
CPCG06V40/10G06V40/161G06V40/174G06V40/18G06V10/803G06V10/82G06N5/041G06N3/08G06N3/045
Inventor 李雪滕以金李锐林俊豪张晖
Owner SHANDONG INSPUR SCI RES INST CO LTD
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