Unlock instant, AI-driven research and patent intelligence for your innovation.

Image target detection method and device based on dynamic label distribution

A technology of target detection and distribution, which is applied in the field of computer vision to achieve the effect of improving performance and detection accuracy

Pending Publication Date: 2022-04-01
SUN YAT SEN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the deficiencies in the above-mentioned prior art, the present invention provides an image target detection method and device based on dynamic label allocation, so that the end-to-end target detection model can avoid the problems caused by manual post-processing while improving its current performance. Label assignment method and performance in object detection at different scales

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
  • Image target detection method and device based on dynamic label distribution
  • Image target detection method and device based on dynamic label distribution
  • Image target detection method and device based on dynamic label distribution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] like figure 1 Shown is an image target detection method based on dynamic label allocation disclosed in this embodiment, which is suitable for airport aircraft detection or other image target detection in satellite images. The method specifically includes the following steps:

[0045] Step 1, preprocessing the images marked with targets to be detected to obtain training images and verification images, and collecting the training images into a training image set, and collecting the verification images into a verification image set;

[0046] Step 2, construct an end-to-end target detection model, and improve the end-to-end target detection model, including normalization improvement and improvement of label assignment method based on regression state;

[0047] Step 3, iteratively train the improved end-to-end target detection model through the training image set, and use the verification image set to verify the accuracy of the end-to-end target detection model in each round...

Embodiment 2

[0067] like image 3Shown is an image object detection device based on dynamic label allocation disclosed in this embodiment, which is suitable for airport aircraft detection or other image object detection in satellite images. The image target detection device includes an image processing module, a model building module, a model training module and a target detection module. Wherein, the image processing module is used to preprocess the images marked with the target to be detected to obtain training images and verification images, and collect the training images into the training image set, and collect the verification images into the verification image set; model construction The module is used to improve the end-to-end target detection model based on the SparseRCNN network, and construct the improved end-to-end target detection model, wherein the improvement of the end-to-end target detection model includes normalization improvement and regression state-based dynamic The l...

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 an image target detection method and device based on dynamic label allocation, the device comprises an image processing module, a model building module, a model training module and a target detection module, the model building module is improved through a normalization mode of an end-to-end target detection model and a label allocation mode, and the model training module is used for training the target detection module. And constructing an improved end-to-end target detection model, and performing target detection on the image through the optimal target detection model obtained through training. The method is applied to the technical field of computer vision, so that the end-to-end target detection model can avoid the problems caused by manual post-processing, the performance of the end-to-end target detection model in the aspects of a label distribution mode and different-scale target detection at present is improved, and the detection precision is improved.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to an image target detection method and device based on dynamic label allocation. Background technique [0002] Object detection is an important task in computer vision and is the basis for many other computer vision tasks, such as instance segmentation, object tracking, and pose estimation. The rapid development of deep learning has made a major breakthrough in object detection and has become a research hotspot. [0003] Target detection of airport aircraft in satellite images is of great military significance. It can obtain military activity information, assess the importance of enemy airports, and provide a basis for precise strikes. Recently, computer vision techniques, especially deep learning-related methods, have been gradually applied to object detection of aircraft in satellite imagery. The methods based on deep learning are classified according to label matching ...

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): G06V10/774G06V10/776G06V10/82G06V10/25G06V20/13G06N3/04G06N3/08G06K9/62
Inventor 张清凌张斐钊莫泽文
Owner SUN YAT SEN UNIV