A Novel Query Strategy-Based Rank Batch-Mode Active Learning Method for High-Resolution Remote Sensing Image Classification

Abstract

An informative training set is necessary for ensuring the robust performance of the classification of very-high-resolution remote sensing (VHRRS) images, but labeling work is often difficult, expensive, and time-consuming. This makes active learning (AL) an important part of an image analysis framework. AL aims to efficiently build a representative and efficient library of training samples that are most informative for the underlying classification task, thereby minimizing the cost of obtaining labeled data. Based on ranked batch-mode active learning (RBMAL), this paper proposes a novel combined query strategy of spectral information divergence lowest confidence uncertainty sampling (SIDLC), called RBSIDLC. The base classifier of random forest (RF) is initialized by using a small initial training set, and each unlabeled sample is analyzed to obtain the classification uncertainty score. A spectral information divergence (SID) function is then used to calculate the similarity score, and according to the final score, the unlabeled samples are ranked in descending lists. The most “valuable” samples are selected according to ranked lists and then labeled by the analyst/expert (also called the oracle). Finally, these samples are added to the training set, and the RF is retrained for the next iteration. The whole procedure is iteratively implemented until a stopping criterion is met. The results indicate that RBSIDLC achieves high-precision extraction of urban land use information based on VHRRS; the accuracy of extraction for each land-use type is greater than 90%, and the overall accuracy (OA) is greater than 96%. After the SID replaces the Euclidean distance in the RBMAL algorithm, the RBSIDLC method greatly reduces the misclassification rate among different land types. Therefore, the similarity function based on SID performs better than that based on the Euclidean distance. In addition, the OA of RF classification is greater than 90%, suggesting that it is feasible to use RF to estimate the uncertainty score. Compared with the three single query strategies of other AL methods, sample labeling with the SIDLC combined query strategy yields a lower cost and higher quality, thus effectively reducing the misclassification rate of different land use types. For example, compared with the Batch_Based_Entropy (BBE) algorithm, RBSIDLC improves the precision of barren land extraction by 37% and that of vegetation by 14%. The 25 characteristics of different land use types screened by RF cross-validation (RFCV) combined with the permutation method exhibit an excellent separation degree, and the results provide the basis for VHRRS information extraction in urban land use settings based on RBSIDLC.

Coastline detection method of remote sensing image based on local information fuzzy clustering

“…Moreover, the spatial resolution of remote sensing images is low when sea fluctuations are significant [5]. Under this condition, this paper determines whether the pixels in the image are edge pixels by extracting the coastline differential edge features of the remote sensing image [6]. The closer the detected pixel gray value is to the current pixel, the more likely that point will be identified as an edge point [7].…”

“…In formula (6), Eki  is the shoreline edge preservation index of remote sensing image; ^( , ) ( , ) i i P x y is the coastline target pixel of the remote sensing image after noise reduction;…”

Application of convolutional neural network in fusion and classification of multi-source remote sensing data

“…In the process of classifying multi-source remote sensing data, Pastorino et al ( 2021 ) designed a hierarchical probabilistic graphical model, which combines Markov framework and decision tree method, which has certain effectiveness and feasibility (Pastorino et al, 2021 ). In order to improve the classification effect of remote sensing images, Luo et al ( 2021 ) designed a combination strategy based on sorting batch mode, combined with spectral information divergence, and good classification effect can be obtained (Luo et al, 2021 ). Dong R. et al ( 2020 ) proposed a fast depth-aware network that combines multiple advantages to achieve simultaneous extraction of deep and shallow features (Dong R. et al, 2020 ).…”