Target shape detecting method and device

A target shape, to-be-detected technology, applied in image data processing, instrument, character and pattern recognition, etc., can solve problems such as low algorithm operation efficiency, increased false detection, and confusion, and achieve stable efficiency, robustness, and high efficiency. and robustness effects

Inactive Publication Date: 2009-03-18
PANASONIC CORP
View PDF4 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the technology disclosed in Patent Document 4 still has the following problems: edge points need to be processed separately, and there is a possibility that edges in multiple directions can be hashed out to false targets, resulting in increased false detections
On the other hand, due to the time-consuming operations of edge point projection and center point accumulation, the algorithm provided by this patent document has low operating efficiency

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
  • Target shape detecting method and device
  • Target shape detecting method and device
  • Target shape detecting method and device

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example ( 3

[0028] First Embodiment (Triangle Detection and Tracking)

[0029] In order to facilitate the understanding of the present invention, a regular triangle is taken as an example to describe the process of detecting and tracking a regular triangle. For simplicity, it can be assumed that the base of the equilateral triangle is above and horizontal. Figures 2a to 2d It shows the process of detecting and tracking the equilateral triangle target at time t and t+1.

[0030] It can be assumed that the target position of the equilateral triangle to be detected in the current frame of the image at a given time t is p t (x, y), the possible position of the target in the frame at time t+1 is located in a w×h rectangular box R. Where w represents the width of the rectangular box R, and h represents the height of the rectangular box R. The rectangular box R only needs to give the approximate area where the target may appear, and does not require an explicit motion model or calculation of...

no. 2 example

[0046] The second embodiment (quadrangle detection)

[0047] The process of detecting the shape of a quadrilateral is described below by taking a quadrilateral as an example. For the sake of simplicity, the description of the same part as the triangle detection and tracking method is omitted here, and only the differences from the triangle-shaped target tracking method are described.

[0048] Figure 4 A schematic diagram showing the continuation direction for continuation of a regular quadrilateral target shape. The sampling points in the quadrilateral target shape detection process can have four extension directions. The four continuation directions can be perpendicular to the four sides that make up the quadrilateral. Without loss of generality, it can be assumed that the angles of the four sides of the target quadrilateral are θ 1 , θ 2 , θ 3 , θ 4 , then the continuation direction angle of the sampling point is θ 1 -90, theta 2 -90, theta 3 -90, theta 4 -90. T...

no. 3 example

[0050] The third embodiment (circle detection)

[0051] Refer below Figure 5a with 5b A detection and tracking method for objects with circular outlines is described. For a circle, if each sampling point is extended in the vertical direction, the directions of the candidate sides of the edge points generated by the sampling points are different due to the different positions of the sampling points.

[0052] For circular targets, each sampling point can be fixed along 4 continuation directions. For the convenience of calculation, four extension directions of 0, 90, 180, and 270 degrees are usually selected, as shown in Fig. 5(a). It should be noted that the present invention is not limited thereto, and each sampling point may also extend along 8 directions or 16 directions. In the case of extension along eight directions, the extension directions can be 0, 45, 90, 135, 180, 225, 270, and 315 degrees, as shown in Fig. 5(b). Similarly, if the continuation is carried out alo...

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 provides an object shape detecting and tracing method, the steps of the method comprise receiving a to-be-detected image, setting a detection area in the to-be-detected image, generating a plurality of sample points in the detection area, extending the sample points along a preset direction, obtaining marginal points at the extending direction through calculating, constructing candidate margins of a to-be-detected shape, performing vote operation to characteristic points of the to-be-detected shape based on the constructed candidate margins, counting vote operation results to confirm whether a vote peak value exists or not, if the vote peak value exists, then confirming the characteristic points corresponding to the to-be-detected shape exist.

Description

technical field [0001] The present invention relates to a target shape detection and tracking method and device, in particular, to the detection and recognition of a moving target with a certain shape and outline, such as a traffic shape, and after the corresponding shape is detected, the shape can be searched for A method and device for tracking the shape of a target by limiting the range. Background technique [0002] Object detection such as shape is an important task in machine vision. With the rapid development of computer and electronic technology, the research and development of the detection and recognition of moving targets with a certain shape and outline, especially the detection and recognition of traffic signs, has been paid more and more attention. Automatic identification of traffic signs is an important part of intelligent transportation technology. Accurate recognition of objects such as traffic signs can effectively reduce the probability of traffic accid...

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 Applications(China)
IPC IPC(8): G06K9/46G06T7/60G06V10/48
CPCG06T2207/10016G06K9/4633G06T2207/30252G06T2207/20168G06T2207/20156G06K9/00818G06T7/0083G06T7/12G06V20/582G06V10/48
Inventor 谢晓辉刘伟杰吴刚魏强
Owner PANASONIC CORP
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