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

Small target detection and recognition method for enhancing feature learning

A technology of small target detection and recognition methods, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve the problems of low network efficiency, slow detection speed, low detection accuracy of small target detection and recognition tasks, etc. Detection speed, reduction of burden, and improvement of the effect of low detection accuracy

Active Publication Date: 2019-11-26
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF7 Cites 50 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005]Aiming at the problems of the above research, the purpose of the present invention is to provide a small target detection and recognition method with enhanced feature learning to solve the small target detection and recognition tasks in the prior art The problem of low detection accuracy and low network efficiency (that is, slow detection speed)

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
  • Small target detection and recognition method for enhancing feature learning
  • Small target detection and recognition method for enhancing feature learning
  • Small target detection and recognition method for enhancing feature learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0084] Extract the small target sample image data from the COCO data set as a test set, and input the small target images in the test set into SSD, DSSD and the method of the present invention for detection respectively, and obtain Figure 5 and Figure 6 The results shown, where, Figure 6 The detection results of three small target images in SSD, DSSD and the method described in the present invention are shown. No matter whether the present invention is in the detection of small targets, medium targets and large targets, the detection accuracy of the prior art is higher, and it can be seen from the figure that the SSD network and the DSSD network have a large number of problems in the detection of small targets. Missing detection problem, and the model structure proposed in this paper has been better improved.

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 small target detection and recognition method for enhanced feature learning, belongs to the field of image processing, pattern recognition and computer vision, and solves theproblems of low small target detection and recognition task detection precision and low network efficiency in the prior art. The method comprises: sequentially constructing a basic network module, afeature extraction module, a candidate box generation module and a prediction output module to serve as a small target detection and identification network; preprocessing the extracted small target sample image data based on the extracted small target sample image data; inputting the preprocessed small target sample image data into the small target detection and recognition network with initialized parameters for training to obtain a trained small target detection and recognition network; and inputting a to-be-predicted small target image into the trained small target detection and recognitionnetwork, and outputting the prediction box position and category information of the small target end to end through forward propagation. The method is used for small target detection and recognition.

Description

technical field [0001] A small target detection and recognition method with enhanced feature learning is used for small target detection and recognition, and belongs to the fields of image processing, pattern recognition and computer vision. Background technique [0002] So far, the task of object detection and recognition is still one of the hot research directions in the field of computer vision. Due to its wide range of engineering applications, this task has been rapidly developed and innovated in the field of academic research. In fact, target detection and recognition tasks also play an important role in life. For example, face recognition based on target detection and recognition tasks is used in security inspection applications in important public transportation places such as airports and railway stations; The license plate detection and recognition under the task also has important practical significance for regulating traffic and testing driving safety. [0003] ...

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): G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V10/40G06V2201/07G06N3/045G06F18/24143G06F18/214
Inventor 程建林莉李灿周晓晔李月男
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
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