1,720,963 research outputs found
Attention-based 3D convolutional neural network for crop boundary detection in high-resolution satellite image time series
No full textAdvancements in satellite missions have dramatically improved the monitoring of vegetation and agricultural activities through high-resolution Satellite Image Time Series (SITS), providing enhanced insights into crop dynamics and boundary identification. However, traditional UNet-based Convolutional Neural Networks (CNNs), though effective for crop mapping, often struggle to capture the full spatio-temporal complexities inherent in these datasets, particularly when it comes to detecting less distinct boundaries. To address these challenges, a novel attention-based residual 3D UNet architecture has been developed, incorporating a spatial-temporal attention mechanism that enhances the networks ability to represent spatial and temporal features. This attention mechanism is strategically implemented in the decoder, where it gathers information from both the encoder and the previous layer within the decoder. This dual-source integration allows the model to focus more effectively on relevant crop boundaries during training, assigning greater weight to these crucial areas while reducing the emphasis on non-crop regions. The residual 3D UNet architecture adeptly handles the intricate spatial-spectral-temporal correlations present in SITS, enabling more accurate and simultaneous modelling of both spatial and temporal information. The proposed method is evaluated on an area with small-scale crop fields in Germany using Sentinel-2 SITS data collected over several months, this approach demonstrated superior performance in boundary detection compared to existing state-of-the-art methods, particularly in scenarios where boundaries are less clearly defined
A convolutional neural network approach to the detection of LC transitions in multi-annual satellite image time series
No full textRecently, deep learning-based methods have been exploited to learn complex features from Satellite Image Time Series (SITS) with superior spatial, spectral, and temporal resolution for the Land Cover Transition (LCT) analysis. However, in order to efficiently utilize High Resolution (HR) SITS for detecting LCTs, there is a need to tackle challenges related to a proper modelling of the LC behavior and pertain to the intricacy of the temporally dense SITS. A novel LCT detection approach is presented that exploits a pretrained Three Dimensional (3D) Convolutional Neural Network (CNN) to simultaneously extract spatio-temporal information from multi-annual SITS to identify the LCTs. To highlight the changed pixels, a multi-feature hyper temporal difference feature vector is generated that properly provides intrinsic information of the LC trends in space and time. To distinguish different LCTs between two consecutive years for the changed pixels, a clustering process is performed that considers the temporal information of the difference hyper features to discriminate and understand the LCTs. The product is a map indicating the location of changed pixels and providing information about the type of LCTs. The preliminary analysis has been done over a region in Sahel – Africa with images acquired between 2015 and 2016. The proposed approach has been compared with another LCT detection approach using 2D CNN. Experimental results confirm the effectiveness of the proposed approach in detecting the LCTs
Multiannual Change Detection Using a Weakly Supervised 3-D CNN in HR SITS
No full textIn recent years, deep learning methods, in particular convolutional neural networks (CNNs), have been increasingly used in change detection (CD). However, most CNN-based CD methods are primarily designed for analyzing only a single pair of images due to the challenge of collecting and constructing ground reference data during the system-training phase. Consequently, the existing CD methods, particularly those focused on detecting multiannual changes, exhibit limited capability in extracting comprehensive spatiotemporal information. To address this limitation, we propose a novel weakly supervised deep-learning-based technique for CD exploiting a 3-D CNN architecture to extract spatiotemporal information. Our technique incorporates a fine-tuning stage to effectively capture temporal patterns from a yearly Satellite Image Time Series (SITS) by using different 3-D convolutional layers. It also exploits a multifeature hypertemporal change vector analysis (CVA) for multiannual change identification. The proposed approach is tested on a four-year dataset in Amazonia and gained the highest yearly CD accuracy of 88.59%, 97.27%, and 87.87% for 2017, 2018, and 2019, respectively
A Multi-Feature Hyper-Temporal Change Vector Analysis Method for Change Detection in Multi-Annual Time Series of HR Satellite Images
No full textA great effort has been put on developing technologies that can process High Resolution (HR) satellite datasets to properly monitor the environmental changes and produce long term Change Detection (CD) maps. However, there is still a need to design CD approaches that process Satellite Image Time Series (SITS) with high spatial, spectral, and temporal resolution and describe changes that have occurred between the consecutive years. Here, a CD processing chain is proposed that: i) extracts several relevant features of the spectral trends of different sets of LC changes, ii) produces a regular and dense feature time series, iii) analyzes differences between the consecutive years by using a Multi-feature Hyper-temporal Change Vector Analysis (MHCVA) technique, and iv) detects the year and the probability of changes at pixel level. The effectiveness of the proposed approach is tested on a multi-annual Landsat 7 and 8 images of an area located in Amazon
Crop Field Boundary Detection Using 3d Convolutions in Multi-Spectral Multi-Temporal Hr Satellite Images
No full textThe advent of new satellite missions offering high spatial, spectral, and temporal resolution has significantly enhanced the possibility to monitor vegetation and agricultural practices. The High-resolution (HR) Satellite Image Time Series (SITS) enables a deeper understanding of crop fields behavior and precise boundary detection. While Convolutional Neural Networks (CNNs) have demonstrated effectiveness in crop fields-related analyses, existing methods for crop boundary detection often focus on mono-temporal image analysis, overlooking valuable multi-temporal information in SITS. To address this gap, we propose the utilization of a UNet-based three-dimensional (3D) CNN architecture, allowing for the simultaneous modeling of spatial-temporal information within multi-spectral multi-temporal SITS. Additionally, we explore various CNN-based U-Net models to further validate the proposed approach in accurately detecting crop field boundaries. The method is evaluated in an agricultural area in Germany using 12 Sentinel-2 Level-2A images and has demonstrated promising results
A land cover-driven approach for fitting satellite image time series in a change detection context
No full textThanks to the freely availability of several Satellite Image Time Series (SITS) covering the Earth, it is now possible to monitor and analyse Land Covers (LC) and Land Cover Changes (LCC) on a yearly or even longer time span. Such applications are relevant in the context of Climate Change (CC), where consequences of the changes can only be seen on long term. Nevertheless, SITS suffer from atmospheric condition related problems (when talking about passive sensors) that reduce the temporal resolution of images in SITS. Several methods have been proposed in literature to mitigate these problems, and are placed under gap filling or SITS fitting methods. Such methods generally work with a single feature, being it a radiometric index or a spectral band. The use of multiple features is limited to specific single LC class or satellite sensor, limiting its usage in LCC and CC. Thus, in this paper, we propose an approach that is automatic, and both LC and feature independent. Here we propose the use of Normalized Difference Indices (NDI), with combination of all available spectral bands. The proposed approach uses a dropout upper-envelope strategy to reconstruct SITS trends, based on a set of rules, and guarantees a smoother closer trend to that of the original data. The proposed approach has been applied over two regions (Amazonia and Saudi Arabia) in the period 2013-2017, and has been compared to other fitting methods: Cubic Splines and Univariate Splines. It has been further evaluated by detecting LCC with long SITS methods such as Breaks For Additive Seasonal and Trend (BFAST). The preliminary results are promising demonstrating the robustness of the approach across different LCs and across different features
Automatic Large-Scale Precise Mapping and Monitoring of Agricultural Fields at Country Level with Sentinel-2 SITS
No full textAvailability of multitemporal (MT) images, such as the sentinel-2 (S2) ones, offers accurate spatial, spectral and temporal information to effectively monitor vegetation, more specifically agriculture. Agricultural practices can benefit from temporally dense satellite image time series (SITS) for accurate understanding of the phenological evolution and behavior of crops. Developing techniques that deal with high spatial correlation and high temporal resolution requires a shift in the processing paradigm and poses new challenges in terms of data processing and methodology. This article presents an automatic approach to large-scale precise mapping of small agricultural fields based on the analysis of S2-SITS at Country level. The approach deals with a flexible and automatic processing chain for massive data and was tested at Country level. The large-scale application requires to consider: the management of big amount of data with particular attention to download and pre-processing of S2-SITS; and MT fine characterization of crop fields accounting for the strong variability in size and phenological behaviors when mapping at large scale. Both challenges are addressed in an automatic way by exploiting and/or updating state-of-the-art methodologies. Promising results have been obtained and validated over 2017 and 2018 agrarian years for Italy
An Unsupervised Change Detection Approach for Dense Satellite Image Time Series Using 3D CNN
No full textRecent satellite missions have initiated a new era in the area of Satellite Image Time Series (SITS) analysis by providing a huge number of High Resolution (HR) spectral-temporal images. The availability of HR images opens a door to an unprecedented wide range of possibilities to produce and develop high resolution Land Cover (LC) and Land Cover Change (LCC) maps. The goal of this paper is to effectively use high spatio-temporal resolution images to generate LCC maps by defining a novel automatic and unsupervised deep learning method based on three-dimensional (3D) Convolutional Neural Network (CNN). The method extracts spatio-temporal information from long SITS by using a pre-trained 3D CNN, detects changes and locates them in space and time. Experiments have provided promising results over both Amazonia and Saudi Arabia in the period 2013–2017, and has been compared to the other well-known LCC detection method
Bi-Temporal to Time Series Data Analysis
No full textMultitemporal data analysis is a hot topic in remote sensing. In this chapter, literature is revised about (i) non-deep learning and (ii) deep learning-based for both bi-temporal and time series image analysis. The bi-temporal image analysis mainly exploits comparison of two images only techniques for the detection of presence/absence of changes and rely on classification methods for detecting land-cover transitions. The time series analysis makes use of multi-temporal images (more than two) for land-cover monitoring and change detection in long time series. Images acquired by multispectral optical systems at medium, high and very high spatial resolution are considered
- …
