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

Target detection algorithm based on wheat image

A target detection algorithm and detection algorithm technology, applied in computing, computer components, neural learning methods, etc., can solve problems such as small targets, few dataset samples, and unbalanced categories, and achieve the advantages of high inference speed, real-time inference, The effect of reducing requirements

Pending Publication Date: 2021-03-12
SOUTHEAST UNIV
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, target detection algorithms still face different problems in specific applications, such as: few data set samples, occlusion problems, small targets, aggregation, category imbalance, etc.

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 algorithm based on wheat image
  • Target detection algorithm based on wheat image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] Embodiment 1: see figure 1 , a kind of target detection algorithm based on wheat image, described detection algorithm comprises the following steps:

[0025] Step 1: The first stage is the training stage of the algorithm,

[0026] Step 2: The second stage is the real-time reasoning stage of the algorithm.

[0027] Such as figure 1 As shown, this algorithm gives the training steps of the training phase:

[0028] Step S11, clustering the anchors of YOLOv5 using k-means. Add the width w and length h of all the boxes in the wheat training set label to the list to define the distance between the two boxes A and B The distance d is the similarity measurement method of the k-means algorithm, because the number of anchors in YOLOv5 is 9, so k=9 is used for clustering. Replace the original anchor of YOLOv5 with the obtained 9 new anchor values. Note: The larger the anchor, the deeper the layer, because the feature map of the deeper layer is responsible for detecting large...

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 a target detection algorithm based on a wheat image, and the detection algorithm comprises the following steps: 1, a first stage is a training stage of the algorithm, and 2, asecond stage is a real-time reasoning stage of the algorithm. The YOLOv5 algorithm after wheat data set optimization has high precision and high reasoning speed, real-time reasoning can be achieved,offline training of the YOLOv5 algorithm can also be completed on a single GPU (such as GTX1080ti or RTX2080Ti), and the requirement for hardware is greatly reduced.

Description

technical field [0001] The invention relates to a detection algorithm, in particular to a target detection algorithm based on wheat images, and belongs to the technical field of artificial intelligence computer vision. Background technique [0002] Target detection is a basic direction in the field of artificial intelligence computer vision, and the usual target detection belongs to supervised learning. Given a data set and labels, the category and location of the target contained in the given data set are trained through preprocessing, feature extraction, feature fusion, and detection, respectively, so as to predict the target contained in similar pictures outside the training set Purpose of Category and Location. [0003] The target detection algorithm mainly has three components: backbone, neck and head. Among them, backbone is the part of feature extraction. Common backbones include VGG, resnet, darknet, etc.; neck is the feature fusion part. Since the advent of featur...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/20G06V2201/07G06N3/045G06F18/23213
Inventor 范淑卷孙长银陆科林徐乐玏
Owner SOUTHEAST 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