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

Method and system for tracking human object

An object and human body technology, applied in the field of image processing, can solve the problems such as the inability to adjust the size of the tracking window adaptively when the size of the tracking window becomes larger or smaller, and the inability to effectively track the change of video size, etc., and achieve the effect of accurate detection and tracking.

Active Publication Date: 2016-09-28
湖南峰华智能科技有限公司
View PDF8 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing pedestrian detection and tracking method based on two-dimensional optical images cannot adaptively adjust the size of the tracking window as the target becomes larger or smaller, so it cannot effectively track the size-changing target in the video

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
  • Method and system for tracking human object
  • Method and system for tracking human object
  • Method and system for tracking human object

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] image 3 is a flow chart showing a method for tracking a human body object according to Embodiment 1 of the present invention. can be for example Figure 5 The illustrated system for tracking a human subject implements the method of this embodiment.

[0045] refer to image 3 , in step S310, acquire a 2D image and a 3D image with a human body object.

[0046] As mentioned above, the image of the scene containing the target human body can be continuously collected by the image acquisition device integrated with the two-dimensional image acquisition device and the three-dimensional image acquisition device or the two-dimensional image acquisition device and the three-dimensional image acquisition device placed together. It is also possible to read two-dimensional and three-dimensional images with human subjects that have been acquired by the aforementioned devices.

[0047] The two-dimensional image may be a two-dimensional optical image, and the three-dimensional ima...

Embodiment 2

[0057] Figure 4 It is a flow chart showing a method for tracking a human body object according to Embodiment 2 of the present invention. can be for example Figure 5 The illustrated system for tracking a human subject implements the method of this embodiment.

[0058] Figure 4 The processing of the method for tracking a human body object shown in is a specific implementation manner of the first embodiment. Figure 4 The processing of steps S310 to S330 shown in image 3 The processing of the corresponding steps in is similar and will not be repeated here.

[0059] In this embodiment, the human body object is tracked by using the directional saliency-based single-source object detection and tracking method with high accuracy of small object detection, and the calculated size of the human body object in the two-dimensional image (section Two dimensions) are used as the filtering variance to detect and track human objects, thereby improving the accuracy of tracking human o...

Embodiment 3

[0072] Exemplary embodiments of the present invention also provide a system for tracking a human subject. Figure 5 It is a logic block diagram showing a system for tracking a human body object according to Embodiment 3 of the present invention.

[0073] refer to Figure 5 , the system for tracking a human body object in Embodiment 3 includes a two-dimensional image acquisition device 510 for acquiring a two-dimensional image with a human body object, a three-dimensional image acquisition device 520 for acquiring a three-dimensional image with a human body object, and an image Analysis unit 530 .

[0074] Wherein, the two-dimensional image acquisition device 510 and the three-dimensional image acquisition device 520 are integrated into one image acquisition device, or placed together to work synchronously.

[0075] Here, the image analysis unit 530 is configured to execute the method of the first embodiment and / or the second embodiment.

[0076] Further, the system may furt...

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 embodiment of the invention provides a method and a system for tracking a human object. The method comprises steps: a two-dimensional image and a three-dimensional image with a human object are acquired; a first size of the human object and the distance between the human object and an image acquisition device are extracted from the three-dimensional image; according to the first size of the human object and the distance with the image acquisition device, the size of a real object presented by a single pixel in the two-dimensional image is determined, and according to the first size of the human object extracted from the three-dimensional image, a second size of the human object in the two-dimensional image is calculated; and according to the second size of the human object in the two-dimensional image, the human object is marked in the two-dimensional image. According to the technical scheme provided by the invention, effective detection and tracking on a motion human object can be realized in a condition in which the computation complexity is not added.

Description

technical field [0001] The invention relates to image processing technology, in particular to a method and system for tracking human objects. Background technique [0002] Pedestrian detection and tracking is a very challenging research topic in the field of computer vision, and it has a wide range of applications in video surveillance, traffic flow observation, robot navigation, video image compression and transmission, etc. Monitoring based on two-dimensional optical images can only provide video and image information, and it is difficult to obtain other information from monitoring, which greatly limits the effectiveness of surveillance video prior warning. [0003] The main monitoring object of the surveillance video is a moving person, and the proportion of the person in the surveillance video is affected by the focal length of the camera and the distance between the person and the camera, which will change greatly. During the tracking process of moving objects, the mov...

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): G06K9/00
CPCG06V40/23
Inventor 滕书华谭志国李洪
Owner 湖南峰华智能科技有限公司