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

Faster R-CNN-based wheat ear number identification method and system, and medium

An identification method and technology of wheat ears, which are applied in the field of intelligent biology and automatic identification of wheat ears, can solve the problems of inapplicability to the overall study of wheat ears, high overlap of wheat ears, and difficulty in identifying wheat ears phenotype, etc. Effects of Genetic Gains in Yield

Pending Publication Date: 2022-04-01
INST OF CROP SCI CHINESE ACAD OF AGRI SCI
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, due to the complex structure of wheat spikes, the small spacing between plants, the height of overlapping spikes, and the presence of awns in some wheat varieties, it is difficult to accurately identify wheat spike phenotypes. The existing wheat spike recognition methods can only The analysis of the length and width of wheat ears, the projected area and orientation of grains wrapped by glumes can only analyze the parts of wheat ears that are relatively clear and do not overlap, and cannot be applied to the overall study of wheat ears, such as The number of ears of wheat purchased, 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
  • Faster R-CNN-based wheat ear number identification method and system, and medium
  • Faster R-CNN-based wheat ear number identification method and system, and medium
  • Faster R-CNN-based wheat ear number identification method and system, and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] A kind of wheat ear number identification method based on Faster R-CNN in the present embodiment, such as figure 1 shown, including:

[0029] S1 extracts the canopy images of wheat ears of different families, and calibrates the ears of wheat in the images to obtain the labels corresponding to each ear of wheat.

[0030] See image 3 ,Such as image 3 As shown in (a), the present embodiment provides 1840 pieces of high-quality wheat ear canopy RGB images, wherein, 1032 pieces come from 166 natural populations, and the model is trained as the training set of the model, and 808 pieces come from Yangmai 16 Create a DH population with Zhongmai 895 as the parent, use it as a verification set for the model to train the model, and perform subsequent QTL mapping. Such as image 3 As shown in (b), a square frame of 0.5 × 0.5 cm is randomly placed in the non-marginal area of ​​the cell as the object of the photo, which can ensure the consistency of the object area acquired each ...

Embodiment 2

[0057] Based on the same inventive concept, the present embodiment discloses a wheat ear number recognition system based on Faster R-CNN, including:

[0058] The calibration module is used to extract the canopy images of wheat ears of different families, and perform calibration on the ears of wheat in the images to obtain the labels corresponding to each ear of wheat;

[0059] The feature map building module is used to input the image and label of the ear of wheat into the ResNet network model for feature extraction, obtain the feature map of the ear of wheat, and establish a corresponding candidate frame according to the outline of the ear of wheat;

[0060] The model training module is used to train the Faster R-CNN model through the feature map to obtain the optimal wheat ear recognition model;

[0061]The wheat ear recognition module is used to input the wheat ear image to be tested into the wheat ear recognition model to obtain the candidate frame corresponding to each wh...

Embodiment 3

[0063] Based on the same inventive concept, this embodiment discloses a computer-readable storage medium storing one or more programs, one or more programs include instructions, and the instructions, when executed by a computing device, cause the computing device to execute any one of the above-mentioned Item's Faster R-CNN-based Wheat Ear Number Recognition Method.

[0064] Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

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 belongs to the technical field of intelligent biology, and relates to a Faster R-CNN-based wheat ear number identification method and system and a medium, and the method comprises the steps: extracting wheat ear canopy images of different families, carrying out the calibration of wheat ears in the images, and obtaining a label corresponding to each wheat ear; inputting the image and the label of the wheat ear into a ResNet network model for feature extraction to obtain a feature map of the wheat ear, and establishing a corresponding candidate box according to the contour of the wheat ear; the Faster R-CNN model is trained through the feature map, and an optimal wheat ear recognition model is obtained; inputting a to-be-detected wheat ear image into the wheat ear recognition model to obtain candidate frames corresponding to each wheat ear; and counting the number of the candidate frames so as to obtain the number of wheat ears. The molecular marker can be used for carrying out accurate QTL positioning on wheat, can be used for accurately identifying wheat with a high overlapping characteristic of wheat ear number, and is expected to provide a high-throughput analysis tool for wheat molecular breeding seed yield-related phenotype identification.

Description

technical field [0001] The invention relates to a method, system and medium for identifying the number of ears of wheat based on Faster R-CNN, belonging to the field of intelligent biotechnology, and in particular to the technical field of automatic identification of the number of ears of wheat. Background technique [0002] Wheat is an important staple food crop in my country, and its panicle morphological parameters directly reflect the growth status and yield information of wheat (Yang Jinwen et al., 2013), and are important parameters that reflect the quality and yield of wheat. At present, the counting of the number of spikelets and grains in the ear of wheat mainly relies on manual counting, which is not only time-consuming and labor-intensive, but also inefficient. The existing means to solve this problem mainly analyze the plant phenotype by optical imaging, which has obvious advantages over manual counting. Due to the existence of a large number of occlusions, it i...

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): G06T7/00G06V10/44G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
Inventor 肖永贵李磊杨梦娇穆哈默德艾迪尔·哈森韩志国夏先春何中虎
Owner INST OF CROP SCI CHINESE ACAD OF AGRI SCI
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