Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A deep learning-based automatic detection method and a deep learning-based automatic detection system for a thrown object on an expressway

A highway and deep learning technology, applied in the field of intelligent transportation, can solve problems such as low accuracy of spilled objects and unrecognizable small spilled objects

Pending Publication Date: 2022-02-11
CHINA SHIPPING NETWORK TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention aims at the problem that the accuracy rate of identifying spills in the prior art is not high and small spills cannot be identified. The present invention provides an automatic detection method for expressway spills based on deep learning. Through the deep learning detection algorithm, the monitoring The spilled objects within the video range are identified and can be detected in real time. Through the determination strategy and continuous optimization and upgrading of the deep learning detection algorithm, the detection accuracy is improved.

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
  • A deep learning-based automatic detection method and a deep learning-based automatic detection system for a thrown object on an expressway
  • A deep learning-based automatic detection method and a deep learning-based automatic detection system for a thrown object on an expressway
  • A deep learning-based automatic detection method and a deep learning-based automatic detection system for a thrown object on an expressway

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be described below with reference to the accompanying drawings.

[0031] The invention relates to a deep learning-based automatic detection method for throwing objects on expressways, the flow chart of which is as follows: figure 1 shown, including:

[0032] 1. The step of video image acquisition, a spherical camera with a pan / tilt installed above the expressway is used to collect video images on the expressway. In this step, the monitoring angle of view is selected, and the spherical camera with the pan / tilt (hereinafter referred to as the camera) can be installed in the middle position of the elevated above the highway to monitor the entire large scene of the highway.

[0033] 2. In the target detection step, a deep learning detection algorithm is used to detect the thrown objects on the collected video images, and the position and frame of the thrown objects in the video images are extracted. Specifically, it includes: sample collection—s...

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 provides a deep learning-based automatic detection method and a deep learning-based automatic detection system for a thrown object on an expressway. The method sequentially comprises a video image acquisition step, a target detection step, a target judgment step, an accident alarm step and an optimization upgrading step. The thrown objects in the monitoring video range are identified through a deep learning detection algorithm, and real-time detection can be carried out; a deep learning detection algorithm is continuously optimized and upgraded through a judgment strategy; and the detection accuracy is improved, so that accidents in the expressway are reduced.

Description

technical field [0001] The invention relates to the technical field of intelligent transportation, in particular to a deep learning-based automatic detection method and system for thrown objects on expressways. Background technique [0002] In recent years, the rapid development of expressways has brought convenience to people's lives. At the same time, accidents on expressways have become more frequent. The most important factor causing accidents is the thrown objects on the highway. big challenge. The traditional detection algorithm of spilled objects adopts the method based on image processing, which requires manual extraction of image features, which is not only time-consuming and labor-intensive, but also the detection effect is not ideal. The detection methods of spilled objects based on video sequences also use the traditional Gaussian model and the three-frame difference method to distinguish the foreground, and then further identify the spilled objects, but the rec...

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
IPC IPC(8): G06V20/40G06V10/774G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/241G06F18/214
Inventor 张文风于艳玲杨东烨
Owner CHINA SHIPPING NETWORK TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products