Exploring the potential of deep learning and other data mining methods in traditional remote sensing problems
We mainly target on two major problems: one is land cover mapping; the other one is detection of objects (oil palm tree in our most recent project) in high-resolution remote sensing images.
For the land cover mapping problem, we demonstrate early efforts to apply deep learning-based classification methods to large-scale land-cover mapping. Based on the Stacked Autoencoder (SAE), one of the deep learning models, we built a classification framework for large-scale remote-sensing image processing. Results show that the SAE classifier trained with an entire set of African training samples achieves an overall classification accuracy of 78.99%, which is higher than the accuracies achieved by the other three classifiers (76.03%, 77.74%, and 77.86% of RF, SVM, and ANN, respectively). We also demonstrated the advantages of SAE in prediction time and land-cover mapping results in this study [IJRS16]. We also propose a deep learning based framework for oil palm tree detection and counting using high-resolution remote sensing images for Malaysia. We use a number of manually interpreted samples to train and optimize the convolutional neural network (CNN), and predict labels for all the samples in an image dataset collected through the sliding window technique. Then, we merge the predicted palm coordinates corresponding to the same palm tree into one palm coordinate and obtain the final palm tree detection results. Based on our proposed method, more than 96% of the oil palm trees in our study area can be detected correctly when compared with the manually interpreted ground truth, and this is higher than the accuracies of the other three tree detection methods used in this study [RS17].
Key Publications for Applying Data Mining Methods in Remote Sensing Applications
[RS17] Weijia Li, Haohuan Fu*, Le Yu, and Arthur Cracknell, “Deep learning based oil palm tree detection and counting for high-resolution remote sensing images”, Remote Sensing, 9(1):22, January 2017.
[IJRS16] Weijia Li, Haohuan Fu*, Le Yu, et al., “Stacked Autoencoder-based deep learning for remote-sensing image classification: a case study of African land-cover mapping”, International Journal of Remote Sensing, 2016, 37(23): 5632-5646.