A method and system for identifying falling objects based on image recognition

A technology of image recognition and recognition method, which is applied in the field of image recognition, can solve the problems of low accuracy and recall rate of falling object recognition, and achieve the effect of convenient tracking and traceability, improvement of accuracy rate, high accuracy rate and recall rate

Active Publication Date: 2020-12-15
安徽小眯当家信息技术有限公司
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems in the prior art that the accuracy rate and recall rate of falling object recognition are not high, the present invention provides a falling object recognition method and system based on image recognition, which can improve the recognition rate and recall rate of falling object recognition, Simultaneous identification of multiple falling objects

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
  • A method and system for identifying falling objects based on image recognition
  • A method and system for identifying falling objects based on image recognition
  • A method and system for identifying falling objects based on image recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0075] Such as figure 1 As shown, a falling object recognition method based on image recognition includes the following steps:

[0076] Step 1. Shoot the monitoring area through the shooting device, and send the video to the server for processing. The shooting device here can be a surveillance camera. The camera is installed and debugged according to the site conditions. During the debugging, the camera is fixed according to the installation position For its zoom factor and elevation angle, the camera in this embodiment is 20 meters away from the monitoring place, the zoom factor is set to 2 times, and the elevation angle is 40 degrees.

[0077] Step 2. The server side performs object recognition on the video. The object recognized by the object recognition is a moving object, and judges whether the recognition result meets the requirements....

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 falling object recognition method and system based on image recognition, belonging to the field of image recognition. Aiming at the problem of low accuracy and recall rate of falling object recognition in the prior art, the present invention shoots the monitoring area, sends the video to the server, and the server performs object recognition, group recognition, and suspected falling object recognition on the video And the identification of falling objects, the objects in the video are judged multiple times, if the final result is determined as falling objects, the number of falling objects is counted, and the recognition results are sent to the client. The present invention detects moving objects in OpenCv, The combination of various identification and determination methods such as density clustering, linear regression fitting, and curve fitting can improve the recognition rate and recall rate of falling object recognition, and can identify multiple falling objects at the same time.

Description

technical field [0001] The present invention relates to the field of image recognition, more specifically, to a falling object recognition method and system based on image recognition. Background technique [0002] With the development of the times, there are many high-rise buildings in the city, and the residents' houses are becoming more and more comfortable and taller. At the same time, hidden dangers to safety have also emerged. In recent years, there have been frequent incidents of falling objects in domestic communities, which has caused great harm to the safety of people's lives and property. Although the property has also ordered residents to prohibit residents from throwing objects from high altitudes, intentionally throwing objects from high altitudes is also illegal, but falling objects from high altitudes causes casualties. Cases continue to appear in the newspapers. On the one hand, the weak legal awareness of the public leads to the occurrence of high-altitude ...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/32G06K9/62G06T7/62G06T7/66
CPCG06T7/62G06T7/66G06V20/52G06V10/25G06F18/2321
Inventor 华绘
Owner 安徽小眯当家信息技术有限公司
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