Accumulated water detection method based on video

A detection method and video technology, which are applied in image data processing, instruments, computing, etc., can solve the problems of high installation cost, single feature selection, and difficulty in promotion, and achieve the effect of improving the recognition accuracy.

Pending Publication Date: 2022-03-22
JIANGXI HONGDU AVIATION IND GRP
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the commonly used detection methods are: 1. Using the road to install the water detection device, this method is expensive to install, and it is difficult to fully promote; 2. By analyzing the camera video image, based on the texture characteristics of the water and the SVM classification method to detect the water detection, feature selection single

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
  • Accumulated water detection method based on video
  • Accumulated water detection method based on video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] 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.

[0020] see Figure 1~2 A video-based waterlogging detection method, which first collects sample pictures with a large amount of road waterlogging, and then uses the labeling tool to label the sample pictures, and then trains the labeled sample pictures based on the SSD target detection algorithm to construct a product Water detection model; finally obtain the video stream data of the road camera, and use the constructed water accumulation detection model to detect the accumulation of water on the obtained road camera video stream data. The specific steps are as follows:

[0021] 1) Collect sample pictures

[0022] Collect 1000 sample pictures with a lot of road water;

[0023] 2) Label sample pictures

[0024] Use the labeling tool LabelImag ...

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 video-based ponding detection method comprises the steps of firstly collecting a sample picture with a large amount of road ponding, then labeling the sample picture through a labeling tool, training the labeled sample picture based on an SSD target detection algorithm, and constructing a ponding detection model; and finally, acquiring video stream data of the road camera, and performing ponding detection on the acquired video stream data of the road camera by using the constructed ponding detection model. According to the method, sample collection, sample labeling, target detection and deep learning technologies are effectively combined with an actual road scene, the road waterlogging state is accurately recognized, the recognition accuracy is greatly improved, large-scale application can be performed by means of the constructed video monitoring network, and certain economic benefits and use values can be created.

Description

technical field [0001] The invention relates to the technical field of video intelligent monitoring, in particular to a method for detecting water accumulation based on video. Background technique [0002] In the city, the water accumulation on the road seriously affects the traffic order, and there are potential safety hazards, which endanger the safety of the people. It takes a lot of manpower and financial resources to clean up the water accumulation. If the water accumulation on the road can be found in time and actively dealt with, the loss can be minimized to the greatest extent. At present, the commonly used detection methods are: 1. Using the road to install the water detection device, this method is expensive to install, and it is difficult to fully promote; 2. By analyzing the camera video image, based on the texture characteristics of the water and the SVM classification method to detect the water Detection, feature selection single. Contents of the invention ...

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): G06T7/00G06T7/70
CPCG06T7/0002G06T7/70G06T2207/10016G06T2207/30204G06T2207/20081
Inventor 吴斌谢吉朋应艳丽贠周会叶超王欣欣王旭黄江林贾楠
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

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