A recognition and counting method of wolfberry based on pointnet++ network

A counting method and wolfberry technology, applied in the field of image recognition, can solve problems such as the difficulty of accurate identification by two-dimensional image recognition methods, and achieve the effects of improving the detection ability of wolfberry, improving the accuracy rate, and accurately predicting

Active Publication Date: 2021-10-26
HEFEI INSTITUTES OF PHYSICAL SCIENCE - CHINESE ACAD OF SCI
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the defect that the two-dimensional image recognition method is difficult to accurately identify the two-dimensional image recognition method in order to solve the occlusion overlap before picking the wolfberry fruit in the prior art, and to provide a method for recognizing and counting wolfberry based on the PointNet++ network to solve the above problems

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
  • A recognition and counting method of wolfberry based on pointnet++ network
  • A recognition and counting method of wolfberry based on pointnet++ network
  • A recognition and counting method of wolfberry based on pointnet++ network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0077] In order to have a further understanding and understanding of the structural features of the present invention and the achieved effects, the preferred embodiments and accompanying drawings will be used for a detailed description, as follows:

[0078] like figure 1 Shown, a kind of Lycium barbarum identification and counting method based on PointNet++ network of the present invention, comprises the following steps:

[0079] The first step is the collection and preprocessing of PointNet++ network training samples.

[0080] Obtain 18 pictures of each wolfberry tree and the corresponding context information. The context information includes time, space, temperature and phenological period information. According to the existing method, 18 pictures are used to construct a 3D model to obtain a 3D point cloud, and the context information is used as a training data.

[0081] The second step is to obtain the PointNet++ model based on PointNet++ network fusion context informatio...

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 wolfberry recognition and counting method based on the PointNet++ network. Compared with the prior art, the defect that two-dimensional image recognition methods are difficult to accurately identify the wolfberry fruit due to occlusion and overlap before picking is solved. The invention comprises the following steps: collection and preprocessing of PointNet++ network training samples; obtaining PointNet++ model based on PointNet++ network fusion context information; acquisition and preprocessing of point cloud data to be identified; identification and counting of wolfberry quantity. The invention integrates the PointNet++ network based on the context information and the optimal threshold watershed segmentation algorithm based on the distance transformation, and realizes accurate segmentation and counting of wolfberries.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a PointNet++ network-based wolfberry recognition and counting method. Background technique [0002] During the planting process of wolfberry, by accurately predicting the yield of wolfberry, it is possible to carry out targeted rectification of low-yielding areas, adjust factors such as soil, variety, or moisture content, and rationally arrange the manpower, material resources, and storage resources required for harvesting. . [0003] At present, when performing fruit target recognition and estimating yield, most of them use two-dimensional images as data input for yield measurement. However, in practical applications, due to the small size of goji berries and the occlusion and overlapping problems of most goji berry fruits before picking, it is difficult to guarantee the accuracy of yield measurement using the deep learning method based on two-dimensional images with ...

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 Patents(China)
IPC IPC(8): G06T7/136G06K9/62
CPCG06T7/136G06T2207/30242G06T2207/30188G06T2207/20152G06T2207/10028G06F18/23213
Inventor 贾秀芳王儒敬李伟谢成军孙丙宇黄河王雪李娇娥徐玲玲
Owner HEFEI INSTITUTES OF PHYSICAL SCIENCE - CHINESE ACAD OF SCI
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