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

A moving vehicle detection method based on aerial video images

A video image and vehicle detection technology, which is applied in the field of moving vehicle detection based on aerial video images, can solve the problems that the accuracy is easily affected by scale changes, complex environments and camera movements, and it is difficult to apply multi-moving vehicle detection.

Inactive Publication Date: 2020-03-13
HEBEI UNIV OF TECH
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to provide a moving vehicle detection method based on aerial video images. The detection of moving vehicles in a single scene is difficult to apply to the detection of multi-moving vehicles in different scenes, and the detection accuracy is easily affected by scale changes, complex environments and camera movements.

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 moving vehicle detection method based on aerial video images
  • A moving vehicle detection method based on aerial video images
  • A moving vehicle detection method based on aerial video images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0070] A moving vehicle detection method based on aerial video images. This method integrates time and space characteristics, and is suitable for accurate detection of moving vehicles in different scenes. The specific steps are as follows:

[0071] The first step is to match the color sequence image of the input moving vehicle, and further obtain the image after background compensation:

[0072] (1.1) Image matching based on SURF feature points:

[0073] Use simple aerial photography scenes to collect color sequence images of moving vehicles in simple aerial photography scenes and complex aerial photography scenes to collect color sequence images of moving vehicles in complex aerial photography scenes, input all the collected color sequence images F of moving vehicles into the computer, and convert them from RGB space to gray degree space, the formula (1) adopted is as follows:

[0074] I=0.299R+0.587G+0.114B (1),

[0075] Perform SURF feature point detection on the obtained...

Embodiment 2

[0113] The moving vehicle detection result of the inventive method is compared with the moving vehicle detection result of the COCOA system of the prior art, the significance fusion method and the LBP method, and the results are shown in Table 2.

[0114] Table 2. Four methods of moving vehicle detection results on the Egtest01 and Crossroad01 databases

[0115]

[0116] As can be seen from Table 2, compared with the current popular prior art COCOA system, saliency fusion method and LBP method, the method of the present invention can detect moving vehicles no matter on the Egtest01 database with simple background or the Munich Crossroad01 database with complex scenes. Both the recall rate and the precision rate of moving vehicle detection are the highest, which verifies the robustness and effectiveness of the method of the present invention.

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 moving vehicle detection method based on aerial video images of the present invention relates to image motion analysis in image data processing, the steps are: matching the input moving vehicle color sequence image, and further obtaining the image after background compensation: including image matching based on SURF feature points and estimate the global motion parameters of the camera to obtain the image after background compensation; rough detection of moving vehicle position; precise detection of moving vehicle position: including adaptive road detection, extracting CHLBP features of candidate vehicle areas and using SVM classifier to perform CHLBP features The judgment acquires accurate detection of the position of the moving vehicle. This method combines time and space characteristics, overcomes the existence of the existing technology, which is only suitable for simple single-scene moving vehicle detection, and is difficult to apply to multi-moving vehicle detection in different scenes. The detection accuracy is easily affected by scale changes, complex environments and cameras. Movement affects defects.

Description

technical field [0001] The technical solution of the present invention relates to image motion analysis in image data processing, in particular to a moving vehicle detection method based on aerial video images. Background technique [0002] With the rapid development and popularization of computer and information technology, the intelligent transportation system (ITS) has emerged as the times require. It is an important way to solve the current traffic problems, and it is also the main direction of the future development of intelligent transportation. Moving vehicle detection is one of the basic technologies of intelligent transportation systems, and it is the basis for the measurement of traffic flow parameters such as vehicle count, vehicle speed, traffic flow and vehicle density. In moving vehicle detection, only by accurately segmenting the vehicle from the image background can the identification and tracking of moving vehicles be carried out, and then the measurement an...

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): G06T7/246G06T7/254G06T7/33G06T7/80G06T7/11G06T7/136G06K9/62
CPCG06T2207/10016G06T2207/10024G06T2207/20016G06T2207/20081G06T2207/30236G06F18/2411
Inventor 于明刘双岭于洋师硕郭迎春刘依
Owner HEBEI UNIV OF TECH