Semantic segmentation from very fine resolution (VFR) urban scene images plays a significant role in several application scenarios including autonomous driving, land cover classification, urban planning, etc. However, the tremendous details contained in the VFR image, especially the considerable variations in scale and appearance of objects, severely limit the potential of the existing deep learning approaches. Addressing such issues represents a promising research field in the remote sensing community, which paves the way for scene-level landscape pattern analysis and decision making. In this paper, we propose a Bilateral Awareness Network which contains a dependency path and a texture path to fully capture the long-range relationships and fine-grained details in VFR images. Specifically, the dependency path is conducted based on the ResT, a novel Transformer backbone with memory-efficient multi-head self-attention, while the texture path is built on the stacked convolution operation. In addition, using the linear attention mechanism, a feature aggregation module is designed to effectively fuse the dependency features and texture features. Extensive experiments conducted on the three large-scale urban scene image segmentation datasets, i.e., ISPRS Vaihingen dataset, ISPRS Potsdam dataset, and UAVid dataset, demonstrate the effectiveness of our BANet. Specifically, a 64.6% mIoU is achieved on the UAVid dataset.

The integrated navigation system, which consists of the Global Navigation Satellite System (GNSS) and inertial navigation system(INS), is widely used in various platforms. However, when the GNSS signal is unavailable, the GNSS / INS integrated navigation system will be converted to INS working alone. The error will gradually diverge. To solve this problem, this paper constructs a hybrid neural network model composed of Convolutional Neural Networks(CNN) and Gated Recurrent Unit(GRU). It combines the pseudo-measurement information of GNSS predicted by the model with INS for integrated navigation to compensate for the interruption of GNSS and correct the error of INS. At the same time, considering that the predicted GNSS position information has a significant error, if the estimation is not accurate, the filtering accuracy of the system will decrease. Therefore, this paper proposes an improved robust adaptive Kalman filter (IRAKF) algorithm to estimate the measurement noise covariance matrix for GNSS pseudo-measurement information. The actual road test results show that the addition of the CNN-GRU model and IRAKF algorithm improves the overall accuracy of the system.

Assigning geospatial objects with specific categories at the pixel level is a fundamental task in remote sensing image analysis. Along with the rapid development of sensor technologies, remotely sensed images can be captured at multiple spatial resolutions (MSR) with information content manifested at different scales. Extracting information from these MSR images represents huge opportunities for enhanced feature representation and characterisation. However, MSR images suffer from two critical issues: (1) increased scale variation of geo-objects and (2) loss of detailed information at coarse spatial resolutions. To bridge these gaps, in this paper, we propose a novel scale-aware neural network (SaNet) for the semantic segmentation of MSR remotely sensed imagery. SaNet deploys a densely connected feature network (DCFFM) module to capture high-quality multi-scale context, such that the scale variation is handled properly and the quality of segmentation is increased for both large and small objects. A spatial feature recalibration (SFRM) module was further incorporated into the network to learn intact semantic content with enhanced spatial relationships, where the negative effects of information loss are removed. The combination of DCFFM and SFRM allows SaNet to learn scale-aware feature representation, which outperforms the existing multi-scale feature representation. Extensive experiments on three semantic segmentation datasets demonstrated the effectiveness of the proposed SaNet in cross-resolution segmentation.

Semantic segmentation of remote sensing images plays a vital role in a wide range of Earth Observation applications, such as land use land cover 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. Non-visual 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 multimodal segmentation network (MetaSegNet) that applies vision-language representation learning for 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% mIoU) and the Potsdam dataset (93.3% mean F1 score) as well as the LoveDA dataset (52.0% mIoU).

With the widespread application of remote sensing technology in environmental monitoring, the demand for efficient and accurate remote sensing image change detection (CD) for natural environments is growing. We propose a novel deep learning framework named EfficientCD, specifically designed for remote sensing image change detection. The framework employs EfficientNet as its backbone network for feature extraction. To enhance the information exchange between bi-temporal image feature maps, we have designed a new Feature Pyramid Network module targeted at remote sensing change detection, named ChangeFPN. Additionally, to make full use of the multi-level feature maps in the decoding stage, we have developed a layer-by-layer feature upsampling module combined with Euclidean distance to improve feature fusion and reconstruction during the decoding stage. The EfficientCD has been experimentally validated on four remote sensing datasets: LEVIR-CD, SYSU-CD, CLCD, and WHUCD. The experimental results demonstrate that EfficientCD exhibits outstanding performance in change detection accuracy. The code and pretrained models will be released at https://github.com/dyzy41/mmrscd.

The calculation of volumes for irregular bodies holds significant relevance across various production processes. This spans tasks such as evaluating the growth status of crops and fruits, conducting morphological analyses of spatial objects based on volume parameters, and estimating quantities for earthwork and excavation. While methods like drainage, surface reconstruction, and triangulation suffice for smaller irregular bodies, larger ones introduce heightened complexity. Technological advancements, such as UAV photogrammetry and LiDAR, have introduced efficient point cloud data acquisition methods, bolstering precision and efficiency in calculating volumes for substantial irregular bodies. Notably, open-pit mines, characterized by their dynamic surface alterations, exemplify the challenges posed by large irregular bodies. Ensuring accurate excavation quantity calculations in such mines is pivotal, impacting operational considerations, acceptance, as well as production cost management and project oversight. Thus, this study employs UAV-acquired point cloud data from open-pit mines as a case study. In practice, calculating volumes for substantial irregular bodies often relies on the point cloud slicing method. However, this approach grapples with distinguishing multi-contour boundaries, leading to inaccuracies. To surmount this hurdle, this paper introduces an enhanced point cloud slicing method. The methodology involves segmenting point cloud data at fixed intervals, followed by the segmentation of slice contours using the Euclidean clustering method. Subsequently, the concave hull algorithm extracts the contour polygons of each slice. The final volume calculation involves multiplying the area of each polygon by the spacing and aggregating these products. To validate the efficacy of our approach, we employ model-derived volumes as benchmarks, comparing errors arising from both the traditional slicing method and our proposed technique. Experimental outcomes underscore the superiority of our point cloud volume calculation method, manifesting in an average relative error of 1.17%, outperforming the conventional point cloud slicing method in terms of accuracy.