Improved target object rapid detection method based on SSD network

A detection method and technology for target objects, which are applied in biological neural network models, neural learning methods, instruments, etc., can solve the problem of undiscovered patent documents, etc., and achieve the effects of high speed, improved network computing efficiency, and reduced network parameters.

Inactive Publication Date: 2019-11-22
TIANJIN UNIV
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Through the search of published patent documents, no published patent documents identical to this patent application have been found

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 object rapid detection method based on SSD network
  • Improved target object rapid detection method based on SSD network
  • Improved target object rapid detection method based on SSD network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be further described in detail below through the specific examples, the following examples are only descriptive, not restrictive, and cannot limit the protection scope of the present invention with this.

[0031] A method for fast detection of an improved target object based on SSD network, characterized in that: the steps of the detection method are:

[0032] 1) Improved SSD network construction: The SSD network is composed of a VGG feature extraction network and a detection and positioning network. The construction of the improved network includes two steps:

[0033] a) Modify the standard convolution kernel: The VGG feature extraction network in the SSD network is to perform convolution operations on the input feature map through the 3×3 standard convolution kernel to obtain a new output, while the VGG feature extraction network in the improved SSD network The network uses a decomposed convolution kernel, which decomposes the standard convo...

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 an improved target object rapid detection method based on an SSD network. The improved target object rapid detection method is characterized by comprising the following steps:1) creation of an improved SSD network; (2) image data set acquisition, (3) network training and testing and (4) target detection. The method is scientific and reasonable in design, is suitable for the quick real-time detection of a target object, can reduce the network parameters, improves the network calculation efficiency, and is high in detection precision and speed compared with a standard SSD network.

Description

technical field [0001] The invention belongs to the field of image processing of computer vision, relates to a target object detection method, in particular to an improved fast target object detection method based on SSD (Single Shot MultiBox Detector, SSD) network. Background technique [0002] The development of target detection algorithms is divided into two stages, one is a solution based on traditional features, and the other is an algorithm based on deep learning. Before 2013, the optimization detection method based on traditional feature extraction was the mainstream in the industry. Since the birth of deep learning technology, it has shown strong vitality in the field of image detection. Convolutional neural network is a feed-forward neural network consisting of one or more convolutional layers and a fully connected layer at the top, which has excellent performance in the field of large-scale image processing. Compared with other deep feed-forward neural network st...

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): G06K9/32G06N3/04G06N3/08
CPCG06N3/08G06V10/255G06V2201/07G06N3/045
Inventor 史再峰叶鹏曹清洁罗韬唐锐
Owner TIANJIN UNIV
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