30 results about "Crop phenology" patented technology

The invention discloses a crop classification method and system. The classification method includes: constructing historical crop marker samples according to the historical multi-temporal mid-segment images and historical crop phenology data; constructing high-precision small-area current crop marker samples according to the current multi-temporal high-resolution images and current crop phenology data; according to ResNet model and PSPNet model to establish the remote sensing network RSNet model; pre-train the remote sensing network RSNet model according to the historical training samples to establish the pre-trained remote sensing network RSNet model; fine-tune the pre-trained remote sensing network RSNet model according to the current training samples to establish a fine-tuned remote sensing network RSNet model; establishing an optimal pre-trained remote sensing network RSNet model and an optimal fine-tuning remote sensing network RSNet model; classifying the crops according to the optimal pre-training remote sensing network RSNet model and the optimal fine-tuning remote sensing network RSNet model. By adopting the classification method and system provided by the present invention, the workload of training sample selection can be reduced, and the classification efficiency can be improved.

The invention belongs to the field of agricultural remote sensing, and specifically relates to a cotton remote sensing monitoring method based on phenological analysis, including: combining regional cotton spectral feature analysis and interference crop phenological analysis to clearly identify key phases of cotton; acquiring remote sensing images of key phenological periods, and performing Preprocessing; multi-scale segmentation of multi-temporal images, hierarchical construction of classifiers, and preliminary extraction of cotton information; secondary segmentation of the preliminary results of cotton information and objects that may be mixed, and construction of classifiers based on cotton spectral features and texture features. Remove the mixed points and supplement the missing cotton information; merge and output the extracted cotton information subcategories. The present invention realizes the automatic extraction of cotton planting information through the phenological analysis of cotton and interfering crops combined with the layered classification method based on remote sensing images, and fully considers the spectral difference and texture characteristics of cotton and other interfering crops, so that the cotton planting information extraction results More accurate and faster, easy to promote and apply.

The invention discloses a remote sensing monitoring method for winter wheat wet-spot damage based on the fusion of satellite-earth multi-source precipitation data, including: collecting and arranging ground rain gauge observation precipitation data sets, satellite inversion precipitation data sets, NDVI data sets, DEM data, crops Phenological information, statistical data of winter wheat planting area and field sampling data of winter wheat planting area, and preprocessing and filtering of NDVI data; use the processed NDVI time series data to extract the spatial information of winter wheat planting area; use geographically weighted regression Klicking method Construct a quantitative model of precipitation information fusion to obtain precipitation data sets; use the precipitation data set and extracted winter wheat planting area, combined with wet water damage indicators, to monitor the area affected by winter wheat wet water damage. The invention utilizes the data to carry out an effective method for large-scale spatial monitoring of crop wetness damage, and has stable technical feasibility.

The invention provides a method and a device for determining the phenological period of crops. The method obtains the target crop phenological curve of the target crop and the reference crop phenological curve corresponding to the target crop phenological curve; according to the reference crop phenological curve, performs waveform adjustment on the target crop phenological curve to obtain the adjusted target crop Phenological curve; determine the time alignment relationship information between the adjusted target crop phenology curve and the reference crop phenology curve; determine the phenological period of the target crop according to the time alignment relationship information. The method utilizes the target crop phenological curve of the target crop and the reference crop phenological curve corresponding to the target crop phenological curve to determine the phenological period of the target crop is more accurate and has more reference value, and avoids subjective evaluation caused by manual evaluation based on experience. It improves the efficiency of determining the phenological stages of target crops.

The invention discloses a non-point source pollution source intensity estimation method based on crop information remote sensing accurate inversion, comprising steps: 1, obtaining continuous high-time resolution remote sensing images of the same type and the same phenological crop; 2, extracting EVI time series data of the remote sensing images , to obtain the phenological curve of the crop; to obtain the fertilization amount of different fertilization types at different fertilization nodes of the crop; 3, the ESTARFM time-spatial fusion of the remote sensing data with high spatial resolution and high temporal resolution, and extract the EVI time series data of the fused remote sensing image ; 4. According to the fused EVI time series data, the planting area of ​​different fertilization nodes of crops is obtained; 5. According to the amount of fertilizer applied and the planting area of ​​different fertilization nodes of crops, the intensity of non-point source pollution sources is estimated. The invention accurately extracts crop types through remote sensing images, determines the accumulation process of fertilization amount along with crop growth through crop phenological characteristics and fertilization information, and provides a more accurate estimation value for the strength of non-point source pollution sources.