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

Target detection method and device and electronic system

A target detection and target classification technology, applied in character and pattern recognition, instruments, biological neural network models, etc., can solve problems affecting network detection performance, good detection effect, poor detection effect, etc., to improve target detection effect, reduce The effect of the probability of the background being misidentified as a target

Pending Publication Date: 2021-02-26
MEGVII BEIJINGTECH CO LTD
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The target detection task mainly includes two sub-tasks, target classification and target detection frame regression. Common target detection tasks mainly include face detection tasks, pedestrian detection tasks, etc. Since the detection targets of these detection tasks are relatively single, the detection effect is better; and For the target detection of general objects, due to the wide variety of targets, the detection performance of the network is affected, and the problem of missed or false detection of targets is prone to occur, resulting in poor detection effect

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 and electronic system
  • Target detection method and device and electronic system
  • Target detection method and device and electronic system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] First, refer to figure 1 An example electronic system 100 for implementing the object detection method, device and electronic system of the embodiments of the present invention will be described.

[0028] Such as figure 1 A schematic structural diagram of an electronic system is shown, the electronic system 100 includes one or more processing devices 102, one or more storage devices 104, input devices 106, output devices 108, and may also include one or more image acquisition devices 110 , these components are interconnected via bus system 112 and / or other forms of connection mechanisms (not shown). It should be noted that figure 1 The components and structures of the electronic system 100 shown are exemplary rather than limiting, and the electronic system may also have other components and structures as required.

[0029] The processing device 102 may be a gateway, or an intelligent terminal, or a device including a central processing unit (CPU) or other forms of pr...

Embodiment 2

[0036] see figure 2 A flow chart of a target detection method shown, the method includes the following steps:

[0037] Step S202, extracting image features of the image to be detected;

[0038] The image to be detected can be input into the pre-trained feature extraction network to output image features; before the image to be detected is input to the feature extraction network, preprocessing operations may be required, for example, scaling the image to be detected to a specified Resolution, as an example, the resolution may be 800*1333. In the process of feature extraction network training, the number of sample images can also be expanded through specific operations, for example, flipping the existing sample images with a certain probability. Horizontal flip operation. The above-mentioned feature extraction network can be realized through various networks, and in this embodiment, it can be realized through a RetinaNet network, a network structure of resnet-50+FPN, and the...

Embodiment 3

[0046] This embodiment focuses on describing the network structure of the target detection network and the process of outputting results based on the network results.

[0047] First, the above-mentioned target detection network includes a classification sub-network and a position regression sub-network; the image features are input into the classification sub-network, and the target classification result of the image to be detected is output; the image features are input into the position regression sub-network, and the target of the image to be detected is output Positioning results and foreground recognition results. The difference from the target detection network in the related art is that the position regression sub-network needs to output target positioning results and foreground recognition results; based on this purpose, the position regression sub-network needs to set two branch structures; see image 3 As shown, the above position regression sub-network includes: a f...

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 and device and an electronic system. The method comprises the steps of extracting image features of a to-be-detected image; inputting the image features into a preset target detection network, and outputting a target classification result, a target positioning result and a foreground recognition result of the to-be-detected image, wherein the foreground recognition result comprises the probability that each position in the to-be-detected image belongs to the foreground; adjusting a target classification result based on the foreground recognitionresult; and determining a target detection result of the to-be-detected image based on the target positioning result and the adjusted target classification result. In the mode, the target classification result is adjusted based on the foreground recognition result of the to-be-detected image, so that the features belonging to the foreground area can be strengthened, the features belonging to thebackground area can be weakened, the probability of mistakenly recognizing the background as the target is reduced, and the target detection effect is improved.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a target detection method, device and electronic system. Background technique [0002] The target detection task mainly includes two sub-tasks, target classification and target detection frame regression. Common target detection tasks mainly include face detection tasks, pedestrian detection tasks, etc. Since the detection targets of these detection tasks are relatively single, the detection effect is better; and For the target detection of general objects, due to the wide variety of targets, the detection performance of the network is affected, and the problem of missed or false detection of targets is prone to occur, resulting in poor detection results. Contents of the invention [0003] In view of this, the purpose of the present invention is to provide a target detection method, device and electronic system to improve the target detection effect. [0004] 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): G06K9/46G06K9/62G06N3/04
CPCG06V10/44G06N3/048G06N3/045G06F18/2415
Inventor 朱本金
Owner MEGVII BEIJINGTECH 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