Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method and device for tracking a moving object

A technology for moving objects and target objects, which is applied in the field of artificial intelligence and can solve problems such as loss of tracking of moving objects

Active Publication Date: 2021-02-02
ZHEJIANG DAHUA TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a moving object tracking method and device to solve the problem of missing moving object tracking at the dividing line in the prior art

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
  • A method and device for tracking a moving object
  • A method and device for tracking a moving object
  • A method and device for tracking a moving object

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] Figure 5 A schematic diagram of the moving object tracking process provided by the embodiment of the present invention, the process includes the following steps:

[0049] S101: For each frame image in the continuous frame images, divide the frame image into at least two sub-images according to a preset rule, and determine a dividing line between every two adjacent sub-images.

[0050] Embodiments of the present invention provide a moving object tracking method applied to an electronic device, and the electronic device may be a PC, a tablet computer, or an image acquisition device.

[0051] The electronic device can obtain continuous frame images. If the electronic device is an image acquisition device, the electronic device itself can directly obtain continuous frame images. If the electronic device is a PC, tablet computer, etc., it can receive the continuous frame images sent by the image acquisition device. .

[0052] For each frame image in the continuous frame i...

Embodiment 2

[0067] In order to improve the efficiency of determining the moving object in the image, on the basis of the above embodiments, in the embodiment of the present invention, for each target object in each sub-image of each frame of image, according to the target object Coordinate information, judging whether the target object includes at the dividing line of the sub-image:

[0068] For each frame image, each sub-image of the frame image is sent to the corresponding digital signal processor DSP; for each target object in each sub-image, the corresponding digital signal processor DSP according to the target object The coordinate information of the target object is judged whether the target object is at the dividing line of the sub-image.

[0069] The electronic device includes a plurality of DSPs, after each frame of image is divided into at least two sub-images according to preset rules, for each frame of image, each sub-image of the frame of image is sent to the corresponding DS...

Embodiment 3

[0073] On the basis of the above embodiments, in the embodiment of the present invention, if the target object is not at the dividing line of the sub-image, the method further includes:

[0074] Based on the sub-image and the sub-image corresponding to the previous frame image of the frame image, a moving object detection algorithm is used to determine whether the target object is a moving object;

[0075] If yes, determine the target object as a moving object; and track the moving object.

[0076] For each target object in each sub-image of each frame image, if it is judged that the target object is not at the dividing line of the sub-image, based on the sub-image and the sub-image corresponding to the previous frame image of the frame image, a motion The object detection algorithm judges whether the target object is a moving object, and if so, determines the target object as a moving object. Wherein, the moving object detection algorithm may be an improved Chan-Vese algorit...

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 a moving object tracking method and device, and relates to the field of artificial intelligence of image processing technology. In the embodiment of the invention, for each sub-image of each frame image, if the target object in the sub-image is at the dividing line , when the target object does not appear in the sub-image corresponding to the previous frame image of the frame image, determine the target object as a moving object, or, when the target object appears in the sub-image corresponding to the previous frame image of the frame image object, based on the sub-image and the sub-image corresponding to the previous frame image of the frame image, the moving object detection algorithm is used to determine that the target object is a moving object, and the target object is determined as a moving object; and track each movement object. When a target object appears at the dividing line of the sub-image, the target object is determined as a moving object and tracked, thus avoiding the problem that the moving object at the dividing line is not detected and the tracking of the moving object is lost.

Description

technical field [0001] The invention relates to the field of artificial intelligence of image processing technology, in particular to a method and device for detecting a moving object. Background technique [0002] In the field of security video surveillance, as user demands gradually shift towards high-definition and panoramic images, more and more cameras begin to support the processing of high-definition and panoramic images. Panoramic and high-definition means that multi-sensor (sensor) image stitching technology has super-large viewing angles, super-large resolution and super-high-pixel images, such as 16 million pixel and 32 million pixel images. However, traditional video image acquisition and processing systems are mostly processed by a single sensor and a single DSP (Digital Signal Processing, Digital Signal Processor). Complete image processing with such a large resolution. In order to achieve the timeliness of a single DSP for processing large-resolution images,...

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): G06T7/215G06T7/246G06K9/00
CPCG06T7/215G06T7/246G06V20/40G06V2201/07
Inventor 李树奎
Owner ZHEJIANG DAHUA TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com