Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Intelligent monitoring method based on deep fusion neural network pedestrian re-identification technology

A pedestrian re-identification and neural network technology, applied in the field of intelligent monitoring, can solve the problems of difficult to guarantee the convergence speed, weak coupling between manual features and deep features, and difficult to train neural networks. effect of speed

Pending Publication Date: 2019-07-23
NORTHEASTERN UNIV
View PDF7 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This algorithm deduces the backpropagation process from the loss function to each parameter, and also proves the constraints of the traditional manual features on the parameters of the neural network. However, in practical applications, the neural network is difficult to train, and the convergence speed is difficult to guarantee. Coupling of deep features is weak

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
  • Intelligent monitoring method based on deep fusion neural network pedestrian re-identification technology
  • Intelligent monitoring method based on deep fusion neural network pedestrian re-identification technology
  • Intelligent monitoring method based on deep fusion neural network pedestrian re-identification technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0073] S3B. For an original image with a size of 128*64, DFNN first cuts it out randomly, then rescales it to 256*128 and passes it into the deep neural network ResNet50. The input image is sequentially processed through convolution layer, local normalization layer, modified linear activation function, maximum pooling, etc., and then enters 16 convolution modules. Although the features extracted by these convolution modules are becoming more and more complex, DFFN will maintain and reduce the size of the features at the same time, and the convolution module (convblock) is used to reduce the dimension of the data. There are three other dimensionality reduction modules that are the same as this dimensionality reduction module. After each dimensionality reduction module, the image size will be reduced by 2*2. Therefore, before the input and output are connected through the adder, the input needs to be reduced in size using a convolutional layer to ensure normal addition.

[0074...

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 provides an intelligent monitoring method based on a deep fusion neural network pedestrian re-identification technology. According to the method, after the color enhancement preprocessing is carried out on an obtained image, the traditional manual features of the image are extracted, and a deep residual convolutional neural network extracts the image, and then the traditional manualfeatures subjected to dimension reduction and the deep features extracted by the completely trained neural network are fused, so that the identification of the target pedestrian is completed. Comparedwith the prior art, the recognition precision is greatly improved, the recognition success rate is increased to 81.74% through the pedestrian re-recognition algorithm contained in the method, and thetechnology can be completely practical. The pedestrian re-identification process is automatically completed, and details cannot be lost due to fatigue of people.

Description

technical field [0001] The invention relates to the technical field of intelligent monitoring, in particular to an intelligent monitoring method based on a deep fusion neural network pedestrian re-identification technology. Background technique [0002] Pedestrian re-identification, also known as pedestrian re-identification, is a technology that uses computer vision technology to determine whether a specific pedestrian exists in an image or video sequence. Due to the differences between different camera equipment, pedestrians have both rigid and flexible characteristics, and their appearance is easily affected by clothing, scale, occlusion, posture and viewing angle. Therefore, pedestrian re-identification has become a research value in the field of computer vision. Challenging hot topics. [0003] Currently, there are two main research methods for person re-identification: methods based on manual features and methods based on deep features. Methods based on manual featur...

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): G06K9/00G06K9/46G06K9/62G06N3/04
CPCG06V40/10G06V10/56G06N3/045G06F18/213G06F18/253
Inventor 梁子华如照张越迟剑宁王文浩
Owner NORTHEASTERN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com