Target detection method and device, equipment and storage medium

A target detection and target object technology, applied in the scene field, can solve the problem that it is difficult to accurately predict the number of occluded target objects, and achieve the effect of accurate counting

Pending Publication Date: 2022-05-24
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the above methods are difficult to accurately predict the number of occluded target objects in the scene where the target objects are stacked and occluded, so a large error will be generated.

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
  • Target detection method and device, equipment and storage medium
  • Target detection method and device, equipment and storage medium
  • Target detection method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding and should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.

[0021] figure 1 The main flow of a method for implementing target detection according to an embodiment of the present disclosure is shown. like figure 1 As shown, the method includes: operation S110, performing target detection on the input image to obtain a visible target object; operation S120, performing spatial position relationship analysis according to the 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 a target detection method, device and equipment and a storage medium, relates to the technical field of artificial intelligence, in particular to the technical field of deep learning and computer vision, and can be applied to scenes such as image processing. According to the specific implementation scheme, a visible target object is obtained through target detection; performing spatial position relation analysis on the obtained visible target objects to obtain a spatial position relation between the visible target objects; according to the visible target objects and the spatial position relation between the visible target objects, constructing a spatial diagram structure; and determining the number of the target objects based on the space graph structure. The visible target objects can be counted according to the space diagram structure, and the number of the shielded target objects can be estimated according to the space diagram structure, so that the number of the target objects is more accurate, and the method is particularly suitable for scenes in which the target objects are mutually stacked and shielded.

Description

technical field [0001] The present disclosure relates to the technical field of artificial intelligence, in particular to the technical field of deep learning and computer vision, and can be applied to scenarios such as image processing. Background technique [0002] The early target counting is based on the target detection algorithm, that is, the number of target objects is obtained by counting the detection results of visible target objects. [0003] Later, with the continuous development and progress of artificial intelligence technology, the target technology method of using neural network models for end-to-end prediction appeared, but most of the existing neural network models also estimate the target object's distribution density based on the distribution density of visible target objects. quantity. [0004] However, the above methods are difficult to accurately predict the number of occluded target objects in the scene where the target objects are stacked and occlud...

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): G06V20/00G06V10/26G06V10/44G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/2411
Inventor 倪子涵安容巧陈科桦孙逸鹏姚锟
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
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