Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Method for detecting floating objects in river

A detection method and technology for floating objects, which are applied in neural learning methods, biological neural network models, image data processing, etc., can solve problems such as difficulty in timely discovery, difficulty in salvaging, and large floating randomness, so as to reduce labor costs and improve The effect of salvage efficiency

Pending Publication Date: 2022-02-22
成都福立盟环保大数据有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The content of the present invention is to provide a method for detecting floating objects in the river, which uses the monitoring device installed beside the river to solve the problems that the existing rivers are long, the floating is relatively random, and it is difficult to find in time, which leads to the difficulty of salvage and the low efficiency of salvage. The video data recorded in real time by the camera detects floating objects in the river through image processing, deep learning, and target tracking related technologies

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 detecting floating objects in river
  • Method for detecting floating objects in river
  • Method for detecting floating objects in river

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0052] Taking a certain river course as an example, a method for detecting floating objects in a river course according to the present invention is adopted;

[0053] Utilize the video data of the real-time video recording of the monitoring camera installed beside the river, carry out image processing through steps S1 to S8, and then combine the deep learning of steps S9 and S10 to catch up with the floating objects in the river at the detection place through step S11;

[0054] First frame the pixel area to be detected in the current image, such as figure 2 shown;

[0055] Then select the picture 1 second before the frame selection area and use the mean value filter to process and obtain the mean value picture, such as image 3 shown;

[0056] Obtain the grayscale image of the screen image in the current frame selection area; perform grayscale processing on the average image obtained through S2 to obtain the grayscale image of the average image, such as Figure 4 shown;

...

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 detecting floating objects in a river. The method comprises the following steps: carrying out image processing by framing a pixel region of a river in a real-time video of a monitoring camera, carrying out water wave and suspected floating object classification on an image through a classification neural network, and obtaining a feature value vector of the image by using a feature extraction neural network; tracking each suspected floating object through a Deepsort target tracker, and when a tracked target moves in a picture, determining that the target is a floating object. Thus, floating objects in a river can be found in time to make a judgment for next salvage work, so that the situation that patrol personnel are put into the river without floating objects is effectively avoided, the labor cost is reduced, and the salvage efficiency is improved.

Description

technical field [0001] The invention belongs to the field of river water quality monitoring, and mainly relates to a method for detecting floating objects in a river. Background technique [0002] The river environment has always been the top priority of national environmental governance. Garbage floating in the river seriously affects the ecological environment. Garbage floating in the river pollutes the ecological environment along the way. At the same time, due to the long river, the floating randomness is relatively large Large, difficult to find in time, even some river sections without floating objects have invested a lot of manpower in river inspection, resulting in waste of human resources, increased labor costs, making salvage prediction difficult, high cost of salvage, directly leading to salvage efficiency low. Contents of the invention [0003] The content of the present invention is to provide a method for detecting floating objects in the river, which uses t...

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): G06V20/52G06V10/44G06V10/764G06V10/774G06V10/82G06K9/62G06T7/13G06T5/00G06T5/30G06N3/04G06N3/08
CPCG06T7/13G06T5/30G06N3/04G06N3/08G06T2207/20081G06T2207/20084G06F18/24G06F18/214G06T5/90
Inventor 刘阳
Owner 成都福立盟环保大数据有限公司
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
Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com