Abstract
Tea is an important economic plant, which is widely cultivated in many countries, particularly in China. Accurately mapping tea plantations is crucial in the operations, management, and supervision of the growth and development of the tea industry. We propose an object-based convolutional neural network (CNN) to extract tea plantations from very high resolution remote sensing images. Image segmentation was performed to obtain image objects, while a fine-tuned CNN model was used to extract deep image features. We conducted feature selection based on the Gini index to reduce the dimensionality of deep features, and the selected features were then used for classifying tea objects via a random forest. The proposed method was first applied to Google Earth images and then transferred to GF-2 satellite images. We compared the proposed classification with existing methods: Object-based classification using random forest, Mask R-CNN, and object-based CNN without fine-tuning. The results show the proposed method achieved a higher classification accuracy than other methods and produced smaller over- and under-classification geometric errors than Mask R-CNN in terms of shape integrity and boundary consistency. The proposed approach, trained using Google Earth images, achieved comparable results when transferring to the classification of tea objects from GF-2 images. We conclude that the proposed method is effective for mapping tea plantations using very high-resolution remote sensing images even with limited training samples and has huge potential for mapping tea plantations in large areas.
Highlights
Tea is an important economic crop and has been widely planted in the southern part of China [1]
This study provided an object-based convolutional neural network (CNN) method for extracting tea plantations using Very high resolution (VHR) remote sensing images
We used a fine-tuned CNN model in object-based image analysis setting, referred to as object-based CNN, to automatically extract high-level image features regarding tea image objects that were obtained by image segmentation
Summary
Tea is an important economic crop and has been widely planted in the southern part of China [1]. China is the world’s largest tea producer, and the cultivation and production of tea have played an important role in China’s agricultural economy and agricultural development [3]. Remote sensing images have been widely used to extract crop information [5]. Remote sensing images have been utilized in the detection and analysis of tea plantations [6,7,8,9]. Medium- and low-resolution images (e.g., Landsat, MODIS, and Sentinel-2) have been the most commonly used remote sensing satellites for the extraction of the spatial distribution of tea plantations [10,11]. Ma et al [12] used a time series of MODIS and Landsat data to derive the planting areas of tea, based on a number of selected vegetation indices and phenological features
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
