An Overview of Technological Revolution in Satellite Image Analysis

Abstract

The satellite image based applications are highly utilized nowadays from simple purposes like vehicle navigation to complex surveillance and virtual environment modeling projects. On increased population rate, the depletion of natural resources is highly unavoidable and it leads to increased threats on natural hazards. In order to protect and overcome the physical losses on devastation of properties, the risk mapping models such as weather forecasts, drought modeling and other hazard assessment models are in need. Though many intelligent risk mapping models do exist, the high level of intelligence needed to predict the real time events is still unresolved. And it leads to increased research efforts on designing intelligent assessment models using more advanced machine learning (ML) schemes for better satellite image interpretation. This paper focuses on bringing a clear understanding on satellite image interpretation methods right from the traditional statistical models to the more recent ML methods through stating the gradual revolution in satellite image analysis.

Applications and Challenges of Artificial Intelligence in Space Missions

“…Unfortunately, most traditional algorithms are plagued with a lack of logical reasoning. With ML techniques vibrant progress has been made in incorporating human-level reasoning into these traditional models [157]. Despite the merits of ML methods, supervised ML techniques suffer from excessive computational complexity due to demanding training processes and insufficient ground truth data for labeling.…”

“…Parallel processing of data could also be used to improve the issues with the speed of computation through higher-level Graphical Processing Unit (GPU) architectures. However, the development of this method is still in progress [157]. Table VI shows a few statistical models utilized in satellite image analysis.…”

“…However, using more advanced intelligence schemes like DNN in satellite image analysis could improve the level of reasoning with a reduction in training complexities [159]. Complexities associated with the training of deep networks with a vast number of hidden layers can be resolved to a greater extent by employing a greedy learning-based algorithm [157]. Greedy algorithm or search is an efficient tool that is usually employed in optimization problems, especially when dealing with large sets of data [160].…”

“…Given the merits of ML techniques in deriving prediction models, the hybridization of different ML methods as shown in Table VII and the integration of statistical and ML methods could acquire more efficient results. In [157], Giorgio Giacinto et al proposed an approach with a combination of neural and statistical algorithms in a simple design phase to disclose that every algorithm is significant in solving a particular issue, and no single algorithm is proved to be perfect. Castellana et al [168] performed the combination of both supervised and unsupervised modes of change detection and on a pixel-based method to achieve better classification of remote sensing images.…”

“…Castellana et al [168] performed the combination of both supervised and unsupervised modes of change detection and on a pixel-based method to achieve better classification of remote sensing images. In [169], Pabitra Mitra et al combined an active learning method with SVM and advanced an active SVM with reduced labeled data for classification [157].…”