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

Image processing memory management method and management system for target detection

An image processing and memory management technology, applied in the field of image processing, can solve problems such as low reuse rate and high memory usage overhead, and achieve the effect of improving memory reuse efficiency

Active Publication Date: 2019-01-01
旺微科技(上海)有限公司
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0015] The technical problem to be solved by the present invention is how to solve the defects of large memory usage overhead and low reuse rate 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
  • Image processing memory management method and management system for target detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] In order to have a further understanding and understanding of the structural features and the achieved effects of the present invention, the preferred embodiments and accompanying drawings are used for a detailed description, as follows:

[0049] A memory management method for multi-target detection, the content of which is:

[0050] S1: Obtain the R channel data of the complete original image detected, calculate and save only the normalization factor of the R channel (release the R channel data after the normalization factor calculation is completed); take an image with a height of H and a width of W as an example , save the R channel data of each point in Byte, define the memory RGB_mem size as H×W (Byte), and calculate the normalization factor (multiplication factor scale_r and subtraction factor shift_r), the purpose of which is to normalize the maximum value of the data Normalize to a reasonable data range to ensure that the accuracy of subsequent data processing i...

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 image processing memory management method and a management system for target detection, a three-channel raw data normalization factor of a trichromatic graph (RGB) is respectively calculated and then the data memory is freed, taking out the original image data point by point and linearly combining the normalized + trichromatic image (RGB) to gray level, At that same time,the original grayscale image data memory is multiplexed aft zooming (resize) the picture size, and the reverse zooming (resize) restoration is performed before the target region is reused or extracted subsequently, so that the memory multiplexing efficiency is improved. As that gray scale of the trichromatic image (RGB) is converted point by point, the extra memory overhead is not saved in the process, and the gray scale image data size is still saved to the defined memory multiplexing space, the size H * W (Byte).

Description

technical field [0001] The invention relates to the technology in the field of image processing, and specifically designs an image processing memory management method and management system for target detection. Background technique [0002] With the development of mobile Internet, APP applications have grown explosively. Many APPs involve the entry of ID card, bank card, driving license, and business card information, such as financial APP, Internet APP, mobile visitor system, etc.; if Manually input ID card, bank card, driving license, and business card information is slow, error-prone, and the user experience is very poor. With the rapid development of computer technology, multimedia technology, and artificial intelligence technology, the application of image processing technology is becoming more and more extensive, and certain achievements have been made in scientific research, education management, medical and health, military and other fields. In these applications, i...

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): G06T1/60G06T7/73G06T7/90G06T3/40
CPCG06T1/60G06T3/40G06T7/73G06T7/90G06T2207/10024Y02D10/00
Inventor 刘若堃肖立波徐昕
Owner 旺微科技(上海)有限公司