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

Improved target detection method based on Faster RCNN algorithm

A target detection and algorithm technology, applied in neural learning methods, calculations, computer components, etc., can solve the problems of reduced positioning accuracy, slow detection speed, and large number of parameters, so as to shorten time, improve detection speed, and improve positioning The effect of accuracy

Pending Publication Date: 2020-04-17
TIANJIN UNIV
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Although the classic Faster RCNN algorithm has a good detection effect, it has two prominent problems: one is that the number of parameters is large and the detection speed is slow; the other is that the classification score of the target is used to reflect the positioning accuracy. The traditional NMS algorithm Boxes with lower scores will be filtered out, resulting in lower positioning accuracy

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
  • Improved target detection method based on Faster RCNN algorithm
  • Improved target detection method based on Faster RCNN algorithm
  • Improved target detection method based on Faster RCNN algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0047] The network framework of the present invention such as figure 1 As shown, it involves DenseNet, RPN, ROI and prediction modules, and the functions of each module are as follows:

[0048] The DenseNet network achieves feature reuse through dense connections, enhances feature propagation, reduces the number of parameters, and improves detection speed. This network consists of a convolutional layer, 3 Dense Blocks (dense connected blocks) and a transition layer. Its structure is as follows figure 2 shown. In Dense Block, the output of each layer is related to the output of the previous layers, and its output function is X n =H n ([X 0, x 1, x 2, x 3 ""X n-1 ]), X n Rep...

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 improved target detection method based on a Faster RCNN algorithm, and the method comprises the following steps: (1) inputting a picture, carrying out the preprocessing of the input picture, and adjusting the size of the input picture; (2) performing feature extraction through a DenseNet network, and then dividing an extracted feature map into an upper branch and a lowerbranch; (3) generating a candidate box for the upper branch obtained in the step (2) through an RPN network, and obtaining a proposal feature map with a fixed size by a lower branch ROI network through a feature map generated by a DenseNet network and the candidate box generated by the upper branch; and (4) performing target classification and positioning through a prediction module.

Description

technical field [0001] The invention relates to the fields of computer vision target detection and image processing, in particular to an improved target detection method based on the FasterRCNN [1] algorithm. Background technique [0002] With the rise of deep learning, object detection technology has developed rapidly. Traditional target detection technologies are mainly divided into two categories: one is the target detection method based on region proposal, such as RCNN series (RCNN, Fast RCNN [3] and Faster RCNN, etc.); the other is single-stage target detection method, such as YOLO , SSD[1] and DSSD etc. The former has high precision but slow speed; the latter has low precision but fast speed. [0003] Object detection technology is a hot direction of computer vision and image processing, it can be used in driverless cars, intelligent video surveillance and many other fields, therefore, the improvement of object detection system is more and more important. There are ...

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): G06K9/32G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V10/25G06V10/40G06V2201/07G06N3/045G06F18/213
Inventor 郭如意金杰陈景明刘凯燕
Owner TIANJIN UNIV
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