Scene adaptive target detection method based on motion foreground

A target detection and self-adaptive technology, applied in neural learning methods, instruments, biological neural network models, etc., can solve the problems of not considering regression domain differences, unknown data distribution, inability to effectively extract candidate frame targets, etc., to improve generalization performance effect

Pending Publication Date: 2022-04-26
HANGZHOU INNOVATION RES INST OF BEIJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the above algorithm only considers the domain difference in classification, and does not consider the domain difference in regression, resulting in unsatisfactory effects after scene changes.
In addition, for images with large domain differences, due to the unknown data distribut

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
  • Scene adaptive target detection method based on motion foreground
  • Scene adaptive target detection method based on motion foreground
  • Scene adaptive target detection method based on motion foreground

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0027] Figure 1 In the embodiment of , the source domain dataset is ns represents the true sample size in the source domain, represents sample i in the source domain, represents a collection of target box coordinate values for sample i in the source domain, Represents the target category of the ith sample in the source domain. In the present embodiment only a single category of pedestrians, Represents the set of motion foreground target box coordinate values for the ith sample in the source domain, The number of target boxes within the collection is the same The number of target boxes within the collection is inconsistent; the target domain dataset is used represents, where nT represents the true sample size in the target domain, Represents sample i in the target domain, Represents a dataset of motion foreground target frame coordinate values contained in sample i in the target domain.

[0028] According to the present embodiment, the scene adaptive target detection m...

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

With the increasing development of the deep learning technology, the requirement on the generalization performance of the model in a real environment is increased increasingly, and the influence of the differences of illumination, background and the like on the generalization performance of the model has aroused wide attention. The invention discloses a scene adaptive target detection method based on a motion foreground. According to the method, the target frame of the motion foreground is effectively utilized by utilizing the priori of the distribution consistency of the motion foreground and the global target data, and meanwhile, the instance feature similarity is calculated through the decoder, so that the effect of the model in the target domain is greatly improved. Experimental results show that the target detection effect of the method provided by the invention is greatly improved in a real environment.

Description

technical field [0001] The invention relates to a scene adaptive target detection method based on moving foreground. Background technique [0002] In the field of computer vision, object detection is an important topic. His task is to find the region of interest in the image and video, and determine its category and location. At present, many methods based on deep learning can achieve good results on benchmark datasets. However, due to the existence of domain differences, that is, when the target size, camera angle, illumination, and background environment change, the effect of the model will decline to varying degrees. . The simplest and most effective way to solve this problem when training models on the same domain is data-driven training. However, on the one hand, manual labeling of datasets costs a lot of manpower and material resources. On the other hand, many practical fields cannot be manually labeled. Therefore, in order to solve the degradation of model generaliz...

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): G06V20/40G06V10/42G06V10/764G06V10/74G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06N3/045G06F18/22G06F18/2415G06V10/82G06V10/62G06V2201/07
Inventor 胡海苗李明竹张译丹姜宏旭
Owner HANGZHOU INNOVATION RES INST OF BEIJING UNIV OF AERONAUTICS & ASTRONAUTICS
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