General target detection method of adaptive attention guidance mechanism

A technology of target detection and attention, applied in neural learning methods, computer components, instruments, etc.

Active Publication Date: 2020-06-09
NANJING UNIV OF INFORMATION SCI & TECH
View PDF1 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Purpose of the invention: In view of the above problems, the present invention proposes a general target detection method of an adaptive attention guidance mechanism, which solves how to quickly and accurately distinguish them and detected problems, the SnipeDet algorithm is proposed

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
  • General target detection method of adaptive attention guidance mechanism
  • General target detection method of adaptive attention guidance mechanism
  • General target detection method of adaptive attention guidance mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0052] figure 1 It is a schematic flow chart of the general target detection method of the adaptive attention guidance mechanism proposed by the present invention, which can be specifically divided into pyramid prediction convolution (APPK) of cross-down sampling, target region recognition (SORR), and attention guidance mechanism , IoU adaptive loss optimization. The specific process steps are as follows:

[0053] Step 1, using the ResNet-101 feature extractor as the basic architecture of the target detection model, modify its convolution block, that is, perform a cross-downsampling operation on the output of the Mth module of the Nth convolutional layer, based on The input image to be detected generates k feature maps, and the extracted feature maps are input to the network after the Nth convolutional layer for dimensionali...

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 general target detection method of an adaptive attention guidance mechanism, and belongs to the field of computer vision target detection. The method comprises the steps of cross downsampling, target region recognition (SORR), pyramid prediction convolution (APPK) of an attention guidance mechanism and parallel-to-cross ratio (Ioff) adaptive loss optimization. Overall fine texture features in the multi-scale feature map can be reserved through cross downsampling, and loss of spatial information in the image downsampling process is reduced. The SORR module divides thefeature map into n * n grids and obtains an attention score map, so that the target detection efficiency is improved; the APPK module can select a recommendation area to solve the problem of mismatching between the prediction module and the multi-scale target; wherein the IOU adaptive loss function is used for processing the problem that a sample (Hard example) is difficult to process in training.The target detection method is superior to an existing general target detection method in the aspects of accuracy and detection speed.

Description

technical field [0001] The invention belongs to the field of computer vision target detection, in particular to a general target detection method of an adaptive attention guidance mechanism. Background technique [0002] With the wide application of deep learning, computer vision technology has developed rapidly. Computer vision is a science that studies how to let machines replace human eyes to identify, track and detect targets. It is a simulation of biological vision, where the computer replaces the human brain to analyze and process the image data, and ultimately hopes that the computer can observe and understand the world through "vision" like humans. [0003] Target detection is one of the main tasks of computer vision, and the prediction module in its model plays a very important role in the detection of targets. The target detectors at this stage are divided into two categories: one is the secondary detector, which needs to extract the region of interest first, and...

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): G06K9/62G06K9/34G06K9/32G06N3/04G06N3/08
CPCG06N3/08G06V10/25G06V10/267G06V2201/07G06N3/045G06F18/2431
Inventor 陈苏婷张良臣邹戈晨成泽华张闯
Owner NANJING UNIV OF INFORMATION SCI & 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