Pedestrian hash retrieval based on loss measurement in depth learning networks

A deep learning network and pedestrian technology, applied in still image data retrieval, still image data indexing, instruments, etc., can solve problems such as background interference and low retrieval accuracy, achieve shallow structure levels, easy optimization of network weight parameters, The effect of fast convergence speed

Active Publication Date: 2019-01-18
BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY +1
View PDF17 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in complex scenes, there are many uncertain factors such as posture, illumination, occlusion, background interference, etc. Therefore, the existing pedestrian retrieval technology has the problem of low retrieval accuracy. A very challenging technical task

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 hash retrieval based on loss measurement in depth learning networks
  • Pedestrian hash retrieval based on loss measurement in depth learning networks
  • Pedestrian hash retrieval based on loss measurement in depth learning networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] In the following, the present invention is further described through embodiments with reference to the drawings, but the scope of the present invention is not limited in any way.

[0064] The present invention provides a deep hash pedestrian retrieval method based on metric loss in complex scenes. By introducing a CNN model, the network can learn the binary hash code of pedestrian retrieval end-to-end, and realize the retrieval of pedestrians. Pedestrian search accuracy.

[0065] In specific implementation, the present invention uses a 4-layer convolutional neural network model to realize the extraction of pedestrian features. The specific network layer settings are shown in Table 1. The size of the convolution kernel of convolution layer 1 (conv1) is 3×3, and the number of convolution kernels is 32; then connected to convolution layer 2 (conv2), the size of the convolution kernel is 5×5, and the number of convolution kernels There are 32; the pool layer 1 (pool1) is follo...

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 hash retrieval method based on loss measurement in a depth learning network. The pedestrian hash retrieval method realizes hash code learning of a pedestrian imageby constructing a pedestrian hash learning model CFNPHL of a convolution characteristic network. Then the distance between hash codes of pedestrian images is calculated to realize the retrieval of large-scale pedestrian image data. The method includes establishing convolution neural network model and extracting pedestrian feature information; Mapping binary hash codes; Adding quantified loss to measure loss; setting classification los function to learn that distinguishing characteristic of different pedestrians, and obtaining pedestrian categories; Minimizing network losses; Training the network CFNPHL to obtain the pedestrian hash code library for image retrieval; Then inputting the pedestrian image to be retrieved into the trained network to obtain the hash code of the pedestrian to beretrieved; performing pedestrian retrieval by calculating the distance. The pedestrian retrieval method effectively improves the retrieval speed and has high accuracy rate according to the pedestrianretrieval under the complex scene.

Description

Technical field [0001] The invention belongs to the technical field of pattern recognition and machine vision. Aiming at the problem of pedestrian retrieval in complex scenes, a pedestrian hash retrieval method based on measurement loss in a deep learning network is proposed, which effectively improves the accuracy of pedestrian retrieval. Background technique [0002] In recent years, with the development of pattern recognition and machine vision technology, pedestrian retrieval technology has been greatly developed, and a large number of applications have been implemented in the field of complex video scene monitoring. [0003] Pedestrian retrieval has always been a hot research topic in the field of image retrieval. The image hash retrieval method generally includes two parts: the feature code of the image is obtained by feature extraction and the feature code is hashed. The traditional image hash retrieval method uses hand-designed description operators to process the image wh...

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): G06F16/53G06F16/51G06K9/00G06K9/62
CPCG06V40/103G06F18/22G06F18/24G06F18/214
Inventor 于重重马先钦周兰于蕾
Owner BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY
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