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

Fast Tracking Method for Aerial Targets for UAV Aerial Image Sequences

An aerial image and aerial target technology, applied in the field of fast tracking of aerial targets, can solve problems such as slow tracking speed, and achieve the effect of accurate tracking and fast tracking speed

Inactive Publication Date: 2019-07-02
PINGDINGSHAN UNIVERSITY
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, in the actual flight process, it is necessary to correct the rotation and scaling information of the frame to improve the instrument navigation performance of the UAV, and the tracking speed is slow

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0028] The fast tracking method of aerial target for UAV aerial image sequence is:

[0029] 1. Assuming that the current clock is T, then the observation set at time t can be expressed as Z(t), t∈{1,2,..T}, and the number of observations at time t can be expressed as M k =|Z(t)|. Therefore, the data association process can be described as finding a partitioning scheme of the set Z to the track set Tr.

[0030] Suppose further that Z is in [t 0 , t 0 +T] time frame with track set T r The associated image sequence, and the track set T r kept until t 0 +T-1 moment.

[0031] 2. Obtain the orbit set from the UAV aerial image sequence, select a specific time, and decompose the orbit set into orbits;

[0032] 3. Select the target in frame A, use the MHT algorithm based on the sliding time window to cluster the contours, and construct the target object;

[0033] 4. Detect the SIFT descriptor of the target object, and use multi-hypothesis tracking to predict the next frame B wh...

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 unmanned aerial vehicle aerial photography image sequence-oriented aerial target rapid tracking method, including the following steps: assuming that a current clock is T, an observation set of the moment t can be expressed as Z(t), I is an element of a set {1, 2,...T}, the observation number of the moment t is expressed as M<k>=|Z(t)|, and a data association process can be described as looking for a segmentation scheme from a set Z to a track set Tr; a track set is obtained from the unmanned aerial vehicle aerial photography image sequence, a certain specific time is selected, and the track set is decomposed into tracks; and a target is selected in a frame A, an MHT algorithm based on a sliding time window is utilized to cluster an outline, and a target object is constructed. The unmanned aerial vehicle aerial photography image sequence-oriented aerial target rapid tracking method provided by the invention utilizes the Multi-hypothesis Tracking (MHT) algorithm to track a series image sequences of the object (target), utilizes SIFT features to describe vision content of unmanned aerial vehicle aerial photography images, an MHT framework is constructed based on a multi-dimensional allocation formula and sliding time window scheme, the tracking speed is fast and the tracking is precise.

Description

technical field [0001] The invention relates to the technical field of unmanned aerial vehicles, in particular to a fast tracking method for aerial targets oriented to aerial image sequences of unmanned aerial vehicles. Background technique [0002] Unmanned aerial vehicles (UAVs), also known as drones, can fly autonomously without a pilot. Flight status and route are controlled by wireless remote controller or computer program. UAV uses air power to support its flight in the atmosphere. It has the advantages of wide viewing angle and huge potential. It is a small unmanned helicopter with autonomous flight capability, which is suitable for military, civilian and scientific research fields. The basic structure of UAV consists of 6 modules: 1) UAV body, 2) navigation system, 3) flight control system, 4) wireless information communication system, 5) ground station system and 6) mission application system. [0003] As an important part of aircraft, UAV antenna has become an im...

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): G05D1/12
CPCG05D1/12
Inventor 刘建芳郑浩褚龙现马丽高敬礼
Owner PINGDINGSHAN UNIVERSITY