This paper proposes a parallel algorithm exploiting heterogeneous computing and edge computing for anomaly detection (AD) in remotely sensed multispectral images. These images present high spatial resolution and are captured onboard unmanned aerial vehicles. AD is applied to identify patterns within an image that do not conform to the expected behavior. In this paper, the anomalies correspond to human-made constructions that trigger alarms related to the integrity of fluvial ecosystems. An algorithm based on extracting spatial information by using extinction profiles (EPs) and detecting anomalies by using the Reed–Xiaoli (RX) technique is proposed. The parallel algorithm presented in this paper is designed to be executed on multi-node heterogeneous computing platforms that include nodes with multi-core central processing units (CPUs) and graphics processing units (GPUs) and on a mobile embedded system consisting of a multi-core CPU and a GPU. The experiments are carried out on nodes of the FinisTerrae III supercomputer and, with the objective of analyzing its efficiency under different energy consumption scenarios, on a Jetson AGX Orin.

Segmentation is a key issue in the processing of multidimensional images such as those in the field of remote sensing. Most of the segmentation algorithms developed for multidimensional images begin by reducing the dimensionality of the images, thus loosing information that could be relevant in the segmentation process. Evolutionary cellular automata segmentation (ECAS-II) is an evolutionary approach that provides cellular automata-based segmenters considering all the spectral information contained in a hyperspectral image without applying any technique for dimensionality reduction. This paper presents an efficient graphics processor unit implementation of the type of segmenters produced by ECAS-II for land cover hyperspectral images. The method is evaluated over remote sensing hyperspectral images, introducing it on a spectral-spatial classification scheme based on extreme learning machines. Experiments have shown that the proposed approach achieves better accuracy results for land cover purposes than other spectral-spatial classification techniques based on segmentation.

The monitoring of semi-natural ecosystems has become increasingly critical due to the rising impact of ecological disturbances, including natural disasters and unauthorized human-made constructions. Anomaly detection (AD) in multispectral imagery serves as a fundamental tool in this context. Deep learning-based techniques are particularly effective at capturing the intricate spectral and spatial patterns of anomalies. This paper proposes a new AD technique called ACNN, designed to enhance AD performance in multispectral images of high spatial resolution for the detection of human-made constructions. The model integrates attention mechanisms to prioritize informative features while suppressing irrelevant background information, thereby improving sensitivity to subtle and rare anomalies. Experimental results on multispectral datasets from semi-natural ecosystems show that the proposed approach outperforms existing deep learning (DL) techniques in terms of detection accuracy. These findings highlight the potential of attention-based models as a robust framework for environmental monitoring and AD in complex remote sensing scenarios.