Sugarcane segmentation and identification method based on improved vision

A recognition method, sugarcane technology, applied in the field of image processing

CN105654099AInactive Publication Date: 2016-06-08崔胡晋
0 Cites 11 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2016-06-08
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

To monitor the growth of sugarcanes or intelligently cut off seed sugarcanes containing sugarcane shoots, a method for automatically completing sugarcane segmentation and identification by identifying the shape and stem node characteristics of sugarcanes based on an improved computer vision technology is put forward. First, sugarcane images are obtained by a digital device; then, hue saturation intensity (HIS) color space conversion is performed on the sugarcane images, color characteristics and threshold segmentation of H and S components are combined, AND operation is performed on reverse images after threshold segmentation to get a composite image, and the composite image is divided into 64 column areas; and finally, the characteristic indexes of H parameters, S parameters, roughness ratio, white spot ratio and the like are extracted, and nodes and inter-node columns are classified and identified through a support vector machine so as to complete identification of the nodes and positions, and the average identification rate is 94.2%.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of image processing, and relates to a method for extracting and recognizing sugarcane features combined with sugarcane images and calculation models. Background technique

[0002] During the growth and post-processing of sugarcane, the growth state and the cutting of sugarcane buds have been done manually for a long time. This method can automatically recognize the image of sugarcane through the identification and processing of computer vision technology. During the treatment, the whole sugarcane needs to be cut into effective sugarcane fragments containing 1 to 3 cane buds. At present, it is mostly done manually. In order to improve efficiency, reduce labor intensity and realize the refinement of sugarcane planting, it is necessary to develop an intelligent cutting device that can identify stem nodes and internodes, and the most critical thing is to identify sugarcane stem nodes. At present, domestic rese...

Examples

Embodiment Construction

[0044] Extract 50 pictures of sugarcane from the collected images and combine them with the training library for testing. After basic image processing, extract 50 images, each with 64 columns and blocks, a total of 3200 samples, and calculate the feature indicators of each sample; through the method of manual identification, classify the category attributes of 3200 samples. In the statistics, it is found that since the block ratio of internodes and stem nodes in an image reaches 10:1, it is necessary to extract training samples with a similar ratio between classes to train the model, so all stem nodes are extracted from the samples. A total of 800 samples and some internode samples were used to establish a classification model. In SVM, set C=20, G=0.01 through crossover experiment.

[0045] The implementation steps of SVM recognition:

[0046] (1) Obtain the stem nodes identified by the SVM, calculate the number Nm of stem node blocks, and take the position distance between ...