[0075] Example 1:
[0076] The following is an example of sugarcane distribution identification in Zhanjiang City, Guangdong Province, China:
[0077] 1. Since Zhanjiang City is located in southern China, with sufficient temperature and rainfall for many years, referring to expert knowledge and selecting the appropriate time interval according to the phenological information of local sugarcane in Zhanjiang, it is divided into 5 phenological stages. Please refer to Table 1.
[0078] Table 1 Phenological stages of sugarcane in Zhanjiang City
[0079] Seedling stage
[0080] 2. Please refer to 5 and use the following formula to synthesize the 5 maximum NDVI images corresponding to the 5 phenological stages:
[0081] NDVI S1 =max(NDVI 1.1 ,...,NDVI 3.31 )
[0082] NDVI S2 =max(NDVI 4.1 ,...,NDVI 6.25 )
[0083] NDVI S3 =max(NDVI 6.26 ,...,NDVI 8.10 )
[0084] NDVI S4 =max(NDVI 8.11 ,...,NDVI 11.30 )
[0085] NDVI S5 =max(NDVI 12.1 ,...,NDVI 12.31 )
[0086] Among them, NDVI S1 ~NDVI Sn For the 5 maximum NDVI images corresponding to each phenological stage, NDVI 1.1 And NDVI 12.31 Etc. are all Sentinel-2 sequence data corresponding to the date in the lower right corner.
[0087] 3. Please refer to the comparison Image 6 with Figure 7 , Reduce the dimensions of the 5 maximum NDVI images into a one-dimensional image, extract the characteristics of sugarcane, remove the interference of other crops (mainly rice) on the recognition of sugarcane due to the fragmentation of the land, and also eliminate the recognition caused by large cloudiness error.
[0088] 4. See Figure 8 , The above-mentioned one-dimensional image is segmented by the watershed controlled by the label.
[0089] Compared with the prior art, the sugarcane distribution recognition method based on optical remote sensing data of the present invention, because the phenological information of different sugarcanes is different, by matching the phenological stage with the NDVI maximum image, it reflects the sugarcane at different phenological stages Production conditions, and only the target sugarcane will show significantly different maximum NDVI images at different phenological stages, while the NDVI images of other crops have little change. And by reducing the dimensions of several NDVI maximum images into one-dimensional images, which is equivalent to image subtraction, detecting the changes of different NDVI maximum images in the same scene, extracting the characteristics of the target sugarcane, and then passing the subsequent The gradient operator and the watershed segmentation algorithm identify the target sugarcane, thereby solving the problem of low recognition accuracy caused by land fragmentation and cloud interference, accurately reflecting the spatial distribution of the target sugarcane, and benefiting agricultural management and planning.
[0090] The invention also provides a sugarcane extraction device based on optical remote sensing data, including
[0091] The data acquisition module is used to acquire the phenological information of the sugarcane and the historical Sentinel-2 sequence data of the sugarcane, and calculate the NDVI for each scene image;
[0092] Image synthesis module: used to divide phenological stages according to phenological information, and synthesize several NDVI maximum images corresponding to each phenological stage;
[0093] Image dimensionality reduction module, used to reduce the dimensionality of several NDVI maximum image cubes into one-dimensional images;
[0094] An image conversion module for calculating the gradient of the one-dimensional image using a gradient operator to obtain an edge amplitude image;
[0095] The image segmentation module is used to extract the sugarcane distribution by using the watershed segmentation algorithm for the edge amplitude image.
[0096] The present invention also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the sugarcane distribution recognition method based on optical remote sensing data as described in any one of the above are realized.
[0097] The present invention may be in the form of a computer program product implemented on one or more storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing program codes. Computer-readable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be realized by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, Magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices.
[0098] The present invention also provides a computer device, including a storage, a processor, and a computer program stored in the storage and executable by the processor. When the processor executes the computer program, any one of the above The steps of the method for identifying the distribution of sugarcane based on optical remote sensing data.