CNN-LandCoverNet: An Effective Framework of Land Cover Classification Using Hybrid Metaheuristic-Aided Ensemble-Based Convolutional Neural Network

Abstract

Land cover (LC) categorization is considered a necessary task of intelligent interpretation technology for remote sensing imagery that is intended to categorize every pixel to perform the predefined LC classification. Land Use and Land Cover (LULC) information has the ability to provide various insights in order to overcome environmental and socioeconomic impacts such as disaster risk, climate change, poverty, and food insecurity. Therefore, image categorization tasks are involved in conventional works, where the classical visual interpretation techniques completely depend upon professional knowledge as well as a professional’s classification experience, which is more susceptible to subjective awareness, inefficient, and time consuming. By overcoming this issue, the latest deep-structured approach is suggested to perform the LC image classification. Initially, the land images are gathered. Further, the collected images are employed for patch splitting, where the images are split into multiple patches. After splitting, the patches are fed to the Ensemble-based Convolutional Neural Network (ECNN), which is constructed with a Fully Convolutional Network (FCN), U-Net, DeepLabv3, and Mask Region-based Convolutional Neural Network (Mask R-CNN) for performing segmentation. Here, the hyperparameters are optimally tuned with the Hybrid Billiards-inspired Water Wave Algorithm (HB-WWA) by integrating the Billiards-inspired Optimization Algorithm (BOA) and Water Wave Algorithm (WWA). Finally, the classification is carried out with a fuzzy classifier. Thus, the performance is validated and measured through diverse metrics. Consequently, the developed work has demonstrated enhanced classification accuracy when tested on other existing algorithms.