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

A method and device for detecting an occluded object

An object detection and object technology, which is applied in the field of image processing, can solve the problems of whether objects of different shapes and sizes are occluded and cannot be distinguished from each other, so as to improve the accuracy of occlusion recognition and meet the accuracy requirements. The effect of improving detection accuracy

Active Publication Date: 2022-05-17
INST OF MICROELECTRONICS CHINESE ACAD OF SCI
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of the above analysis, the embodiment of the present invention aims to provide a method and device for detecting occluded objects to solve the problem that the existing methods cannot detect whether occlusion occurs between objects of different shapes and sizes and cannot distinguish mutually occluded objects from other objects. Object Distinguishing Problems

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
  • A method and device for detecting an occluded object
  • A method and device for detecting an occluded object
  • A method and device for detecting an occluded object

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] figure 2 It is a flowchart of an occluded object detection method according to an embodiment of the present invention, and the method includes:

[0060] 202: Collect images of objects in dense scenes, using partially overlapping and occluded objects in dense scenes as positive sample images, and using single objects with different backgrounds as negative sample images.

[0061] 204: Preprocessing the acquired object image, converting the preprocessed image into a grayscale image, and simulating the formation of occlusion effects through the Mixup data enhancement method to enrich the diversity of data samples and prevent overfitting.

[0062] 206: Fusing the category and position coordinates of the target to be recognized (single object, mutually occluded objects) in the image into the annotation information of the image, and recording the annotation information of the training image using the xml file.

[0063] 208: Design a network model for occluded object detection...

Embodiment 2

[0104] The method for detecting occluded objects based on deep learning has been described in detail above, and the present invention also provides a device for detecting occluded objects based on deep learning corresponding to the method, because the embodiment of the device part and the embodiment of the method part Corresponding to each other, so for the embodiment of the device part, please refer to the description of the embodiment of the method part, and details will not be repeated here.

[0105] figure 2 , Figure 3A and Figure 3B A schematic structural diagram of an occluded object detection device provided by an embodiment of the present invention, including an acquisition module, a preprocessing module, a labeling module, a detection model generation module and a detection module.

[0106] The occluded object detection device based on deep learning provided by the embodiment of the present invention includes:

[0107] The collection module is used to collect ima...

Embodiment 3

[0116] In addition, the present invention also provides an occluded object detection device, Figure 4 A hardware structure schematic diagram of an object detection device provided for an embodiment of the present invention includes: a memory for storing a computer program; and a processor for executing the above-mentioned occluded object detection method according to instructions in the computer program.

[0117] In addition, the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned method for detecting occluded objects based on deep learning are realized.

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 relates to a method and device for detecting an occluded object, which belongs to the technical field of image processing and solves the problem that existing methods cannot detect whether occlusion occurs between objects of different shapes and sizes and cannot distinguish mutually occluded objects from other objects. The method includes: obtaining the training image and the image to be recognized in the dense scene and preprocessing the training image and the image to be recognized; marking the category and position coordinates of the target to be recognized in the preprocessed training image; establishing an improved neural network Model and use the marked training images to train the improved neural network model to obtain the detection model. The improved neural network model includes the CBAM attention module to enhance the feature extraction ability of the detection model to be recognized; Occluded objects are detected to obtain detection results. This method can improve the detection accuracy and positioning accuracy of occluded objects to meet the accuracy requirements of the algorithm in industrial applications.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method and device for detecting occluded objects. Background technique [0002] With the vigorous development of deep learning in recent years, object detection technology has also been greatly developed. Various object detection algorithms are relatively mature, but there is still a lot of room for optimization in target detection in special scenes. Here we mainly study object detection in dense scenes. Since objects in dense scenes are not in an ideal detection environment, objects of different shapes and sizes may be occluded from time to time, which often results in inaccurate object detection. In some scenes, it is required to accurately detect a single object, which puts forward stricter requirements for the detection model. It is necessary to detect whether occlusion occurs between objects of different shapes and sizes, and to distinguish mutually occlu...

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 Patents(China)
IPC IPC(8): G06V10/774G06K9/62G06N3/08G06T7/73G06V10/764
CPCG06N3/08G06T7/73G06T2207/20081G06F18/214G06F18/24
Inventor 林美伶史朝坤胡子骏郝悦星赵政杰
Owner INST OF MICROELECTRONICS CHINESE ACAD OF SCI
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