Unmanned ship sea surface correlation filter target tracking method suitable for blocking scene

A technology of correlation filtering and target tracking, applied in image data processing, instruments, calculations, etc., can solve the problems of tracking model drift, poor tracking result model, tracking failure, etc., to achieve the effect of solving tracking drift and ensuring tracking speed.

Pending Publication Date: 2018-11-16
SHANGHAI UNIV
View PDF3 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The tracking algorithms of the above two types of update strategies do not judge the tracking results of the correlation filtering algorithm, but directly update the model. Therefore, this type of method has the problem of updating the model due to poor tracking results, resulting in the model Contaminated, especially when the target is occluded or the background similarity is high, the

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
  • Unmanned ship sea surface correlation filter target tracking method suitable for blocking scene
  • Unmanned ship sea surface correlation filter target tracking method suitable for blocking scene
  • Unmanned ship sea surface correlation filter target tracking method suitable for blocking scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] In order to make the object, technical solution and advantages of the present invention clearer, the preferred embodiments of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0020] like figure 1 As shown in Fig. 1, an unmanned surface correlation filtering target tracking method suitable for occlusion scenes, figure 2 It is a flow chart of the method, which mainly includes the following steps:

[0021] S01, feature extraction of the search area:

[0022] 1) Feature applicability analysis:

[0023] For unmanned marine target tracking, the HOG feature is more robust to motion blur and illumination changes, so the algorithm is robust to sea surface illumination changes and reflections, but it is not sensitive to deformation, scale changes, and target ships. When the shape similarity is high, the robustness is poor, and at the same time, the ability to express small target features on the sea is weak; the ...

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 relates to an unmanned ship sea surface correlation filter target tracking method suitable for a blocking scene. In the event of target blocked or high background similarity in the target tracking process of the surface unmanned ship, the tracker is interfered along with further blocking of the target or background clutter, resulting in the model being polluted by occlusion, becomingmore and more impossible to discriminate and finally causing drifting of the tracking model. Aiming at the problem, based on the correlation filter KCF algorithm, the tracking state is discriminatedby defining the oscillation index and the peak value of a correlation filter response graph to realize self-adaption update of the correlation filter model. The method in the invention has obvious advantages in sea surface target tracking aspect, particularly, the sea surface target tracking in the case that the target is blocked; and the real-time requirement of tracking of the unmanned ship is achieved.

Description

technical field [0001] The invention relates to a correlation filtering-based tracking method for an unmanned surface vehicle and a sea surface target suitable for occlusion scenes, and belongs to the field of computer vision target tracking. Background technique [0002] The surface unmanned vehicle is a surface intelligent carrier platform that can navigate autonomously on the water surface and complete various tasks. It is equipped with laser radar, camera, inertial navigation, GPS, antenna, ultrasonic, sonar and other sensor equipment to realize Path planning, autonomous navigation and obstacle avoidance, target detection, recognition and tracking and other functions, so as to complete civil and military tasks such as marine water quality detection, underwater archaeology, ocean cruising, and ship escort. The unmanned boat is mainly composed of the underlying software and hardware system, environmental perception system, navigation and obstacle avoidance system, control ...

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): G06T7/231G06T7/246
CPCG06T2207/10016G06T2207/20081G06T7/231G06T7/246
Inventor 李小毛张云东彭艳谢少荣罗均
Owner SHANGHAI 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