Illegal dog walking identification method

A recognition method and a dog-walking technique, which are applied in the fields of image recognition and computer vision, can solve the problems of slow forward reasoning, difficulty in obtaining high recognition accuracy, and inability to achieve the detection accuracy of the two-stage target detection algorithm model, and achieve improved Accuracy and the effect of improving parameter adaptability

Pending Publication Date: 2020-08-28
ZHEJIANG UNIV OF TECH
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the two-stage target detection model has better detection accuracy, its forward reasoning speed is slow and cannot meet the real-time requirements of business scenarios
In the traditional one-stage target detection algorithm model, the real-time performance of the algorithm is better, but it cannot reach the detection accuracy of the two-stage target detection algorithm model
There are a large

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
  • Illegal dog walking identification method
  • Illegal dog walking identification method
  • Illegal dog walking identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In order to better illustrate the technical solution of the present invention, the present invention will be further described below through an embodiment in conjunction with the accompanying drawings.

[0039] The illegal dog walking identification method comprises the following steps:

[0040] Step 1: Collect a large number of dog sample image data taken at high altitude, construct a dog sample data set M of 10,000, a training data set T of 8,000, a verification data set V of 2,000, and mark the number of dog sample categories C as The value is 5, which are Teddy, Husky, Poodle, Shiba Inu, and Samoyed. The training data batch size is 4, the number of training batches is 1000, and the learning rate l_rate is 0.001. The scale factor ζ between the set T and the verification data set V is set to 0.25, the height, width, and number of channels of all images are set to be the same, and the height h of the image is k and width w k The values ​​are 416 and 416 respectively,...

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 illegal dog walking identification method comprises the following steps: 1) collecting images of high-altitude cameras in a large number of streets and other dog sample data sets, calibrating thedata sets according to on-site management requirements, and determining a used one-stage target detection algorithm model; 2) constructing a parameter self-adaptive loss function; and 3) constructinga loss function LOSS of a one-stage target detection algorithm model; 4) updating the weight of the one-stage target detection algorithm model by adopting a gradient descent method until the model converges; and completing detection of a dog sample in an actual system by using the trained model, and giving an alarm to complete detection of illegal dog walking in a street. The method has the advantages that the parameter adaptability of the target detection model can be improved, and the accuracy of target detection is greatly improved.

Description

technical field [0001] The invention belongs to the technical field of image recognition and computer vision, and relates to an illegal dog walking recognition method. Background technique [0002] At present, individual residents in the street do not follow the property regulations to walk their dogs illegally, which has caused unsafe problems for other owners who go out for exercise and walks. The traditional method is mainly through the uninterrupted inspection of the streets by the property administrators, and dissuades the illegal dog owners after they are found. However, this method requires a lot of manpower and material resources to implement, and it cannot achieve real-time and all-round supervision of the entire street. The use of high-altitude security cameras in the existing streets to detect illegal dog-walking behaviors can not only achieve real-time monitoring, but also save manpower and material costs, and equipment maintenance and repair are also very easy....

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/10G06V20/52G06N3/045G06F18/241
Inventor 邵奇可卢熠颜世航陈一苇
Owner ZHEJIANG 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