Unlock instant, AI-driven research and patent intelligence for your innovation.

An intelligent video smoky vehicle detection method based on multi-feature fusion

A technology of multi-feature fusion and detection method, which is applied in the field of intelligent video smoky vehicle detection based on multi-feature fusion, to achieve the effect of improving law enforcement efficiency, improving robustness, and reducing candidate areas

Active Publication Date: 2021-07-27
SOUTHEAST UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this approach is still in its infancy

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
  • An intelligent video smoky vehicle detection method based on multi-feature fusion
  • An intelligent video smoky vehicle detection method based on multi-feature fusion
  • An intelligent video smoky vehicle detection method based on multi-feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0100] The present invention provides an intelligent video smoky car detection method based on multi-feature fusion, the flow chart of which is as follows figure 1 As shown, follow the steps below:

[0101] Step 1: Use the foreground detection algorithm to extract the moving target from the road surveillance video, and identify the vehicle target;

[0102] Step 2: Use integral projection and filtering technology to detect the rear position of the vehicle;

[0103] Step 3: Extract the statistical features, frequency domain features and some manual features of the area behind the rear of the car, and fuse them to form a feature vector;

[0104] Step 4: Use the BP network classifier to classify the proposed feature vectors to identify the smoky frame and further identify the smoky car.

[0105] The foreground detection algorithm in the step 1 adopts the following process:

[0106] Step 1.1: Initialize the background I using the following formula back (t),

[0107]

[0108...

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 an intelligent video smoky car detection method based on multi-feature fusion, which comprises the following steps: (1) using a foreground detection algorithm to extract a moving target from a road monitoring video, and identifying the vehicle target; (2) using integral projection and filtering technology to detect the position of the rear of the vehicle; (3) extract the statistical features, frequency domain features and some manual features of the area behind the rear of the vehicle, and fuse them to form a feature vector; (4) use the BP network classifier to classify the proposed feature vector, Identify smoky frames to further identify smoky cars. The invention can improve the robustness and detect the black smoke vehicle more effectively.

Description

technical field [0001] The invention relates to the technical field of pyrotechnic detection, in particular to an intelligent video smoky car detection method based on multi-feature fusion. Background technique [0002] Accelerate the construction of motor vehicle pollution monitoring platforms in the region, focusing on the treatment of heavy-duty diesel vehicles and high-emission vehicles. The usual performance of heavy-duty diesel vehicles and high-emission vehicles is thick black smoke from the vehicle exhaust, which we usually call smoky vehicles. The smoky tail gas emitted by smoky vehicles not only pollutes the air, but also damages human health. Therefore, it is very meaningful to study how to effectively detect smoky vehicles. [0003] The current methods for detecting smoky vehicles can be divided into three categories: [0004] (1) Traditional methods. For example, mass reporting, regular road inspections, night inspections and manual video surveillance. Trad...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/32G06N3/08
CPCG06N3/084G06V20/42G06V20/46G06V20/52G06V20/584G06V10/245
Inventor 路小波陶焕杰
Owner SOUTHEAST UNIV