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

Domain-adaptive foggy day image target detection method and device

A technology of target detection and domain adaptation, applied in the field of target detection, can solve the problems of poor detection accuracy, insufficient feature map, and high missed detection rate, improve detection frame accuracy and missed detection rate, strengthen domain discrimination ability, save money cost effect

Active Publication Date: 2021-04-09
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the feature map extracted by the current detection model for domain adaptation is not fine enough, and the multi-scale design of the domain classifier is not comprehensive enough, resulting in limited improvement of the method based on domain adaptation and a high rate of missed detection.
[0007] In summary, the existing fog image detection methods have defects such as poor detection accuracy, poor real-time performance and applicability, and high missed detection rate.

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
  • Domain-adaptive foggy day image target detection method and device
  • Domain-adaptive foggy day image target detection method and device
  • Domain-adaptive foggy day image target detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0078] Such as figure 1 As shown, the embodiment of the present invention discloses a domain-adaptive object detection method in foggy images. The method introduces attention and can be applied to object detection in foggy images, and can improve the accuracy and missed detection rate of foggy image detection. The method comprises the steps of:

[0079] Select the general target detection data set as the source domain and preprocess it, transform the backbone network to improve the multi-scale performance of the model, and then train the target detection model;

[0080] After the training is completed, a domain classifier is built based on the target detection model, and the high-level attention of global average pooling is integrated in each layer, and the entire transfer learning model is built so far;

[0081] Input the foggy image as the target domain to start training, and get a detection model that is better adapted to the foggy scene.

[0082] In this embodiment, the ...

Embodiment 2

[0121] Such as Figure 6 As shown, the embodiment of the present invention provides a domain adaptive fog image target detection device, including the following modules:

[0122] The preprocessing module is used to preprocess the obtained target detection data set, and perform multi-scale performance transformation and reconstruction of the backbone network;

[0123] The first training module is used for utilizing the preprocessed target detection data set to train the transformed backbone network to obtain the target detection model;

[0124] A building block for building a domain classifier for the target detection model;

[0125] The second training module is used to train and build the target detection model of the domain classifier to obtain a domain adaptive detection model by using the fog image and the preprocessed target detection data set;

[0126] The detection module is used to use the domain adaptive detection model to perform target detection on the foggy image...

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 discloses a domain-adaptive foggy day image target detection method and device, and belongs to the technical field of target detection, and the method comprises the following steps: carrying out preprocessing on an obtained target detection data set; carrying out model multi-scale performance reconstruction on the backbone network; training the reconstructed backbone network by using the preprocessed target detection data set to obtain a target detection model; building a domain classifier for the target detection model; training the target detection model with the domain classifier being built by adopting the foggy day image and the preprocessed target detection data set to obtain a domain-adaptive detection model; and performing target detection on the foggy day image to be detected by using the domain-adaptive detection model. The method and device have the advantages of being high in detection precision, high in real-time performance and applicability, low in omission ratio and the like, and the performance of the detection model in a foggy day scene is improved.

Description

technical field [0001] The present invention relates to the technical field of target detection in deep learning and computer vision, in particular to a method and device for domain adaptive fog image target detection. Background technique [0002] With the development of artificial intelligence-based autonomous driving technology, safety has become an important issue to be solved in intelligent transportation. In recent years, due to the acceleration of industrial development, more and more serious environmental pollution has been caused. Most areas frequently encounter fog, haze, etc. Bad weather is coming. Due to the wide coverage of smog, road visibility is low, which seriously interferes with the detection of traffic elements through cameras in autonomous driving scenarios. Image target detection itself is a research hotspot in the field of deep learning and computer vision. However, in foggy days, the images collected by imaging equipment not only decrease in clarity ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/20G06V2201/07G06N3/045G06F18/253G06F18/254Y02A90/10
Inventor 邵文泽贾再兴
Owner NANJING UNIV OF POSTS & TELECOMM
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