Water surface garbage detection method based on a deep learning algorithm

A technology of deep learning and water surface garbage, which is applied in computing, computer parts, instruments, etc., can solve problems such as delaying water surface garbage cleaning, affecting work efficiency, and affecting accuracy, so as to ensure real-time detection, save investment costs, high precision effect

Inactive Publication Date: 2019-04-12
JIANGXI HONGDU AVIATION IND GRP
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the detection of water surface garbage in freshwater basins such as inland rivers and lakes in my country is basically based on manual inspection, and some areas use simple video image analysis and detection methods, but the core algorithm of this simple video image analysis and detection method uses frame difference No matter how these algorithms are optimized and upgraded, their essence is to use the current video frame to subtract the previous video frame or subtract the background video key frame to find the area where the pixels change, and then filter the noise reduction and The final change area determined by the threshold judgment is the water surface garbage judged by this type of algorithm. Obviously, for the swimming behavior of humans or animals on the water surface, the ripples or surges caused by rain or wind on the water surface, and the video picture changes caused by camera shake Many similar situations will cause the pixels of the video image to change before and after the frame, resulting in being mistakenly judged as water surface garbage, seriously affecting the accuracy of judgment, delaying the cleaning of water surface garbage, and often requiring manual secondary inspections, which did not meet expectations purpose, affect work efficiency

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
  • Water surface garbage detection method based on a deep learning algorithm
  • Water surface garbage detection method based on a deep learning algorithm
  • Water surface garbage detection method based on a deep learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] In order to make the technical means, creative features, goals and effects achieved by the present invention easy to understand, the present invention will be further described below in conjunction with specific illustrations.

[0025] A water surface garbage detection method based on a deep learning algorithm, the specific steps are as follows:

[0026] 1) Lay out and install the detection system, such as figure 1 As shown, front-end cameras are deployed in several important sections of inland rivers, lakes and other waters to be detected. The cameras are equipped with voice alarms, and the height and angle of the cameras are adjusted to ensure that all deployed cameras can capture high-quality images; The network cable, signal line, data line and other lines are piped and laid, and finally connected to the core switch through the access layer switch; the video analysis server based on the deep learning algorithm obtains the real-time video stream of all front-end came...

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

A water surface garbage detection method based on a deep learning algorithm comprises the steps that hardware equipment is arranged and installed, front-end cameras are arranged in a plurality of important sections of water areas such as an inland river and a lake to be detected, and the front-end cameras are finally connected to a core switch through an access layer switch; a deep learning algorithm and a feedback mechanism are arranged in the video analysis server based on the deep learning algorithm, and the feedback mechanism performs secondary training on pictures which are misreported ormissed in deep learning training, so that the model characteristics of the continuously trained deep learning algorithm are more comprehensively covered, and the false report rate and the missed report rate of the pictures are reduced; the video analysis server adopts a multi-GPU parallel computing architecture, hardware server resources are utilized to the maximum extent, and the investment costis saved; a CAFFE-based SSD deep learning algorithm is outstanding in calculation speed, and the detection real-time performance is effectively ensured.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a method for detecting water surface garbage based on a deep learning algorithm. Background technique [0002] Fresh water is an indispensable resource for human survival and social development. With the continuous increase of the population and the continuous development of the social economy, the human demand for fresh water resources is also increasing, but the accompanying fresh water pollution is also becoming more and more serious. At present, the quality of fresh water environment in my country is worrying. The national fresh water quality inspection results show that more than 90% of urban waters are seriously polluted. So far, the economic loss caused by fresh water pollution is as high as 240 billion yuan. [0003] Water surface garbage refers to the dead branches and leaves of plants floating on the water for a long time, the corpses of animals such as...

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): G06K9/00G06K9/62
CPCG06V20/41G06F18/214
Inventor 王旭贠周会吴斌谢吉朋王欣欣叶超应艳丽黄江林钟媛
Owner JIANGXI HONGDU AVIATION IND GRP
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