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

Object Tracking Method and Device

An object tracking and object technology, applied in the field of image recognition, can solve problems such as tracking failure, and achieve the effect of good tracking effect

Inactive Publication Date: 2017-08-11
RICOH KK
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current matching tracking algorithm based on the disparity value generally has the following problem: when the object is rotated to cause the shape or outline of the object to change, such as figure 1 As shown, when the vehicle as the tracked object turns, it may cause tracking failure

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
  • Object Tracking Method and Device
  • Object Tracking Method and Device
  • Object Tracking Method and Device

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0023] image 3 A flowchart of an object tracking method using a disparity map according to the first embodiment of the present invention is shown.

[0024] Such as image 3 As shown, in step S301, the size of the object in the disparity map of the current frame is determined based on the size of the object in the disparity map of the previous frame.

[0025] As is well known by those skilled in the art, the disparity map is based on any one of a pair of images as the reference image, the size is the size of the reference image, and the gray value of each point (pixel) is the value of the corresponding point in the reference image Parallax image. The disparity map can be obtained in many ways known in the art, which will not be described in detail here.

[0026] How to estimate the size of the object in the current frame according to the size of the object in the disparity map of the previous frame, there are many implementation methods in the art, and will not be described in detai...

no. 2 example

[0069] As mentioned above, in the object tracking method according to the first embodiment, the matching features are not reconstructed in the disparity map of each frame, so the matching features used in the disparity map of each frame are actually the same, namely The matching feature constructed in the first frame. This method may affect the tracking effect when the object is occluded. In response to this situation, this embodiment provides an improved object tracking method.

[0070] The object tracking method according to this embodiment is basically the same as the object tracking method described in the first embodiment. The only difference is that the position of the object in the disparity map of the current frame is determined in step S305 (that is, the position area with the greatest matching degree). ) After that, in the subsequent step S306, the matching feature adopted in the current frame is optimized. The following will combine Picture 10 Give a detailed explan...

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

An object tracking method and device are provided. The object tracking method includes: determining the size of the object in the disparity map of the current frame based on the size of the object in the disparity map of the previous frame; sliding in a predetermined area in the disparity map of the current frame with a rectangular frame corresponding to the size ; The matching feature used in the disparity map of the previous frame is used as the matching feature used in the disparity map of the current frame, and for each position area where the rectangular frame in the disparity map of the current frame slides, calculate the matching feature in the position area Vector representation; calculate the matching degree between the vector representation of the matching feature in each position area and the vector representation of the matching feature in the previous frame of the disparity map where the object is located; determine the position area with the maximum matching degree in each of the position areas , as the position of the object in the disparity map of the current frame. The object tracking method does not cause tracking loss when the tracked object rotates, and has a good tracking effect.

Description

Technical field [0001] The present invention generally relates to image recognition, in particular to object tracking methods and equipment Background technique [0002] Object tracking technology has a wide range of applications in many fields such as monitoring, human-computer interaction, car navigation, and video indexing. [0003] Matching and tracking objects frame by frame is a classic research topic. At present, many methods of matching and tracking objects based on gray / color images have been proposed, such as tracking based on geometric shapes, target contours, color histograms, gradient histograms, etc. For example, the patent document US8102390B2 discloses a frame-by-frame matching tracking method based on grayscale images. In this method, the image block in the grayscale image is divided into several regions, and the fast Fourier transform (FFT) value of each region is used as the matching feature to match the object, and finally realize the tracking of the object. ...

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): G06T7/246G06T7/254
Inventor 杨田雨刘殿超鲁耀杰师忠超王刚
Owner RICOH KK