Remote sensing video vehicle target detection and tracking method based on dynamic association model

A technology of dynamic association and target detection, which is applied in the field of image processing, can solve problems such as difficulty in obtaining the target position of the first frame, reduced tracking accuracy, and poor track smoothness, and achieves reduction in the number of false detection targets, flexible initialization and destruction, and vehicle The effect of smooth motion trajectory

Active Publication Date: 2019-10-29
XIDIAN UNIV
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the regularity of the target driving state of the vehicle, the target motion state changes greatly at intersections, overpass entrances, etc., and it is difficult for the Kalman filter to handle this change well.
The traditional method often judges the disappearance of the target at the boundary. This method conforms to common sense, and the amount of calculation is relatively small, which simplifies the algorithm process. However, when the tracker loses the target during the actual tracking process, the algorithm will not reset the lost will not delete trackers that have lost targets from the storage data, which will reduce the calculation speed of the algorithm and cause unreasonable use of storage resources
[0006] In practical applications, for remote sensing video moving vehicle tracking, it is difficult to obtain the accurate target position of the first frame, and because of the low re

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
  • Remote sensing video vehicle target detection and tracking method based on dynamic association model
  • Remote sensing video vehicle target detection and tracking method based on dynamic association model
  • Remote sensing video vehicle target detection and tracking method based on dynamic association model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033]Existing methods usually perform moving target detection and tracking work separately. For tracking, the exact position of the tracking target is given in the first frame, and no new targets will be detected and added later. The Kalman filter method is used to predict the target position during the tracking process. , use the similarity measure to correlate objects between frames, and only consider the object to disappear when it leaves the boundary. In tracking, the Kalman filter method is often used to predict the motion state of the target. However, in the remote sensing video moving vehicle target tracking task, there are often situations such as deceleration at intersections and overpass occlusion. track effect. Ideally, the remote sensing moving vehicle target detection will give the specific position of the tracking vehicle in the first frame, but in practical applications, it is expensive to accurately calibrate each moving vehicle target. The commonly used meth...

Embodiment 2

[0051] The remote sensing video vehicle target detection and tracking method based on the dynamic association model is the same as embodiment 1, and the moving target detection step in step (2.1) is as follows:

[0052] (2a) Build a background model, use the background subtraction method to obtain a difference map, and filter the moving target area according to the area.

[0053] More specific operations are described as follows:

[0054] (2a.1) For the background model, use the road extraction or manual segmentation method to obtain the road mask; build the background model. Instead of calculating the mean value of all frames in the continuous video, a preliminary screening is performed first, and the pixel value of the current position "still" frame in the video is selected as the background pixel value of the current position. The specific operation is as follows: if the deviation between the pixel value at the position of the current frame (x, y) and the pixel value at th...

Embodiment 3

[0060] The remote sensing video vehicle target detection and tracking method based on the dynamic association model are the same as embodiment 1-2, using the trajectory optimization method described in step (3.4), the specific steps are as follows:

[0061] Trajectory optimization refers to ensuring a stable change in direction between each frame, making the entire trajectory relatively smooth. According to common sense, it is believed that the vehicle is not allowed to turn at a large angle suddenly and go backwards during driving, so the change of the driving angle of the vehicle should not exceed the direction threshold, that is,

[0062]

[0063]

[0064] |θ t-1 -θ t |≤θ threshold

[0065] The specific steps of the trajectory optimization method are as follows:

[0066] (3.4a) Calculate the historical movement direction of the vehicle target

[0067] (3.4b) Calculate the new movement direction of the vehicle target after adding the candidate target

[0068]...

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 remote sensing video vehicle target detection and tracking method based on a dynamic association model, and solves the problems of low tracking precision, poor stability andinflexible algorithm. The method comprises the following steps: intercepting an image frame by frame, performing moving target detection on a first frame image, and creating a storage space storage target; and for subsequent frame images, detecting candidate moving targets, selecting historical target estimation positions from the storage space and matched with the candidate moving targets, then updating historical target states, arranging the storage space and storing newly-appearing targets. Interference outside a road area is filtered by using a road mask, targets are flexibly added and deleted by using dynamic association, the state estimation of a disappearing moving target is optimized by using a group effect, and the tracking precision is improved by using a trajectory optimizationmethod. Simulation experiments also prove that the method reduces the calculation amount, improves the tracking precision and stability, and is used in the fields of traffic flow monitoring, driving route analysis and military intelligence acquisition.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to moving target detection and multiple moving target state prediction and matching, in particular to a remote sensing video vehicle target detection and tracking method based on a dynamic correlation model, which is used for detecting vehicle targets in remote sensing video with tracking. Background technique [0002] Remote sensing video satellite is a new type of earth observation satellite. Its biggest feature is that it can continuously observe a certain target area by "staring" and store it in the form of video, from which more time-space related information can be obtained. Ground object detection and tracking provides a new opportunity. Satellite video imaging provides important data support for remote sensing and earth observation. How to use satellite remote sensing video to realize the intelligent detection and tracking of important targets is an important resear...

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): G06K9/00G06K9/62
CPCG06V20/52G06V10/7553G06F18/22
Inventor 张向荣焦李成张金月唐旭马晶晶呼延宁张静炎马文萍
Owner XIDIAN UNIV
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