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

Foreground object extraction solution method based on computer vision

A computer vision and solution technology, applied in the field of foreground object extraction based on computer vision, can solve problems such as memory space fragmentation and system instability, and achieve the effect of eliminating the release process and low computing overhead

Inactive Publication Date: 2018-10-26
深圳腾视科技有限公司
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Some one-time traversal algorithms need to use dynamic space development. Frequent memory application and release will cause memory space fragmentation and make the system unstable.

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
  • Foreground object extraction solution method based on computer vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0022] see figure 1 , a computer vision-based foreground object extraction solution, comprising the following steps:

[0023] First, the image information is received from the infrared sensor, and the information is stored in the buffer pool, and the processor obtains its position, which is processed by DSP or other processing cores. The main processing procedures are described as follows:

[0024] 1. Scale the obtained image to meet a certain granularity; ...

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 foreground object extraction solution method based on computer vision, comprising the following steps: A, obtaining and storing a near-infrared camera image; B, binarizing the image at a predetermined threshold; C, using an algorithm to the binarized image to extract the foreground object position area; and D, feeding back to the upper level for other processing after theprocessing ends. The algorithm used in the connected domain tag of the invention creatively uses an algorithm of equivalent transformation on the basis of only traversing the secondary algorithm, which eliminates the process of releasing the dynamic memory application, and has extremely low computational overhead.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a solution method for extracting foreground objects based on computer vision. Background technique [0002] At present, the Internet of Things technology is becoming more and more developed, artificial intelligence technology is developing rapidly, and smart cameras with object detection functions based on computer vision technology are rapidly popularizing. [0003] The algorithms generally used for foreground object extraction have high spatio-temporal complexity, such as various algorithms in the field of deep learning, watershed algorithm, GrabCut algorithm, etc. Smart cameras using near-infrared light sources, vehicle cameras, and security cameras have limited hardware resources and cannot carry out algorithm execution with large space-time complexity, or their power consumption is large, which will affect the stability and life of the equipment for a long time, and increa...

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): G06T7/11G06T7/136G06T7/194
CPCG06T2207/10048G06T7/11G06T7/136G06T7/194
Inventor 高永光王庆庆
Owner 深圳腾视科技有限公司