Target detection method based on DenseNet and multi-scale feature fusion

A multi-scale feature and target detection technology, which is applied in the field of computer vision, can solve the problems that the detection accuracy and detection speed cannot be guaranteed at the same time, and achieve the effect of improving detection accuracy, reducing model size, and improving representation ability

Active Publication Date: 2019-08-02
JIANGNAN UNIV
View PDF0 Cites 52 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem that the detection accuracy and detection speed cannot be guaranteed at the same time for small target detection in the prior art, the present invention provid...

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
  • Target detection method based on DenseNet and multi-scale feature fusion
  • Target detection method based on DenseNet and multi-scale feature fusion
  • Target detection method based on DenseNet and multi-scale feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Such as Figure 1~Figure 6 As shown, the present invention is based on the target detection method of DenseNet and multi-scale feature fusion, which includes the following contents.

[0036] S1: Build a feature extraction network model; use the 121-layer dense convolutional neural network DenseNet as the basic network, add multiple convolutional layers, perform feature extraction, and extract multi-scale feature maps;

[0037] The feature extraction network model is composed of 4 Dense blocks and 3 transition layers alternately spliced; then three sets of convolutional layers Conv1~Conv3 are connected in turn, and each set of convolutional layers includes a convolutional layer with a convolution kernel of 1×1 And the convolutional layer with a convolution kernel of 3×3, the size of these convolutional layers is gradually reduced; it also includes a feature fusion module, which fuses the low-level detail feature map with the high-level semantic feature map, introduces co...

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 provides a target detection method based on DenseNet and multi-scale feature fusion. The target detection method comprises the following steps: S1, constructing a feature extraction network model; S2, training the feature extraction network model, and obtaining an optimal target detection model through multiple times of iterative training; S3, inputting the to-be-detected image datainto the optimal target detection model for detection, and marking the position and the category of each object on the to-be-detected image by using a rectangular frame. According to the feature extraction network model, a DenseNet network serves as a basic network, the network hierarchy is deepened, the feature quality is improved, meanwhile, a feature fusion module is used, context information is introduced, six feature maps used for final prediction are obtained, and the feature extraction network model has rich semantic information and high resolution. According to the method, the model scale can be reduced on the basis of ensuring the detection speed, and the detection precision of a small target is improved.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a target detection method based on DenseNet and multi-scale feature fusion. Background technique [0002] Object detection is a very important research direction in the field of computer vision. Target detection is to accurately identify and locate objects in images and videos, so that the computer can understand the surrounding environment and achieve good human-computer interaction. In recent years, object detection has been widely used in autonomous driving, environmental monitoring, traffic security and other fields. [0003] In practical applications, there are many scenes that need to identify small targets in the image to be detected. However, because the resolution and information of the small target object in the image to be detected is limited, so far, the detection of the small target is still a difficult point in the prior art. Currently, object detection m...

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): G06K9/62G06N3/04
CPCG06V2201/07G06N3/045G06F18/254G06F18/253G06F18/214Y02T10/40
Inventor 曹毅翟明浩张威刘晨盛永健黄子龙李巍张宏越易灵杰
Owner JIANGNAN 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