Abstract
Mapping the crop type can provide a basis for extracting information on crop planting structure, and area and yield estimation. Obtaining large-scale crop-type mapping by field investigation is inefficient and expensive. Traditional classification methods have low classification accuracy due to the fragmentation and heterogeneity of crop planting. However, the deep learning algorithm has a strong feature extraction ability and can effectively identify and classify crop types. This study uses GF-1 high-resolution remote sensing images as the data source for the Shuangcheng district, Harbin city, Heilongjiang Province, China. Two spectral feature data sets are constructed through field sampling and employed for training and verification, combined with basic survey data of grain production functional areas at the plot scale. Traditional machine learning algorithms, such as random forest (RF) and support vector machine (SVM), and a popular deep learning algorithm, convolution neural network have been utilized. The results show that the fusion of multi-spectral information and vegetation index features helps improve classification accuracy. The deep learning algorithm is superior to the machine learning algorithm in both classification accuracy and classification effect. The highest classification accuracy of Crop Segmentation Network (CSNet) based on fine-tuning Resnet-50 is 91.2%, kappa coefficient is 0.882, and mean intersection over union is 0.834. The classification accuracy is 13.3% and 9.5% points higher than RF and SVM, respectively, and the best classification performance is obtained. The classification accuracy and execution efficiency of the model are suitable for a wide range of crop classification tasks and exhibit good transferability.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 8
Claim · model-written summary
The highest classification accuracy of CSNet based on fine-tuned Resnet-50 was 91.2%.
Verbatim
e1“The highest classification accuracy of Crop Segmentation Network (CSNet) based on fine-tuning Resnet-50 is 91.2%”
Claim · model-written summary
The kappa coefficient of CSNet was 0.882.
Verbatim
e2“kappa coefficient is 0.882”
Claim · model-written summary
The mean intersection over union of CSNet was 0.834.
Verbatim
e3“mean intersection over union is 0.834”
Claim · model-written summary
The classification accuracy of CSNet was 13.3% higher than that of RF.
Verbatim
e4“The classification accuracy is 13.3% and 9.5% points higher than RF and SVM, respectively”
Claim · model-written summary
The classification accuracy of CSNet was 9.5% higher than that of SVM.
Verbatim
e4“The classification accuracy is 13.3% and 9.5% points higher than RF and SVM, respectively”
Claim · model-written summary
Fusing multi-spectral information with vegetation index features helps improve classification accuracy.
- Treatment
- fusion of multi-spectral information and vegetation index featurese5
- Outcome
- classification accuracye5
- Direction
- improvee5
Not reportedValue
Verbatim
e5“The results show that the fusion of multi-spectral information and vegetation index features helps improve classification accuracy”
Claim · model-written summary
The deep learning algorithm is superior to the machine learning algorithm in classification accuracy and classification effect.
Verbatim
e6“The deep learning algorithm is superior to the machine learning algorithm in both classification accuracy and classification effect”
Claim · model-written summary
The CSNet model exhibits good transferability.
- Outcome
- good transferabilitye7
Not reportedComparator
Verbatim
e7“exhibit good transferability”