Multi-video-frame black smoke diesel vehicle detection method and system based on space-time optical flow network

A detection method and technology for diesel vehicles, applied in neural learning methods, biological neural network models, instruments, etc., can solve problems such as insufficient accuracy and real-time performance, reduce recognition and false detection, and ensure accuracy and efficiency. Effect

Pending Publication Date: 2021-08-06
INST OF ADVANCED TECH UNIV OF SCI & TECH OF CHINA +1
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] A multi-video frame black smoke diesel vehicle detection method and system based on spatio-temporal optical flow network proposed by the present invention can solve the shortcomings of traditional smoke detection algorithms in accuracy and real-time performance in complex dynamic scenes, while taking into account continuous The connection between video frames and the dynamic characteristics of smoke provide a real-time black smoke detection algorithm suitable for complex traffic road scenes under different weather conditions

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
  • Multi-video-frame black smoke diesel vehicle detection method and system based on space-time optical flow network
  • Multi-video-frame black smoke diesel vehicle detection method and system based on space-time optical flow network
  • Multi-video-frame black smoke diesel vehicle detection method and system based on space-time optical flow network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0089] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments.

[0090] Such as Figure 1 to Figure 5 As shown, the multi-video frame smoky diesel vehicle detection method based on the spatio-temporal optical flow network described in this embodiment includes:

[0091] Step 1: Obtain the camera video of the complex road scene, and extract key frames from the video containing the detection target; then, preprocess the dataset image using image processing methods such as filtering and denoising, image enhancement, etc., and select the appropriate dataset image ;Finally, calibrate the diesel vehicles that emit blac...

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 multi-video-frame black smoke diesel vehicle detection method and system based on a space-time optical flow network, and the method comprises the steps: carrying out the key frame extraction and processing of a video containing a detection target based on an obtained video; establishing a model required for detecting the black smoke diesel vehicle, and training the model; analyzing the relation between continuous video frames by using an improved LK space-time optical flow network, capturing and segmenting a video dynamic region, and screening out a suspected black smoke region; inputting the framed region which is suspected to contain the black smoke into a trained target detection model, and carrying out secondary detection; and if the black smoke is finally detected, carrying out frame selection on the diesel vehicles discharging the black smoke, and outputting a detection result. According to the invention, through the LK optical flow network, the space-time relation among the continuous multiple video frames is established, the dynamic area is quickly and efficiently selected, the identification and false detection of non-black smoke images in the static area are effectively reduced, and through the end-to-end target detection model, the accuracy and high efficiency of video black smoke detection are ensured.

Description

technical field [0001] The invention relates to the technical field of environmental detection, in particular to a multi-video frame black-smoky diesel vehicle detection method and system based on a spatio-temporal optical flow network. Background technique [0002] Since the 21st century, the number of motor vehicles in my country has increased rapidly, and the problem of air pollution caused by mobile sources has become increasingly significant. The number of gasoline vehicles in urban areas is increasing rapidly. At the same time, there are also a large number of diesel vehicles emitting black smoke in suburban areas, causing serious environmental pollution problems. The black smoke exhaust gas emitted by diesel vehicles contains about 200 different compounds, which is one of the main causes of fine particulate matter and photochemical smog pollution. Considering the mileage and emission coefficient of diesel vehicles comprehensively, the nitrogen oxide and fine particle...

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): G06K9/62G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V20/46G06N3/045G06F18/23213G06F18/214
Inventor 康宇陈佳艺曹洋夏秀山李兵兵许镇义
Owner INST OF ADVANCED TECH UNIV OF SCI & TECH OF CHINA
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