The fraction of absorbed photosynthetically active radiation (fAPAR) is an important biophysical characteristic in models of vegetation productivity. Synoptic estimation of fAPAR has been performed by using Normalized Difference Vegetation Index(NDVI) as a linear proxy of fAPAR. However, in high-density canopies, the sensitivity of NDVI to fAPAR is reduced. The NDVI/fAPAR relationship is analyzed in high-density rice in this paper. In addition, we combine the absorption ratio of senescent leaves and green leaves in the photosynthetically active radiation (PAR) region, re-determines the meaning of green fAPAR, and analyzes the sensitivity of green fAPAR under different nitrogen treatments. Moreover, other more effective alternative vegetation indices such as Wide Dynamic Range Vegetation Index (WDRVI) and absorption coefficient of PAR (αPAR) by remote sensing are also utilized to evaluate changes in green fAPAR.

Semantic segmentation of remote sensing images plays a vital role in a wide range of Earth Observation applications, such as land-use land-cover (LULC) mapping, environment monitoring, and sustainable development. Driven by rapid developments in artificial intelligence, deep learning (DL) has emerged as the mainstream for semantic segmentation and has achieved many breakthroughs in the field of remote sensing. However, most DL-based methods focus on unimodal visual data while ignoring rich multimodal information involved in the real world. Nonvisual data, such as text, can gather extra knowledge from the real world, which can strengthen the interpretability, reliability, and generalization of visual models. Inspired by this, we propose a novel metadata-collaborative segmentation network (MetaSegNet) that applies vision-language representation learning for the semantic segmentation of remote sensing images. Unlike the common model structure that only uses unimodal visual data, we extract the key characteristic (e.g., the climate zone) from freely available remote sensing image metadata and transfer it into geographic text prompts via the generic ChatGPT. Then, we construct an image encoder, a text encoder, and a crossmodal attention fusion subnetwork to extract the image and text feature and apply image-text interaction. Benefiting from such a design, the proposed MetaSegNet not only demonstrates superior generalization in zero-shot testing but also achieves competitive accuracy with the state-of-the-art semantic segmentation methods on the large-scale OpenEarthMap dataset [70.4% mean intersection over union (mIoU)] and the Potsdam dataset (93.3% mean${F}1$score) as well as the LoveDA dataset (52.0% mIoU).

Unmanned aerial vehicles (UAVs) equipped with different sensors can provide data with high spatiotemporal resolution and have broad application prospects. During the flight of the UAV, changes in illumination, exposure time, etc., will cause different degrees of radiometric differences between images, resulting in a calibration relationship established on a single image that cannot be applied to other images; in addition, the vignetting effect also significantly changes the brightness distribution inside an image, thus posing challenges for radiometric calibration of UAV images. In this paper, based on block adjustment (BA), we proposed a radiometric block adjustment model under the consideration of vignetting and the light-dark differences between images. The proposed method requires only a small number of calibration blankets, thus reducing the complexity of the experiment. The results from two study areas showed that the proposed method could compensate for vignetting to a certain extent and the radiometric consistency of the two datasets was improved from 12.9%~21.8% to 4.7%~12.7%. Validated using ground samples, the mean RMSE and MRPE of all five bands were 0.054, 21.8%, and 0.037, 20.4% in the two study areas, respectively. The total uncertainty was less than 8.1%. When there were obvious light-dark differences between images, such as in the visible light bands, our method could significantly improve the accuracy of the radiometric calibration.

The fully convolutional network (FCN) with an encoder-decoder architecture has been the standard paradigm for semantic segmentation. The encoder-decoder architecture utilizes an encoder to capture multilevel feature maps, which are incorporated into the final prediction by a decoder. As the context is crucial for precise segmentation, tremendous effort has been made to extract such information in an intelligent fashion, including employing dilated/atrous convolutions or inserting attention modules. However, these endeavors are all based on the FCN architecture with ResNet or other backbones, which cannot fully exploit the context from the theoretical concept. By contrast, we introduce the Swin Transformer as the backbone to extract the context information and design a novel decoder of densely connected feature aggregation module (DCFAM) to restore the resolution and produce the segmentation map. The experimental results on two remotely sensed semantic segmentation datasets demonstrate the effectiveness of the proposed scheme.

Due to different imaging mechanisms bringing significant nonlinear radiation differences (NRDs), traditional feature matching methods are difficult to obtain satisfactory results for multispectral images. The key to multispectral image matching is eliminating the NRDs and extracting more robust features. This letter proposed a novel descriptor combining the phase consistency (PC) gradient and log-polar coordinates to solve the NRDs of multispectral images. First, the nonlinear weighted moment (NWM) is constructed for detecting feature points. Then, the PC model is extended to construct the absolute PC orientation gradient. Combined with the log-polar description, the histogram of PC gradients (HPCG) is established. Finally, a purification algorithm with dynamic adaptive Euclidean distance and fast sample consensus (FSC) constraints is proposed to eliminate mismatches while retaining the correct matches. The proposed HPCG descriptor was evaluated using six groups of multispectral images. The experimental results show that our method is better than the other seven descriptors [i.e., scale-invariant feature transform (SIFT), edge-oriented histogram (EOH), edge histogram descriptor (EHD), log-Gabor histogram descriptor (LGHD), PC edge histogram descriptor (PCEHD), optical-to-SAR-SIFT (OSSIFT), and histogram of oriented self-similarity (HOSS)], which have strong adaptability and robustness.

As an important carrier of human productive activities, the extraction of buildings is not only essential for urban dynamic monitoring but also necessary for suburban construction inspection. Nowadays, accurate building extraction from remote sensing images remains a challenge due to the complex background and diverse appearances of buildings. The convolutional neural network (CNN) based building extraction methods, although increased the accuracy significantly, are criticized for their inability for modelling global dependencies. Thus, this paper applies the Vision Transformer for building extraction. However, the actual utilization of the Vision Transformer often comes with two limitations. First, the Vision Transformer requires more GPU memory and computational costs compared to CNNs. This limitation is further magnified when encountering large-sized inputs like fine-resolution remote sensing images. Second, spatial details are not sufficiently preserved during the feature extraction of the Vision Transformer, resulting in the inability for fine-grained building segmentation. To handle these issues, we propose a novel Vision Transformer (BuildFormer), with a dual-path structure. Specifically, we design a spatial-detailed context path to encode rich spatial details and a global context path to capture global dependencies. Besides, we develop a window-based linear multi-head self-attention to make the complexity of the multi-head self-attention linear with the window size, which strengthens the global context extraction by using large windows and greatly improves the potential of the Vision Transformer in processing large-sized remote sensing images. The proposed method yields state-of-the-art performance (75.74% IoU) on the Massachusetts building dataset. Code will be available at https://github.com/WangLibo1995/BuildFormer.

In this paper high resolution remote sensing data (ALOS and ZY-3) and abundant geological data were applied to analysis the weight of the influence factor of landslide in the Three Gorges area. The evaluation factor includes engineering rock group, human activity, hydrogeology, etc. The multivariate statistical analysis strategy was applied to confirm the weight of each factor. Results show that the method plays more attention to the surface and strata. Its accuracies could be greater than 94%. The result is more close to reality. This method can be presented as a new means for stability evaluation of the geological disasters.

Landsat TM data of six multispectral bands were used to extract the fault information in the southwest region of Zigui basin which is near the Three Gorges bam, located at the eastern section of Daba Mountain tectonic belt. The techniques consist of spectral enhancement and spatial enhancement. Band ratioing methods, Principal component analysis(PCA), decorrelation stretching were applied in this paper. In the end, these methods would be compared and evaluated. The results showed that the fault information extraction method with Landsat TM data performed satisfied.