86,677 research outputs found
Statistical Difference Models for Change Detection in Multispectral Images
No full textThis chapter aims to present a general mathematical framework for the representation and analysis of multispectral images. It introduces two statistical models for the description of the distribution of spectral difference-vectors, and provides from them change detection methods based on image difference. The chapter presents an overview of the change detection problem in multispectral imagery and the methods proposed in the literature to address it, with emphasis on the statistical models associated with the difference image and their challenges. It also introduces the standard two-class unchange/change model for binary change detection, as derived from the hypothesis of the Gaussian distribution of natural classes in the difference image. Experiments on different image pairs from different sensors confirmed that the improved fitting of the magnitude histogram corresponds to nearly optimal change detection accuracy
Unsupervised Change Detection in Multitemporal Remote Sensing Images
No full textRemote sensing satellites have a great potential to recurrently monitor the dynamic changes of the Earth's surface in a wide geographical area, and contribute substantially to our current understanding of the land-cover and land-use changes. This chapter focuses on the unsupervised change detection (CD) problem in multitemporal multispectral images. It investigates the spectral–spatial change representation for addressing the important multiclass CD problem. Depending on the purpose of unsupervised CD tasks, two main categories of methods are defined: binary change detection and multiclass change detection. Deep learning-based CD approaches have shown great potential in extracting more high-level deep features, which represents a popular direction in CD research. The chapter introduces a proposed multiscale morphological compressed change vector analysis method. Owing to the automatic and unsupervised nature, unsupervised CD always represents a very interesting and important CD research and application frontier
TransSounder: A Hybrid TransUNet-TransFuse Architectural Framework for Semantic Segmentation of Radar Sounder Data
No full textRadar sounders (RSs) are nadir-looking sensors operating in high frequency (HF) or very high frequency (VHF) bands that profile subsurface targets to retrieve miscellaneous scientific information. Due to the complex electromagnetic interaction between backscattered returns, the interpretation of RS data is challenging. The investigations of ice-sheet subsurface structures require automatic techniques to account for both the sequential spatial distribution of subsurface targets and relevant statistical properties embedded in RS signals. Automatic techniques exist for characterizing these targets either related to probabilistic inference models or convolutional neural network (CNN) deep learning methods. Unfortunately, CNN-based methods capture local spatial context and merely model the global spatial context. In contrast to CNN, the transformer-based models are reliable architectures for capturing long-range sequence-to-sequence global spatial contextual prior. Motivated by the aforementioned fact, we propose a novel transformer-based semantic segmentation architecture named TransSounder to effectively encode the sequential structures of the RS signals. The TransSounder was constructed on a hybrid TransUNet-TransFuse architectural framework to systematically augment the modules from TransUNet and TransFuse architectures. Experimental results obtained using the Multichannel Coherent Radar Depth Sounder (MCoRDS) dataset confirms the robustness and capability of transformers to accurately characterize the different subsurface targets
Transformer-based Spatio-temporal Change Detection Network Using Satellite Image Time Series: A Case Study of Forest Disturbance in Trentino, Italy Following the Vaia Storm
No full textA Hybrid CNN-Transformer Architecture for Semantic Segmentation of Radar Sounder data
No full textRadar Sounders (RSs) are space-borne and airborne sensors operating on the nadir-looking geometry to collect sub-surface information by transmitting linearly modulated electro-magnetic (EM) pulses and receiving backscattered (reflected from different subsurface targets) echoes. The echoes are coherently represented to generate radargrams. A radargram is used to characterize subsurface target structures. Interestingly, radargram signals depict sequential structures due to linearly homo-geneous subsurface target features such as ice layers. Several automatic techniques are proposed to characterize the subsurface targets in the radargrams mostly associated with the probabilistic models or CNN-based deep learning models. The CNN-based architectures explicitly model the local spatial high dimensional contexts which are often infeasible for establishing the long-range sequential contextual relationship between local spatial features. Motivated by the aforementioned fact, we propose a hybrid CNN-Transformer-based encoder-decoder architectural framework for addressing the long-range sequential contextual dependencies within the sequential structures of RS signals. We tested the architecture on Multi-channel Coherent Radar Depth Sounder (MCoRDS) dataset. Experimental results confirm the capability of Transformers to characterize the subsurface targets
- …
