Target fruit instance segmentation method and system

A fruit and target technology, applied in the field of computer vision, can solve problems such as insufficient accuracy and inability to achieve real-time operations, and achieve the effect of reducing missed detection and false detection rates, improving recognition and segmentation speed, and reducing complexity.

Pending Publication Date: 2022-02-25
SHANDONG NORMAL UNIV
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods are often not accurate enough to meet the requirements of real-time operations in complex orchard environments.

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 fruit instance segmentation method and system
  • Target fruit instance segmentation method and system
  • Target fruit instance segmentation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Present embodiment 1 provides a kind of target fruit instance segmentation system, and this system comprises:

[0043] Obtain module, be used for obtaining orchard environment image;

[0044] The segmentation module is used to process the image of the orchard environment by using a pre-trained segmentation model to obtain the recognition and segmentation results of the target fruit; wherein, the pre-trained segmentation model is obtained by training a training set, and the training set includes multiple An image of the orchard environment and labels for the target fruit in the image;

[0045] Among them, when the pre-trained segmentation model is used to process the orchard environment image, the extracted features are subjected to semantic category recognition and mask segmentation to obtain the target fruit instance segmentation result.

[0046] In the present embodiment 1, utilize above-mentioned target fruit instance segmentation system to realize target fruit inst...

Embodiment 2

[0058] Present embodiment 2 provides a kind of target fruit instance segmentation system, and this system comprises:

[0059] Obtain module, be used for obtaining orchard environment image;

[0060] The segmentation module is used to process the image of the orchard environment by using a pre-trained segmentation model to obtain the recognition and segmentation results of the target fruit; wherein, the pre-trained segmentation model is obtained by training a training set, and the training set includes multiple An image of the orchard environment and labels for the target fruit in the image;

[0061] Among them, when the pre-trained segmentation model is used to process the orchard environment image, the extracted features are subjected to semantic category recognition and mask segmentation to obtain the target fruit instance segmentation result.

[0062] In the present embodiment 2, utilize above-mentioned target fruit instance segmentation system to realize target fruit inst...

Embodiment 3

[0098] In the present embodiment 3, a kind of fruit picking robot is provided, and this fruit picking robot comprises target fruit instance segmentation system, and this system can realize target fruit instance segmentation method, comprises:

[0099] Utilize the acquisition module to obtain the orchard environment image;

[0100] Using the segmentation module, based on the pre-trained segmentation model, the image of the orchard environment is processed to obtain the recognition and segmentation results of the target fruit; wherein, the pre-trained segmentation model is obtained by training a training set, and the training set includes a plurality of orchards The environmental image and the label of the target fruit in the marked image; wherein, when using the pre-trained segmentation model to process the orchard environmental image, the extracted features are subjected to semantic category recognition and mask segmentation to obtain the target fruit instance segmentation resu...

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 fruit instance segmentation method and system, which belong to the technical field of computer vision. The method comprises steps of for an acquired orchard environment image, processing the orchard environment image by using a pre-trained segmentation model to obtain an identification segmentation result, wherein the pre-trained segmentation model is obtained by training a training set, and the training set comprises a plurality of orchard environment images and labels for labeling target fruits in the images, and when the orchard environment image is processed by using a pre-trained segmentation model, conducting semantic category recognition and mask segmentation on the extracted features to obtain a target fruit instance segmentation result. According to the method, the dependence of a model on an anchor frame is avoided, the complexity of the model is reduced, and mask annotation is independently used for instance segmentation tasks in an end-to-end mode to optimize a network; the method does not depend on a model detection frame, directly obtains the pixel segmentation result of the instance, improves the target fruit recognition and segmentation speed, is high in robustness and real-time performance, and reduces the missing detection rate and the false detection rate.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a method and system for segmenting target fruit instances based on an optimized SOLO-A network. Background technique [0002] For picking apples, tomatoes, strawberries and other fruits and vegetables or spraying medicines, using intelligent robots for machine picking or spraying medicines instead of traditional manual methods can greatly improve work efficiency. The rapid and accurate identification and positioning of the target directly affects the reliability and real-time performance of the picking robot for picking the target fruit. Accurate identification and positioning of target fruit is the key to the vision system. However, for complex orchard environments, there will be problems such as shading of branches and leaves, overlapping fruits, and rainy weather, which will make it more difficult for robots to identify fruits. [0003] In recent years, many excellen...

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): G06T7/11G06T7/13G06K9/62G06V10/774G06V10/764G06V10/44G06V10/26G06V10/80
CPCG06T7/11G06T7/13G06T2207/10024G06T2207/20081G06T2207/20221G06T2207/30188G06F18/241G06F18/253G06F18/214
Inventor 魏金梦贾伟宽张为可赵瑞娜丁艳辉
Owner SHANDONG NORMAL 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