Meadow image identification method and device

A technology of image recognition and grass, applied in the field of image processing, can solve the problem of low accuracy of judgment results, achieve the effects of improving accuracy, clear texture recognition, and preventing missed cuts

Inactive Publication Date: 2018-01-09
POSITEC POWER TOOLS (SUZHOU) CO LTD
View PDF5 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Therefore, the technical problem to be solved by the present invention is that the existing grassland recognition method only uses a set of color judgment thresholds and texture judgment thresholds to judge whether the captured image corresponds to grassland, and the accuracy of the judgment result is low.

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
  • Meadow image identification method and device
  • Meadow image identification method and device
  • Meadow image identification method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0081] This embodiment provides a method for image recognition of grass, which is mainly applied to intelligent lawn mowers, such as figure 1 shown, including the following steps:

[0082] S1: Obtain an image of the grass to be identified;

[0083] S2: Divide at least one image block from the image;

[0084] S3: Obtain the color ratio and texture ratio of grass in the image block;

[0085] S4: Determine whether the image block is a grass image by comparing the color ratio with at least two preset color thresholds and the texture ratio with at least two preset texture thresholds.

[0086] The method for image recognition grass provided by this embodiment judges whether an image is a grass image through multiple sets of color thresholds and texture thresholds, that is, as long as an image block satisfies one of the threshold conditions, it can be judged as a grass image, thereby avoiding the grass image Misjudgment as a non-grass image greatly improves the accuracy of grass r...

Embodiment 2

[0122] This embodiment provides a method for image recognition of grass. The difference from the above-mentioned embodiment 1 is that this embodiment provides three sets of judgment thresholds. The first set of judgment thresholds are: the first color threshold, the second texture threshold, and the second The group judgment thresholds are: the second color threshold and the first texture threshold; the third group judgment thresholds are: the third color threshold and the third texture threshold. And the first color threshold is greater than the second color threshold, the second color threshold is greater than the third color threshold, the first texture threshold is greater than the second texture threshold and smaller than the third texture threshold. The above method judges whether the image block is a grass image by comparing the color ratio with at least two preset color thresholds and the texture ratio with at least two preset texture thresholds, including:

[0123] 1)...

Embodiment 3

[0134] Such as Figure 5 As shown, this embodiment provides an image recognition grass device, including:

[0135] An image acquisition unit U1, configured to acquire an image of the grass to be identified;

[0136] A division unit U2, configured to divide at least one image block from the image;

[0137] Judgment element acquisition unit U3, used to acquire the color proportion and texture proportion of grass in the image block;

[0138]The judging unit U4 judges whether the image block is a grassland image by comparing the color ratio with at least two preset color thresholds and the texture ratio with at least two preset texture thresholds.

[0139] The device for image recognition of grass provided by this embodiment judges whether an image is a grass image through multiple sets of color thresholds and texture thresholds, that is, as long as an image block satisfies one of the threshold conditions, it can be judged as a grass image, thereby avoiding the grass image , es...

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 meadow image identification method and device, and relates to the image processing technical field; the method comprises the following steps: obtaining an image of a to-be-identified meadow; splitting at least one image block from the image; obtaining the grass color ratio and texture ratio in the image block; comparing the color ratio with at least two preset color thresholds, and comparing the texture ratio with at least two preset texture thresholds, thus determining whether the image block is a meadow image. The method uses various groups of color thresholds and texture thresholds to determine whether the image is a meadow image or not; compared with a conventional method using only one group of determination threshold for determinations, the method and devicecan hardly determine the meadow image as a non-meadow image, thus providing more accurate determination result.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image recognition method and device for grass. Background technique [0002] The intelligent lawn mower has functions such as automatic walking, collision prevention, wire-out prevention within the range, and automatic return to charge. Reduces labor required for lawn mowing. Existing intelligent lawn mowers generally use real-time image acquisition devices to collect real-time ground images in the forward direction of the lawn mower, and then use image processing technology to judge whether the ground in front is grass, so as to determine whether mowing operations are required. For example: [0003] The invention patent application with the publication number CN104111653A discloses a self-propelled device and its working area judgment method. Its image acquisition device captures the target area to form an image; the main control module divides the image into sever...

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): G06T7/90G06T7/41
Inventor 邵勇达维德·多尔夫
Owner POSITEC POWER TOOLS (SUZHOU) CO LTD
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