Illegal dog walking event detection method and device based on monitoring video

A monitoring video and event detection technology, applied in neural learning methods, computer components, instruments, etc., can solve problems such as inability to identify and effectively identify whether a dog is on a leash

Active Publication Date: 2021-06-04
小视科技(江苏)股份有限公司
View PDF13 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing disclosed technology mainly detects and locates people and dogs separately, and cannot identify or effectively identify whether the dog is on a leash and the relationship between the person and the dog, that is, whether the person is leading the dog.

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 event detection method and device based on monitoring video
  • Illegal dog walking event detection method and device based on monitoring video
  • Illegal dog walking event detection method and device based on monitoring video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Aiming at the shortcomings of the existing technology, the solution idea of ​​the present invention is to use machine vision algorithm to detect the behavior of walking the dog without leash, and to reduce the amount of calculation and improve the accuracy by optimizing the algorithm.

[0038] Specifically, the monitoring video-based illegal dog-walking event detection method proposed by the present invention includes the following steps:

[0039] Step A: Carry out dog and human detection on the image frame of the surveillance video. If no dog is detected in the image frame, then judge "the status is normal" and return; ” and return; otherwise, go to step B;

[0040]Step B. Estimate the distance between the person and the dog in the image frame and judge whether it exceeds the preset distance threshold. If so, judge "the dog is not on a leash" and return; otherwise, go to step C;

[0041] Step C, intercept the image containing the dog from the image frame and input it ...

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 an illegal dog walking event detection method based on a monitoring video, and the method comprises the following steps: A, carrying out the detection of a dog and a person in an image frame, and judging that the state is normal if no dog is detected, and returning; if no dog exists, judging that the dog is not tied with the rope and returning; otherwise, entering the step B; step B, estimating the distance between the person and the dog and judging whether the distance exceeds a distance threshold value or not, if so, judging that the dog is not tied with the rope and returning; otherwise, entering step C; C, intercepting an image containing the dog, inputting the image into the dog rope tying recognition model, and if the output is that the dog is tied with the rope or the dog is not tied with the rope, outputting and returning the result; otherwise, entering the step D; and step D, finding out k persons closest to the dog, intercepting a maximum detection frame image, inputting the maximum detection frame image into the person-dog relation identification model, and judging whether the dog is tied with a rope or not according to model output. The invention further discloses an illegal dog walking event detection device based on the monitoring video.

Description

technical field [0001] The invention belongs to the technical field of machine vision, and in particular relates to a monitoring video-based detection method for illegal dog-walking events. Background technique [0002] With the development of society, more and more people began to keep dogs as pets, followed by uncivilized behaviors such as walking dogs without leashes, which also seriously disturbed others. Animal Epidemic Prevention Law clearly lists such behaviors as illegal behaviors. For such illegal activities, if the traditional methods of human monitoring and dissuasion are adopted, a large amount of manpower will be required, which is actually not feasible. If the high-altitude security cameras in the existing streets can be used to detect illegal dog-walking behavior, not only real-time monitoring can be achieved, but also manpower and material costs can be saved, and equipment maintenance and repair are also very easy. The illegal dog walking detection system o...

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): G06K9/00G06K9/32G06K9/34G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/44G06V20/41G06V10/25G06V10/267G06V10/44G06N3/045G06F18/2415
Inventor 杨帆冯帅刘利卉胡建国
Owner 小视科技(江苏)股份有限公司
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