Riverway floating object detection algorithm under static camera

A detection algorithm and technology for floating objects, which are applied in the field of computer vision to achieve the effects of high detection accuracy, real-time performance, and convenient large-scale deployment.

Pending Publication Date: 2021-09-03
湖南汇视威智能科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing deep learning-based river floating object detection model still has some practical problems, and cannot well fit the river floating object detection task with high real-time requirements.

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
  • Riverway floating object detection algorithm under static camera
  • Riverway floating object detection algorithm under static camera
  • Riverway floating object detection algorithm under static camera

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0034] 1. Dataset

[0035] The data set uses a private monitoring video data set of river floating objects, including 1000 video segments, each segment is about 15s long, and the frame rate is 30. Since the present invention does not distinguish between training sets and test sets, all video sequences can be tested directly.

[0036] 2. Performance Evaluation Criteria

[0037] In order to evaluate the performance of the algorithm and compare it with other methods, the present invention selects the evaluation method widely used in target detection: Accuracy (accuracy rate) and F1-Score (F1 score) calculated based on IOU (intersection-over-union ratio) ;

[0038] First, the calculation process of IOU is introduced. IOU is the ratio of the intersection and union of the rectangular frame of the detection result and the rectangular frame marked by the sample;

[0039] Secondly, according to the position of the sample, it can be judged whether it is a positive example or a negat...

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 riverway floating object detection algorithm under a static camera, and aims to solve the problem of detecting floating pollutants in a riverway. According to the technical scheme, the method comprises the following steps: calculating an average video frame of video frames by using Opencv and other computer software tools based on a front and back background subtraction idea of computer vision, then carrying out difference calculation on the video frames and the average video frame, analyzing a difference result, carrying out contour calculation to obtain a minimum rectangle surrounding a contour, and returning attribute information of the minimum rectangle, and judging the river floaters according to the attribute information. With the adoption of the system and the method, the river floating pollutants in the video can be detected, and relatively high detection precision and relatively high detection speed are realized. In addition, the method is low in computing power requirement, and wide deployment can be achieved.

Description

technical field [0001] The invention belongs to the field of computer vision and relates to a detection algorithm for floating objects in a river, in particular to a detection algorithm for floating objects in a river under a static camera. Background technique [0002] River pollution is a very serious environmental pollution. As a major pollution source of river pollution, the existence of river floating objects seriously pollutes the water quality of rivers and lakes, and also destroys the beauty of the environment. Floating debris in the river mainly includes domestic garbage, factory waste, and algae plants that bloom and grow. At present, the main solution is to manually control the salvage equipment at the water inlet or outlet of the river to deal with the floating objects. However, due to the limitations of the human eye, the visibility in the environment is not very high or the water flow is fast. Under normal circumstances, the human eye cannot accurately detect ...

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): G06K9/00G06K9/46
Inventor 顾善植蓝丹彭智亮吴瑶王聪睿胡亚清王明兴杨石梦
Owner 湖南汇视威智能科技有限公司
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap