Search

Tracking of ships' motion and monitoring of maritime traffic can be performed with the use of distributed Kalman Filtering. However, some of the local Kalman Filters which constitute distributed estimation schemes may be based on inaccurate models of the vessel's dynamics or kinematics and in such a case the aggregate state estimate provided by the distributed filter is unreliable. To treat this problem the paper proposes a statistical method of optimized performance for the validation of Fuzzy Kalman Filters used in ship tracking. This statistical validation test is capable of detecting the faulty local filter within the distributed estimation method, even in the case of small errors in the local model's parameters which do not exceed 1% of the associated nominal values. [ABSTRACT FROM AUTHOR]

Tracking of ships' motion and monitoring of maritime traffic can be performed with the use of distributed Kalman Filtering. However, some of the local Kalman Filters which constitute distributed estimation schemes may be based on inaccurate models of the vessel's dynamics or kinematics and in such a case the aggregate state estimate provided by the distributed filter is unreliable. To treat this problem the paper proposes a statistical method of optimized performance for the validation of Fuzzy Kalman Filters used in ship tracking. This statistical validation test is capable of detecting the faulty local filter within the distributed estimation method, even in the case of small errors in the local model's parameters which do not exceed 1% of the associated nominal values. [ABSTRACT FROM AUTHOR]

This paper explores the coherence of a time series of fully polarized RADARSAT 2 imagery for vegetation state monitoring in the North Braila Terrace agricultural crop fields. The dataset consists of four scene acquired in the joint ESA-CSA SOAR Europe- 16605 scientific proposal framework covering August 2014 to March 2015 period. The PolInSAR RADARSAT 2 data contain maize, wheat and successive crops, alpha-alpha, sugar beet, sunflower and vegetables. Interferogram and coherence images were generated using single and fully polarimetric data. PolInSAR coherence describes physical properties of various targets. Man-made targets (Braila Town) show high coherence magnitude while agricultural areas suffer by temporal and volume decorrelation due to seasonal changes and exhibit lower coherence. Polarized amplitude backscattering coefficients, ratio, correlations and inter-channel phase differences at different basis are analyzed. Change detection techniques such as intensity, coherence and Wishart statistics were applied to separate changes classes from the no-changes. The results are usefully for farming activities and yield estimation. [ABSTRACT FROM AUTHOR]

One of the most pressing problems arising during the monitoring of the Earth's surface by space means of observation equipped with synthetic aperture radars is the task of increasing the efficiency of the observation means. A quantitative indicator of the named effectiveness is the probability of the correct detection of spatially distributed targets, as well as the signal-to-noise ratio. In a large number of practical situations, the coherent summation of pulses reflected from the target during the entire time of synthesis of the antenna aperture is not possible, due to phase fluctuations of the reflected signal caused by the instability of the generator, random deviations of the aircraft trajectory, random fluctuations of the reflected signals, etc. In this case, the coherent accumulation time can turn out to be significantly less than the total time of radar imaging, and coherent processing during the whole time of receiving the signal ceases to be optimal, which leads to a deterioration in detection efficiency compared to partially coherent SAR performing coherent accumulation during the coherence time followed by an incoherent summation of the obtained radar images [1,2]. With a limited length of the coherent accumulation session (synthesis session), the most rational means of increasing the detection efficiency is the use of partially coherent processing. In this case, it is assumed that the signal is coherent within a limited area with a subsequent incoherent summation of the accumulated signals. The indicated problem is solved in this paper, where the calculation formulas are obtained and their operability is demonstrated on several typical problems, indicating the requirements for the numerical ratio between the various parameters of the used system. [ABSTRACT FROM AUTHOR]

Identifying changes in the Earth's phenomena is vital for understanding and mitigating the impacts of environmental issues. Monitoring the Earth's surface phenomena can be carried out effectively using satellite images acquired at different times. In addition to spectral features, spatial features play a significant role in detecting precise changes. However, classical change detection (CD) methods rarely consider spatial information and fail to account for scale variations within images. The present study introduces a novel deep learning-based CD method that hierarchically extracts spatial–spectral features at various scales to address these issues. The proposed deep neural network generates a binary change map by employing a multi-scale approach that integrates the information of patches of varied sizes at the decision level. We conducted experiments using Landsat-8 images from Sahand City, East Azarbaijan, Iran, because of their remarkable capacity to represent the Earth's surface details. Tabriz's population growth has led to rapid development in Sahand City to accommodate citizens. Studying these changes can offer valuable insights into urban planning. The performance of the proposed deep model is evaluated in comparison to two classical methods, the change vector analysis (CVA) method and a random forest (RF) algorithm. Based on the change detection results, the proposed deep learning network demonstrates a significant improvement in the kappa coefficient (KC) compared to the RF and CVA methods, with increases of approximately 11.86% and 29.36%, respectively. Furthermore, in terms of overall accuracy (O.A.), the proposed network outperforms both the RF and CVA methods by approximately 17.08% and 29.16%, respectively. The proposed multi-scale deep network performs better at detecting changes across all metrics. As a result, the CVA method fails to identify changes with sufficient accuracy. [ABSTRACT FROM AUTHOR]

Water is an essential resource for the survival of living beings. Remote-sensing data provides the best possible way to detect water bodies and monitor change over time. With a surplus amount of remote sensing data, machine learning approaches have become an effective and efficient way to detect and monitor surface water bodies. This research focused on utilizing remote sensing and machine learning approaches to monitor changes in the surface water of Lake Okeechobee, Florida, USA. This investigation used two sources of remotely sensed data, Landsat 7, and Landsat 8, for 2002 and 2022, respectively. Two machine learning algorithms, support vector machine (SVM) and random forest (RF), were adopted, considering their power and robustness, among other factors, for supervised classification. Both algorithms provided an accuracy of over 92% and a kappa statistic exceeding 0.8. Further, we used image differencing techniques to track changes across two decades. The SVM suggested an increase of 85 km2, and RF indicated an expansion of 52 km2 in the surface water area. This study explicitly demonstrates how dynamic natural resources are, especially water sources. Thus, it can provide a foundation for research that further explores environmental assessments and sustainable water resource planning in Lake Okeechobee. [ABSTRACT FROM AUTHOR]