Detection model training method and device, target detection method and device and electronic system

A technology for detecting models and electronic equipment, applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as a large amount of manpower and time costs, limited target labeling information, and affect the training accuracy of detection models, so as to improve detection accuracy Effect

Pending Publication Date: 2021-08-10
BEIJING KUANGSHI TECH
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the training of the detection model needs to label a large number of images. Usually, the label information includes the category and location information of the target object (that is, the ground truth...

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
  • Detection model training method and device, target detection method and device and electronic system
  • Detection model training method and device, target detection method and device and electronic system
  • Detection model training method and device, target detection method and device and electronic system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] First, refer to figure 1 A schematic structural diagram of the electronic system 100 is shown. The electronic system can be used to implement the detection model training method, object detection method and device of the embodiments of the present invention.

[0040] 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 one or more image acquisition devices 110, these components The interconnections are 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.

[0041] The processing device 102 may be a server, an intelligent terminal, or a device including a cen...

Embodiment 2

[0049] As a possible implementation, see figure 2 , this embodiment provides a target detection model, and the detection model includes: a backbone network, and a classification network, a regression network, and a multi-category prediction network connected to the backbone network.

[0050] The backbone network is used to extract the semantic features of the image samples and output the feature map of the image samples. The backbone network can include ResNet, AlexNet, or VGG, etc., which can be selected according to actual needs. The regression network is used to locate the position coordinates of the target in the feature map. Specifically, separate image frame selection is performed on different positions in the feature map, so that several detection frames containing the specified target and the position coordinates of the detection frame on the feature map are obtained. Taking the detection frame as a rectangular frame as an example, The position coordinates can usuall...

Embodiment 3

[0064] On the basis of the second embodiment above, in order to further improve the reliability of the new sample label, the present embodiment changes the generation method of the new sample label in the above step S304 (that is, based on the feature map of the image sample and the original label generation on the image sample New sample label) has been optimized, and the following steps can be used specifically:

[0065] Step 1. For the feature map of the image sample, the anchor frame group is generated with the pixel point on the feature map as the coordinate center.

[0066] Step 2. Assign new sample labels to the anchor boxes based on the IoU between the anchor boxes in the above anchor box group and the ground truth boxes marked on the above image samples, and the original labels of the ground truth boxes.

[0067] On the basis of the above-mentioned second embodiment or on the basis of the above-mentioned steps 1 to 2, in order to ensure that the number of sample label...

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 detection model training method and device, a target detection method and device and an electronic system, and relates to the technical field of target detection, and the detection model training method and device comprises the steps: obtaining an image sample corresponding to a current period from an image sample set in at least one training iteration period, obtaining a feature map of each image sample through a backbone network, and then generating a new sample label based on the feature maps of the image samples and the original labels on the image samples; and training a classification network, a regression network and a multi-class prediction network based on the image samples after the new sample labels are distributed, controlling the number of training iterations by taking loss functions corresponding to the three networks as training constraint conditions, and establishing a detection model for target detection until training is stopped. Through the invention, the problem that a detection model has relatively limited target labeling information in the image can be relieved, and the training precision of the detection model is improved.

Description

technical field [0001] The invention relates to the technical field of target detection, in particular to a training method for a detection model, a target detection method, a device and an electronic system. Background technique [0002] A single-stage detection model or a two-stage detection model often has two branches, namely the regression branch and the classification branch; the regression branch is used to predict the position of the target in the image, and the classification branch is used to predict the category of the target in the image. [0003] However, the training of the detection model needs to label a large number of images. Usually, the label information includes the category and location information of the target object (that is, the ground truth information), which often requires a lot of manpower and time costs, which leads to the target label information in the image. Relatively limited, to a certain extent, it affects the training accuracy of the det...

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
IPC IPC(8): G06K9/62G06K9/46
CPCG06V10/44G06V2201/07G06F18/2415
Inventor 陈坤鹏姚聪王鹏周争光
Owner BEIJING KUANGSHI 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