Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for reducing power transmission scene continuous image target detection false alarm

A continuous image and target detection technology, applied in image enhancement, image analysis, image data processing, etc., can solve problems such as target classification and reduce real-time performance, improve accuracy and real-time performance, reduce the number of false alarms, and scope of application wide effect

Pending Publication Date: 2021-11-02
SHANDONG ZHIYANG ELECTRIC
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the classification model itself has accuracy problems. It cannot 100% determine the authenticity of the target, nor can it classify all the targets, which will greatly reduce the real-time performance.

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
  • Method for reducing power transmission scene continuous image target detection false alarm
  • Method for reducing power transmission scene continuous image target detection false alarm
  • Method for reducing power transmission scene continuous image target detection false alarm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] Such as figure 1 shown.

[0034] A method for reducing false alarms for continuous image target detection in a power transmission scene, comprising:

[0035] a. Obtain real-time image data of the transmission channel;

[0036] b. Use the target detection algorithm to detect hidden dangers in the transmission channel scene for the front and rear frame images distributed according to the time axis in the real-time image data, and determine the hidden danger detection results; One frame of image and the next frame of image;

[0037] The hidden danger detection result of determining the previous frame image is determined by one of the following methods:

[0038] When the previous frame image is the first frame image, use the target detection algorithm to complete the hidden danger detection of the frame image, and obtain the hidden danger detection result;

[0039] When the previous frame image is a non-first frame image, the hidden danger detection result of the non-fi...

Embodiment 2

[0048] As described in Embodiment 1, a method for reducing false alarms in continuous image target detection of a power transmission scene further includes: performing morphological post-processing on the image obtained in step c2, performing corrosion and expansion processing, and obtaining the image Mn;

[0049] The step c3 extracts the rectangular frame of the connected area from the obtained image Mn, that is, connects the target areas with differences, extracts the largest circumscribed rectangular frame, and outputs the coordinates of the upper left vertex and the lower right vertex of each rectangular frame.

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 method for reducing power transmission scene continuous image target detection false alarms, and particularly relates to a method for completing power transmission channel scene hidden danger detection on images shot by a front-end camera by using a Faster-RCNN-based target detection algorithm. The method comprises the following steps: carrying out noise reduction and gray processing on an image, obtaining a difference image by adopting a frame difference method, carrying out binarization and morphological post-processing on the difference image to extract a difference region of a front frame image and a rear frame image, positioning the difference region of the front frame image and the rear frame image, and screening out an effective detection target. The frame difference method and the morphological post-processing method are used to extract the difference area of the two frames of images, the position of the newly added hidden danger point is positioned, and the problem of high false alarm rate of power transmission channel scene hidden danger detection is reduced.

Description

technical field [0001] The invention discloses a method for reducing false alarms in continuous image target detection of power transmission scenes, and belongs to the technical field of hidden danger detection in power transmission channel scenes. Background technique [0002] With the continuous development of artificial intelligence technology, it is more and more widely used in the field of transmission channel scenarios, mainly covering hidden danger detection of power transmission channel scenes, hidden danger detection of iron towers, etc. The emergence of various new technologies has improved the recognition rate of hidden danger detection to a certain extent, but the scene environment of transmission channels is complex and changeable, and computer vision technology has a strong dependence on prior data sets. As a result, the number of false alarms also increased, which increased the workload of background staff to identify real alarms. At present, the commonly use...

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): G06K9/00G06T7/11G06T7/136G06T7/155G06T7/73
CPCG06T7/11G06T7/136G06T7/155G06T7/73G06T2207/20028G06T2207/10016
Inventor 王光平胡志坤周璐王飞
Owner SHANDONG ZHIYANG ELECTRIC