Object analysis method, device and storage medium

An object analysis and target object technology, applied in the computer field, can solve the problem that the target detection algorithm cannot achieve speed and accuracy, and improve at the same time.

Active Publication Date: 2022-07-26
SUZHOU KEDA TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This application provides an object analysis method, device and storage medium, which can solve the problem that the existing target detection algorithm cannot achieve simultaneous improvement of speed and accuracy

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 analysis method, device and storage medium
  • Object analysis method, device and storage medium
  • Object analysis method, device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The specific implementations of the present application will be described in further detail below with reference to the accompanying drawings and embodiments. The following examples are used to illustrate the present application, but are not intended to limit the scope of the present application.

[0049] First, some terms involved in this application are introduced.

[0050] Center-based detection network (CenterNet): is an end-to-end object detector. Object detection requires the detection of the smallest rectangular box containing the object. Traditional object detectors usually list and classify a large number of candidate boxes. And CenterNet locates the target to be detected to a point, that is, the center point of the detection rectangle. In other words, in CenterNet, each center point corresponds to the position of a target, and there is no need to judge the overlap of rectangular boxes, and the target detection speed and efficiency are higher than those of t...

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 present application relates to an object analysis method, device and storage medium, belonging to the field of computer technology. The method includes: obtaining a target image; inputting the target image into a pre-trained image recognition model to obtain an object analysis result of the target image. It includes target object position information, target object key point information and target object attribute information; it can solve the problem that the existing target detection algorithm cannot achieve the simultaneous improvement of speed and accuracy; the fusion method makes the obtained feature layer more comprehensive and comprehensive. , while improving the sensitivity of identifying targets at different scales, and improving the accuracy of detection; the use of depthwise separable convolution can speed up the inference time of the feature layer fusion part; the fusion attribute analysis function enables a model to have both target detection, The three functions of key point prediction and attribute output not only reduce the memory occupancy rate of the three functions, but also improve their running speed in the system.

Description

【Technical field】 [0001] The present application relates to an object analysis method, device and storage medium, belonging to the technical field of computers. 【Background technique】 [0002] With the development of artificial intelligence technology, more and more target detection algorithms have emerged. Such as anchor-free series of algorithms. [0003] The anchor-free series of algorithms avoids the pre-setting of anchor boxes, reduces a lot of related calculations, and significantly improves its memory usage and speed. Moreover, there is no pre-set anchor frame, and the prediction frame returns to the target position within the entire feature map, which is suitable for the detection of target objects of various shapes and sizes. [0004] However, the existing target detection algorithm will reduce the accuracy of the algorithm while improving the speed of the algorithm, resulting in inaccurate target detection results. [Content of the invention] [0005] The prese...

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): G06V10/774G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/214
Inventor 丁鑫肖潇付马孟祥昊
Owner SUZHOU KEDA TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap