ISPRS Journal of Photogrammetry and Remote Sensing最新文献

Change detection in high-resolution Earth observation is a fundamental Earth vision task to understand the subtle temporal dynamics of Earth’s surface, significantly promoted by generic vision technologies in recent years. Vision Transformer is a powerful component to learning spatiotemporal representation but with enormous computation complexity, especially for high-resolution images. Besides, there is still lacking principles in designing macro architectures integrating these advanced vision components for various change detection tasks. In this paper, we present a deep probabilistic change model (DPCM) to provide a unified, interpretable, modular probabilistic change process modeling to address multiple change detection tasks, including binary change detection, one-to-many semantic change detection, and many-to-many semantic change detection. DPCM describes any complex change process as a probabilistic graphical model to provide theoretical evidence for macro architecture design and generic change detection task modeling. We refer to this probabilistic graphical model as the probabilistic change model (PCM), where DPCM is the PCM parameterized by deep neural networks. For parameterization, the PCM is factorized into many easy-to-solve distributions based on task-specific assumptions, and then we can use deep neural modules to parameterize these distributions to solve the change detection problem uniformly. In this way, DPCM has both theoretical macro architecture from PCM and strong representation capability of deep networks. We also present the sparse change Transformer for better parameterization. Inspired by domain knowledge, i.e., the sparsity of change and the local correlation of change, the sparse change Transformer computes self-attention within change regions to model spatiotemporal correlations, which has a quadratic computational complexity of the change region size but independent of image size, significantly reducing computation overhead for high-resolution image change detection. We refer to this instance of DPCM with sparse change Transformer as ChangeSparse to demonstrate their effectiveness. The experiments confirm ChangeSparse’s superiority in speed and accuracy for multiple real-world application scenarios, such as disaster response and urban development monitoring. The code is available at https://github.com/Z-Zheng/pytorch-change-models. More resources can be found in http://rsidea.whu.edu.cn/resource_sharing.htm.

Laser scanning is an active remote sensing technique applied in many disciplines to acquire state-of-the-art spatial measurements. Semantic labeling is often necessary to extract information from the raw point cloud. Deep learning methods constitute a data-hungry solution for the semantic segmentation of point clouds. In this work, we investigate the use of simulated laser scanning for training deep learning models, which are applied to real data subsequently. We show that training a deep learning model purely on virtual laser scanning data can produce results comparable to models trained on real data when evaluated on real data. For leaf-wood segmentation of trees, using the KPConv model trained with virtual data achieves 93.7% overall accuracy, while the model trained on real data reaches 94.7% overall accuracy. In urban contexts, a KPConv model trained on virtual data achieves 74.1% overall accuracy on real validation data, while the model trained on real data achieves 82.4%. Our models outperform the state-of-the-art model FSCT in terms of generalization to unseen real data as well as a baseline model trained on points randomly sampled from the tree mesh surface. From our results, we conclude that the combination of laser scanning simulation and deep learning is a cost-effective alternative to real data acquisition and manual labeling in the domain of geospatial point cloud analysis. The strengths of this approach are that (a) a large amount of diverse laser scanning training data can be generated quickly and without the need for expensive equipment, (b) the simulation configurations can be adapted so that the virtual training data have similar characteristics to the targeted real data, and (c) the whole workflow can be automated through procedural scene generation.

Building height serves as a crucial parameter in characterizing urban vertical structure, which has a profound impact on urban sustainable development. The emergence of street-view data offers the opportunity to observe urban 3D scenarios from the human perspective, benefiting the estimation of building height. In this paper, we propose an efficient and robust building height estimation model, which we call the Pano2Geo model, by precisely projecting street-view panorama (SVP) coordinates to geospatial coordinates. Firstly, an SVP refinement stratagem is designed, incorporating NENO rules for observation quality assessment from four aspects: number of buildings, extent of the buildings, number of nodes, and orthogonal observations, followed by the application of the art gallery theorem to further refine the SVPs. Secondly, the Pano2Geo model is constructed, which provides a pixel-level projection transformation from SVP coordinates to 3D geospatial coordinates for locating the height features of buildings in the SVP. Finally, the valid building height feature points in the SVP are extracted based on a slope mutation test, and the 3D geospatial coordinates of the building height feature points are projected using the Pano2Geo model, so as to obtain the building height. The proposed model was evaluated in the city of Wuhan in China, and the results indicate that the Pano2Geo model can accurately estimate building height, with an average error of 1.85 m. Furthermore, compared with three state-of-the-art methods, the Pano2Geo model shows superior performance, with only 10.2 % of buildings have absolute errors exceeding 2 m, compared to the Map-image-based (27.2 %), Corner-based (16.8 %), and Single-view-based (13.9 %) height estimation methods. The SVP refinement method achieves optimal observation quality with less than 50 % of existing SVPs, leading to highly efficient building height estimation, particularly in areas of a high building density. Moreover, the Pano2Geo model exhibits robustness in building height estimation, maintaining errors within 2 m even as building shape complexity and occlusion degree increase within the SVP. Our source dataset and code are available at https://github.com/Giser317/Pano2Geo.git.

The scale of meteorological data products does not match the requirements of application scenarios, which limits their application. It is suggested that large-scale reanalysis data must be downscaled before use. Attention mechanism is the key to high-performance downscaling models. However, in different application scenarios and different locations on the network, the attention mechanism is not always beneficial. In this paper, we propose a dynamic attention module that can adaptively generate weights for each branch based on input features, thereby dynamically suppressing unnecessary attention adjustments. At the same time, we propose a layer attention module, which can independently and adaptively aggregate the feature representation of different network layers. In addition, we design a unique loss function based on homoscedasticity uncertainty, which can directly guide the model to learn the numerical mapping relationship from low resolution to high resolution at the pixel level, and implicitly motivate the model to better reconstruct the data distribution of each meteorological field by guiding the model to learn the distribution difference between different meteorological fields. Experiments show that our model is more robust in time dimension, with an MAE average reduction of about 40% compared to VDSR and other methods in downscaling composite meteorological data. It can more accurately reconstruct multivariate high-resolution meteorological fields. Codes available at https://github.com/HitKarry/SDDN.

Evapotranspiration (ET), which represents water loss due to soil evaporation and crop transpiration, is a critical hydrological parameter for managing available water resources in irrigation systems. Traditional methods for monitoring actual evapotranspiration (ETa) involve field measurements. While accurate, they lack scalability, are labor-intensive, and incur high costs. Remote sensing satellites can help address these practical challenges by providing high-resolution imagery for spatially explicit mapping and near-real-time monitoring of ETa. This study aimed to develop simple yet robust models for estimating ETa using Sentinel-2 (S2A and S2B) satellite vegetation indices (VIs)—the normalized difference vegetation index (NDVI) and the enhanced vegetation index (EVI)—and the Google Earth Engine (GEE) cloud platform for irrigated sugarcane plantations of the Metehara Sugarcane Estate in the semiarid landscape of the Ethiopian Rift Valley. Six empirical ET-VI models that combined NDVI-based proxies (NDVI_Kc, NDVI*, and NDVI*_scaled) and EVI-based proxies (EVI_Kc, EVI*, and EVI*_scaled) for the crop coefficient (Kc) with the reference ET (ETo) were developed and evaluated for growing seasons between 2020 and 2022. Model validation using independently estimated sugarcane ET (ET_sugarcane) and open-access remote sensing ET, Actual EvapoTranspiration and Interception (ETIa) showed that all ET-VI models captured spatiotemporal dynamics in the consumptive fraction of sugarcane water use, with a higher coefficient of determination (R²) of ≥ 0.91. However, comparative analyses of ETa retrieval models indicated improved accuracy of the ET-EVI models (root mean square error (RMSE) of ± 8 mm for ET_sugarcane and ± 4 mm for ETIa) compared with the ET-NDVI models. Among the EVI models, ET-EVI_Kc achieved the highest R² of 0.98, RMSE of ≤ 30 mm, and percentage bias (PBIAS) of ≤ 15 %. The results also revealed a strong correlation between the scaled VI-derived models and the reference ETIa (R² = 0.94–0.97), which best explained the field-by-field variability, with the ET-EVI*_scaled model achieving a lower RMSE of 18 mm than the ET-NDVI*_scaled model (RMSE= 32 mm), while both the models showed similar levels of bias (∼17 %). Moreover, compared to the referenced ET_sugarcane, the bias was minimal at − 9 % for ET-NDVI*_scaled and − 1 % for ET-EVI*_scaled. At the field scale, the NDVI and EVI models estimated the mean monthly ETa ranging from 99 to 129 mm m⁻¹ and 89 to 148 mm m⁻¹, respectively, with total annual averages of 1188–1537 mm yr⁻¹ and 1296–1566 mm yr⁻¹. In this context, the modeled ETa provided improved insights into consumptive water use in irrigated sugarcane plantations with limited field measurements. The statistical model evaluation metrics indic