Spatial Information Research Articles

Earthquake, flood and resilience management through spatial planning, decision and information system

Assessment and planning of crisis management with the natural disasters approach include many components. In this regard, floods and earthquakes are some of the fundamental pillars in this field. With this view, paying attention to the current and future planning and research priorities of the world shows that crisis management in flood-prone and earthquake-prone areas and increasing resilience are the most important priorities for sustainable development studies and planning in the world. The western region of Iran (Lorestan province) has a special place due to the prominent features of flood and seismicity. This study aims to investigate the current situation regarding floods and earthquakes and increase the resilience of settlements with emphasis on the study area. After studying the current structure of flood and earthquake zoning according to multi-factor criteria, zoning was performed based on the integration of GIS and AHP information systems, and at the output of the work, high-risk settlements were determined separately for rural and urban areas with geographical coordinates, and then areas with low, very low, medium, high, and very high resilience were presented separately for rural and urban settlements. Also, after analyzing the SWOT model, strategies to increase the resilience of settlements to floods and earthquakes were presented. The study method of this research and the results, strategies, and operational options presented while being used in the study area are also applicable in other areas.

Single-cell and spatial transcriptomic investigation reveals the spatiotemporal specificity of the beta-defensin gene family during mouse sperm maturation

Low sperm motility is a significant contributor to male infertility. beta-defensins have been implicated in host defence and the acquisition of sperm motility; however, the regulatory mechanisms governing their gene expression patterns and functions remain poorly understood. In this study, we performed single-cell RNA and spatial transcriptome sequencing to investigate the cellular composition of testicular and epididymal tissues and examined their gene expression characteristics. In the epididymis, we found that epididymal epithelial cells display a region specificity of gene expression in different epididymal segments, including the beta-defensin family genes. In particular, Defb15, Defb18, Defb20, Defb25 and Defb48 are specific to the caput; Defb22, Defb23 and Defb26 to the corpus; Defb2 and Defb9 to the cauda of the epididymis. To confirm this, we performed mRNA fluorescence in situ hybridisation (FISH) targeting certain exon region of beta-defensin genes, and found some of their expression matched the sequencing results and displayed a close connection with epididimosome marker gene Cd63. In addition, we paid attention to the Sertoli cells and Leydig cells in the testis, along with fibroblasts and smooth muscle cells in the epididymis, by demonstrating their gene expression profile and spatial information. Our study provides a single-cell and spatial landscape for analysing the gene expression characteristics of testicular and epididymal environments and has important implications for the study of spermatogenesis and sperm maturation.

Recognizing online video genres using ensemble deep convolutional learning for digital media service management

It's evident that streaming services increasingly seek to automate the generation of film genres, a factor profoundly shaping a film's structure and target audience. Integrating a hybrid convolutional network into service management emerges as a valuable technique for discerning various video formats. This innovative approach not only categorizes video content but also facilitates personalized recommendations, content filtering, and targeted advertising. Given the tendency of films to blend elements from multiple genres, there is a growing demand for a real-time video classification system integrated with social media networks. Leveraging deep learning, we introduce a novel architecture for identifying and categorizing video film genres. Our approach utilizes an ensemble gated recurrent unit (ensGRU) neural network, effectively analyzing motion, spatial information, and temporal relationships. Additionally,w we present a sophisticated deep neural network incorporating the recommended GRU for video genre classification. The adoption of a dual-model strategy allows the network to capture robust video representations, leading to exceptional performance in multi-class movie classification. Evaluations conducted on well-known datasets, such as the LMTD dataset, consistently demonstrate the high performance of the proposed GRU model. This integrated model effectively extracts and learns features related to motion, spatial location, and temporal dynamics. Furthermore, the effectiveness of the proposed technique is validated using an engine block assembly dataset. Following the implementation of the enhanced architecture, the movie genre categorization system exhibits substantial improvements on the LMTD dataset, outperforming advanced models while requiring less computing power. With an impressive F1 score of 0.9102 and an accuracy rate of 94.4%, the recommended model consistently delivers outstanding results. Comparative evaluations underscore the accuracy and effectiveness of our proposed model in accurately identifying and classifying video genres, effectively extracting contextual information from video descriptors. Additionally, by integrating edge processing capabilities, our system achieves optimal real-time video processing and analysis, further enhancing its performance and relevance in dynamic media environments.

Crowdsourcing RTK: a new GNSS positioning framework for building spatial high-resolution atmospheric maps based on massive vehicle GNSS data

High-quality spatial atmospheric delay correction information is essential for achieving fast integer ambiguity resolution (AR) in precise positioning. However, traditional real-time precise positioning frameworks (i.e., NRTK and PPP-RTK) depend on spatial low-resolution atmospheric delay correction through the expensive and sparsely distributed CORS network. This results in limited public appeal. With the mass production of autonomous driving vehicles, more cost-effective and widespread data sources can be explored to create spatial high-resolution atmospheric maps. In this study, we propose a new GNSS positioning framework that relies on dual base stations, massive vehicle GNSS data, and crowdsourced atmospheric delay correction maps (CAM). The map is easily produced and updated by vehicles equipped with GNSS receivers in a crowd-sourced way. Specifically, the map consists of between-station single-differenced ionospheric and tropospheric delays. We introduce the whole framework of CAM initialization for individual vehicles, on-cloud CAM maintenance, and CAM-augmented user-end positioning. The map data are collected and preprocessed in vehicles. Then, the crowdsourced data are uploaded to a cloud server. The massive data from multiple vehicles are merged in the cloud to update the CAM in time. Finally, the CAM will augment the user positioning performance. This framework forms a beneficial cycle where the CAM’s spatial resolution and the user positioning performance mutually improve each other. We validate the performance of the proposed framework in real-world experiments and the applied potency at different spatial scales. We highlight that this framework is a reliable and practical positioning solution that meets the requirements of ubiquitous high-precision positioning.

ABNet: An Aggregated Backbone Network Architecture for Fine Landcover Classification

High-precision landcover classification is a fundamental prerequisite for resource and environmental monitoring and land-use status surveys. Imbued with intricate spatial information and texture features, very high spatial resolution remote sensing images accentuate the divergence between features within the same category, thereby amplifying the complexity of landcover classification. Consequently, semantic segmentation models leveraging deep backbone networks have emerged as stalwarts in landcover classification tasks owing to their adeptness in feature representation. However, the classification efficacy of a solitary backbone network model fluctuates across diverse scenarios and datasets, posing a persistent challenge in the construction or selection of an appropriate backbone network for distinct classification tasks. To elevate the classification performance and bolster the generalization of semantic segmentation models, we propose a novel semantic segmentation network architecture, named the aggregated backbone network (ABNet), for the meticulous landcover classification. ABNet aggregates three prevailing backbone networks (ResNet, HRNet, and VoVNet), distinguished by significant structural disparities, using a same-stage fusion approach. Subsequently, it amalgamates these networks with the Deeplabv3+ head after integrating the convolutional block attention mechanism (CBAM). Notably, this amalgamation harmonizes distinct scale features extracted by the three backbone networks, thus enriching the model’s spatial contextual comprehension and expanding its receptive field, thereby facilitating more effective semantic feature extraction across different stages. The convolutional block attention mechanism primarily orchestrates channel adjustments and curtails redundant information within the aggregated feature layers. Ablation experiments demonstrate an enhancement of no less than 3% in the mean intersection over union (mIoU) of ABNet on both the LoveDA and GID15 datasets when compared with a single backbone network model. Furthermore, in contrast to seven classical or state-of-the-art models (UNet, FPN, PSPNet, DANet, CBNet, CCNet, and UPerNet), ABNet evinces excellent segmentation performance across the aforementioned datasets, underscoring the efficiency and robust generalization capabilities of the proposed approach.

A dosiomics model for prediction of radiation-induced acute skin toxicity in breast cancer patients: machine learning-based study for a closed bore linac

BackgroundRadiation induced acute skin toxicity (AST) is considered as a common side effect of breast radiation therapy. The goal of this study was to design dosiomics-based machine learning (ML) models for prediction of AST, to enable creating optimized treatment plans for high-risk individuals.MethodsDosiomics features extracted using Pyradiomics tool (v3.0.1), along with treatment plan-derived dose volume histograms (DVHs), and patient-specific treatment-related (PTR) data of breast cancer patients were used for modeling. Clinical scoring was done using the Common Terminology Criteria for Adverse Events (CTCAE) V4.0 criteria for skin-specific symptoms. The 52 breast cancer patients were grouped into AST 2 + (CTCAE ≥ 2) and AST 2 − (CTCAE < 2) toxicity grades to facilitate AST modeling. They were randomly divided into training (70%) and testing (30%) cohorts. Multiple prediction models were assessed through multivariate analysis, incorporating different combinations of feature groups (dosiomics, DVH, and PTR) individually and collectively. In total, seven unique combinations, along with seven classification algorithms, were considered after feature selection. The performance of each model was evaluated on the test group using the area under the receiver operating characteristic curve (AUC) and f1-score. Accuracy, precision, and recall of each model were also studied. Statistical analysis involved features differences between AST 2 − and AST 2 + groups and cutoff value calculations.ResultsResults showed that 44% of the patients developed AST 2 + after Tomotherapy. The dosiomics (DOS) model, developed using dosiomics features, exhibited a noteworthy improvement in AUC (up to 0.78), when spatial information is preserved in the dose distribution, compared to DVH features (up to 0.71). Furthermore, a baseline ML model created using only PTR features for comparison with DOS models showed the significance of dosiomics in early AST prediction. By employing the Extra Tree (ET) classifiers, the DOS + DVH + PTR model achieved a statistically significant improved performance in terms of AUC (0.83; 95% CI 0.71–0.90), accuracy (0.70), precision (0.74) and sensitivity (0.72) compared to other models.ConclusionsThis study confirmed the benefit of dosiomics-based ML in the prediction of AST. However, the combination of dosiomics, DVH, and PTR yields significant improvement in AST prediction. The results of this study provide the opportunity for timely interventions to prevent the occurrence of radiation induced AST.

G2D-Net: Efficient Dehazing with Second-Order Gated Units

Image dehazing aims to reconstruct potentially clear images from corresponding images corrupted by haze. With the rapid development of deep learning-related technologies, dehazing methods based on deep convolutional neural networks have gradually become mainstream. We note that existing dehazing methods often accompany an increase in computational overhead while improving the performance of dehazing. We propose a novel lightweight dehazing neural network to balance performance and efficiency: the g2D-Net. The g2D-Net borrows the design ideas of input-adaptive and long-range information interaction from Vision Transformers and introduces two kinds of convolutional blocks, i.e., the g2D Block and the FFT-g2D Block. Specifically, the g2D Block is a residual block with second-order gated units, which inherit the input-adaptive property of a gated unit and can realize the second-order interaction of spatial information. The FFT-g2D Block is a variant of the g2D Block, which efficiently extracts the global features of the feature maps through fast Fourier convolution and fuses them with local features. In addition, we employ the SK Fusion layer to improve the cascade fusion layer in a traditional U-Net, thus introducing the channel attention mechanism and dynamically fusing information from different paths. We conducted comparative experiments on five benchmark datasets, and the results demonstrate that the g2D-Net achieves impressive dehazing performance with relatively low complexity.

InViTMixup: plant disease classification using convolutional vision transformer with Mixup augmentation

ABSTRACT Computer vision-based research is carried out to enhance the crop yield with automation solutions. In Tamil Nādu, tomato cultivation is carried out in many districts, including Coimbatore, and its contribution to the Indian economy, i.e. GDP growth, is significant. This paper proposes InViT Mixup, a novel approach toward image classification of diseased tomato leaves. The effectiveness of convolutional neural network (CNN) in obtaining spatial information and the attention mechanism of vision transformers, along with Mixup data augmentation, are combined, and the model’s generalization in predicting the diseased tomato based on leaf symptoms is evaluated. The proposed convolutional transformer model improvised the classification results of tomato disease in terms of accuracy and training speed compared to pure CNN or transformer-based models. In the proposed work, 10 tomato leaf disease classes from the PlantVillage dataset are used. Top-1 accuracy of 93.5% and Top-5 accuracy of 99.7% are achieved.

Simulating bare soil evaporation for undisturbed soil cores—Using HYDRUS 3D simulation on X‐ray µCT determined soil macrostructures

AbstractEvaporation of soil water depends not only on climatic conditions, soil surface roughness, soil texture, and soil hydraulic properties but also on the soils’ macrostructure. Evaporation is characterized by water losses over time for a defined soil volume, where soils are assumed to be homogeneous in texture and structure. In this technical note, we investigated the potential and limitations of 3D modeling of evaporation processes on 250 cm3 soil cores with structural features ≥480 µm determined by X‐ray computed tomography. For this, we used isothermal Richards equation as the main governing equation, accounting also for isothermal vapor flow. We simulated two evaporation experiments with same soil texture but contrasting macrostructures, that is, the spatial arrangement of voxels classified as soil matrix and air‐filled voids, of a ploughed and non‐ploughed grassland soil with HYDRUS 3D. In both simulations, we fixed the potential evaporation rates to the experimental rates and evaluated simulation results with measured matric potential data at two depths (1.25 cm and 3.75 cm) continuously recorded at 10 min intervals. We could show that the simulations of bare soil evaporation were able to predict the tensiometer dynamics and water losses for the full experimental time of 7 days. The simulation provided unique spatial information of water content and flow velocities as a function of time, which are important when studying the effect of air‐filled macropores, macro‐connectivity of soil matrix, and water dynamics on soil evaporation.

Preface: ISPRS Technical Commission I Midterm Symposium on “Intelligent Sensing and Remote Sensing Application”

Abstract. The ISPRS Technical Commission I Midterm Symposium on "Intelligent Sensing and Remote Sensing Application" was held in Changsha, China, during May 13–17, 2024, aiming to provide a platform to share the latest researches, advanced technologies and application experience, to discuss the future development and to seek international cooperation in various forms. The Symposium has received 229 full paper and abstract s, among them 45 double-blind peer-reviewed full papers were published in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information, and 165 papers accepted through abstract review were published in the International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. These papers are mostly dedicated to topics of the 8 TC I Working Groups, 3 Inter-commission Working Groups, including Satellite Missions and Constellations for Remote Sensing, Mobile Mapping Technology, Multispectral, Hyperspectral and Thermal Sensors, LiDAR, Laser Altimetry and Sensor Integration, Microwave and InSAR Technology for Earth Observation, Orientation, Calibration and Validation of Sensors, Data Quality and Benchmark of Sensors, Multi-sensor Modelling and Cross-modality Fusion, Robotics for Mapping and Machine Intelligence, Autonomous Sensing Systems and their Applications, Digital Construction: Reality Capture, Automated Inspection and Integration to BIM, Point Cloud Generation and Processing, Artificial Intelligence Technology Related to Sensor Systems, Multi-sensor Remote Sensing Applications.. These papers presented the latest trends of sensor systems. The full papers and abstracts were reviewed by the members of the Symposium Scientific Committee comprised of Working Group officers and invited experts. We would like to take this opportunity to express our great gratitude to the Scientific Committee, Local Organizing Committee, Sponsors, Exhibitors and all those who have contributed to this successful Symposium. We also want to express our thanks to the authors for their excellent papers and presentations. Tang Xinming, Antonio Maria Garcia Tommaselli, Zhang Tao, Xie JunfengISPRS Technical Commission I on Sensor SystemsMay 2024, Changsha, China

Research on the Joint Construction of a National Multi-source and Multi-resolution image Checkpoint Database

Abstract. In the process of quality inspection of Remote sensing image data results, the reuse of spatial location information of multiple units, multiple projects and multiple sources can not only overcome the problems of long time to obtain control information, high cost and difficulty in obtaining some areas, but also the basis for achieving efficient and high-precision geometric correction. From the perspective of reusability of checkpoints and saving the cost of quality inspection of remote sensing images, this paper discusses the necessity of joint construction of multi-source and multi-resolution image checkpoint database. And put forward the construction principle and management objectives of checkpoint database. At last, this paper briefly introduces and prospects the application of the national multi-source and multi-resolution image checkpoint database.

Identification of Counterfeit Videos using Deep Learning Methodology

The rise of deep learning has ushered in a proliferation of deep fake videos, posing significant challenges to the credibility of visual content. Our research introduces a groundbreaking approach by merging Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) to enhance the accuracy of deepfake prediction. This unique integration, which has not been previously implemented, significantly boosts the model's capability to discern deepfakes. The synergy of CNNs and RNNs in our methodology represents an advancement, contributing to increased accuracy in detecting synthetic content. We leverage CNNs and RNNs for an efficient solution. First, we employ a Res-Next CNN to extract distinctive features from individual video frames, effectively encoding spatial information. These features are then used in the subsequent phase, where a LSTM-RNN models temporal dynamics within the videodata.The temporal aspect is crucial in differentiating deep fake videos due to subtle inconsistencies over time. The LSTM RNN processes the feature sequence, enabling the model to identify temporal patterns unique to deep fakes. This holistic approach, combining spatial and temporal analysis, enhances the model's ability to detect even highly convincing synthetic content. Our model is trained on a comprehensive dataset with rigorous evaluations, demonstrating competitive performance through standard metrics such as accuracy, precision. Practically, our model offers real- time video analysis, automatically identifying deep fake content and mitigating potential risks. Importantly, our approach is simple and robust, suitable for deployment across diverse scenarios. In summary, our research provides an effective solution to the critical issue of deepfake detection. By synergizing CNNs and LSTM-based RNNs, we offer a practical means to uphold the integrity of visual content in an era where digital information authenticity is paramount. Keywords— Deep Learning, CNN, RNN, Deepfake, LSTM, accuracy, precision, visual content, digital information

Towards Integration of IndoorGML and GDF for Robot Navigation in Warehouses

Abstract. With the development of the navigation technology, the outdoor navigation has made great progress, whereas the indoor navigation has some areas which is underdeveloped, insufficient to meet the rapidly increasing demands of people as well as the robotics. Even though, the advance in indoor navigation technology still has really brought a wide range of applications and a broad market, for instance, the flourishing intelligent warehouse system utilizes multi-robot operation which have the certain requirement for an accurate indoor navigation system. As for the indoor navigation, the OGC standard IndoorGML has been released and undergoing revision constantly. While the document really provides more advantageous support for the applications of Indoor Location-Based Services (LBS), in some aspects, especially the door-to-door navigation and the warehouse environment, it is not sufficiently adaptable, with still some room for improvement. IndoorGML is powerful for the common indoor scenarios like malls and offices, while as for carefully-arranged warehouse environment and other large-scale operation scenarios with multi-robots that is more similar to an ordered system, it is obviously insufficient. In this paper, we discuss about the potential to combination of IndoorGML and ITS standard ISO 20524 (GDF5.1), and extend the OGC standard indoorGML. We analyze the definition as well as function of related concepts, making some comparisons between these two standards. We conclude that these two standards are well-matched with vital potential to merge and unify the indoor and outdoor systems for spatial information.

A study of pedestrian wayfinding behavior based on desktop VR considering both spatial knowledge and visual information

Understanding pedestrian wayfinding behavior is crucial for traffic management and building design. The use of virtual reality technology presents an efficient approach for investigating pedestrian wayfinding behavior in large public spaces, offering numerous advantages for data collection. However, the impact of different scenario dimensions on pedestrian wayfinding behavior in large public spaces remains unclear. Additionally, the selection of virtual experiment scenario dimensions currently relies primarily on researchers’ experience and practical conditions, lacking sufficient evidence to support their rational. Another challenge is the limited focus on spatial knowledge’s effect on wayfinding behavior, with insufficient analysis of the utility of pedestrian visual information and a lack of precise methods to quantify visual field information accurately. This study addresses these gaps by incorporating spatial knowledge at multiple scales and pedestrian visual field information as influencing factors in the analysis of wayfinding behavior. Furthermore, it distinguishes between three-dimensional and two-dimensional scenarios to compare the impact of dimensional differences on pedestrian wayfinding behavior. By analyzing behavior data from non-immersive wayfinding experiments, this research employs statistical analysis methods and a deep learning framework to derive results regarding the factors influencing wayfinding behavior. The findings demonstrate that considering both spatial and visual field information effectively enhances the predictive ability of the wayfinding model. Additionally, dimensional differences significantly influence the pedestrian wayfinding process. These results offer empirical evidence to guide researchers in selecting experimental scenarios of pedestrian behavior and provide insights for public space layout, signage design, and improving pedestrian efficiency.

Integrating spatial and single-cell transcriptomics reveals tumor heterogeneity and intercellular networks in colorectal cancer

Single cell RNA sequencing (scRNA-seq), a powerful tool for studying the tumor microenvironment (TME), does not preserve/provide spatial information on tissue morphology and cellular interactions. To understand the crosstalk between diverse cellular components in proximity in the TME, we performed scRNA-seq coupled with spatial transcriptomic (ST) assay to profile 41,700 cells from three colorectal cancer (CRC) tumor-normal-blood pairs. Standalone scRNA-seq analyses revealed eight major cell populations, including B cells, T cells, Monocytes, NK cells, Epithelial cells, Fibroblasts, Mast cells, Endothelial cells. After the identification of malignant cells from epithelial cells, we observed seven subtypes of malignant cells that reflect heterogeneous status in tumor, including tumor_CAV1, tumor_ATF3_JUN | FOS, tumor_ZEB2, tumor_VIM, tumor_WSB1, tumor_LXN, and tumor_PGM1. By transferring the cellular annotations obtained by scRNA-seq to ST spots, we annotated four regions in a cryosection from CRC patients, including tumor, stroma, immune infiltration, and colon epithelium regions. Furthermore, we observed intensive intercellular interactions between stroma and tumor regions which were extremely proximal in the cryosection. In particular, one pair of ligands and receptors (C5AR1 and RPS19) was inferred to play key roles in the crosstalk of stroma and tumor regions. For the tumor region, a typical feature of TMSB4X-high expression was identified, which could be a potential marker of CRC. The stroma region was found to be characterized by VIM-high expression, suggesting it fostered a stromal niche in the TME. Collectively, single cell and spatial analysis in our study reveal the tumor heterogeneity and molecular interactions in CRC TME, which provides insights into the mechanisms underlying CRC progression and may contribute to the development of anticancer therapies targeting on non-tumor components, such as the extracellular matrix (ECM) in CRC. The typical genes we identified may facilitate to new molecular subtypes of CRC.

Deep Convolutional Network Based on Attention Mechanism for Matching Optical and SAR Images

Abstract. Complex geometric distortions and nonlinear radiation differences between optical and synthetic aperture radar (SAR) images present challenges for the matching of sufficient and evenly distributed corresponding points. To address this problem, this paper proposes a deep convolutional network based on an attention mechanism for matching optical and SAR images. In order to obtain robust feature points, we employ phase consistency instead of image intensity and gradient information for feature detection. A deep convolutional network (DCN) is designed to extract high-level semantic features between optical and SAR images, providing robustness to geometric distortion and nonlinear radiation changes. Notably, incorporating multiple inverted residual structures in the DCN facilitates efficient extraction of local and global features, promoting feature reuse, and reducing the loss of key features. Furthermore, a dense feature fusion module based on coordinate attention is designed, focusing on the spatial positional information of effective features, integrating key features into deep descriptors to enhance the robustness of deep descriptors to nonlinear radiometric differences. A coarse-to-fine strategy is then employed to enhance accuracy by eliminating mismatches. Experimental results demonstrate that the proposed network performs better than the manually designed descriptors-based methods and the stateof- the-art deep learning networks in both matching effectiveness and accuracy. Specifically, the number of matches achieved is approximately 2 times greater than that of other methods, with a 10% improvement in F-measure.

Stower-13: A Multi-View Inspection Image Dataset for the Automatic Classification and Naming of Tension Towers

In high-voltage transmission lines, the tension tower needs to withstand the tension load of the overhead power line for a long time, which is prone to damage, and it is an important part of the inspection in the circuit inspection. In the modern circuit inspection process, operation and maintenance personnel mostly use unmanned aerial vehicles (UAVs) to photograph various parts of the tension tower, obtain inspection images, and manually classify and name the massive inspection images, which is low in accuracy and efficiency. Based on the above problems, this paper collects a large number of real-life UAV inspection images of various parts of a tension tower, and proposes the Stower-13 inspection image dataset, which is used to train the classification model to achieve automatic classification and naming of inspection images. Based on this dataset, this paper also proposes an improved MobileViT model, in which the Scale-Correlated Pyramid Convolution Block Attention Block (SCPCbam) module is introduced, which adds the Convolution Block Attention Module (CBAM) to the four branches of the original Scale-Correlated Pyramid Convolution (SCPC) module, so as to strengthen the ability of image multi-scale information extraction and improve the classification accuracy. This paper discusses a number of experiments on the model, and the experimental results show that the dataset proposed in this paper helps the model to understand the feature information. At the same time, the improved MobileViT model has a strong ability to extract image spatial feature information, the classification accuracy is higher than that of other models of the same type, so it is able to cope with a wide range of problems that arise in the course of practice, and it meets the practical needs of automatically naming transmission line inspection images.

Building footprint extraction from aerial images using an edge-aware YOLO-v8 network

Abstract. Building footprint extraction is a critical indicator for assessing urban infrastructure, and extracting building footprints from remote sensing imagery can have significant practical applications. However, achieving rapid and accurate extraction of building footprints remains highly challenging, especially in scenarios with complex scenes, dense building distributions, and small targets. The instance segmentation models of the YOLO series offer strong real-time performance, reducing considerable time and effort in practical applications. Therefore, we propose building footprint extraction based on an enhance YOLO-v8 network. This study focuses on three enhancements to the YOLO-v8 network to improve extraction accuracy. Building upon the YOLO-v8 framework, we have incorporated the Feature Pyramid Network (FPN) module into feature maps at all scales to efficiently propagate high-level semantic information. Additionally, we introduce the Triple Feature Encoder (TFE) module, which integrates spatial detail information from feature maps at three different scales to enhance the network's ability to extract multi-scale information. Finally, we explore the integration of the Prewitt model, a conventional edge detection operator, to assist in extracting edge features in target regions of feature maps. This integration aims to reduce the jagged edges frequently seen in the outcomes of the original YOLO-v8. Furthermore, the Prewitt operator's noise suppression capability helps mitigate the influence of non-target areas in the feature maps. The proposed framework achieves an instance segmentation accuracy of mAP50 is 84.6% and mAP50:95 is 51.4% on public datasets, outperforming the original YOLO-v8 network.

Research on Sugarcane Recognition based on Joint Spatial and Spectral Information from Satellite-Based Hyperspectral Imagery

Abstract. The total amount of sugarcane planting in China ranks third in the world, and Guangxi is the largest sugarcane planting base in China. In order to help the Guangxi government and industry better understand the annual planting distribution and scale of sugarcane in the whole region, it is convenient to optimize the planting structure and improve the efficiency of resource utilization, so as to ensure the stable development of Guangxi sugar industry. Based on the satellite-based hyperspectral image data of ' Zhuhai No.1 ', this paper carries out sugarcane recognition and area extraction, which fills the application gap of satellite-based hyperspectral image data in extracting sugarcane area in China. A globally optimized extended random walk model was used to identify and extract sugarcane by combining the spatial-spectral information of hyperspectral imagery. Firstly, the Initial probability estimation is performed using the LOR classifier, and then use the data after MNF dimensionality reduction to construct a weighted graph, and finally the probability optimization and recognition are carried out based on the extended random walk model. The results show that the spatial-spectral joint method based on extended random walk can effectively identify sugarcane, and the sugarcane recognition accuracy of 2021 year image can reach 91.4%, the misrecognition rate is 2.8%; the sugarcane recognition accuracy of 2020 year image can reach 90.5 %, the misrecognition rate is 3.1%.

Research on power generation prediction of hydropower in river basin based on multi-head attention graph convolutional neural network

For the power generation prediction of traditional hydropower stations, most of them only use time series prediction and neglect to study the spatial topological relationship of hydropower stations in the river basin, so that it is difficult to fully explore the characteristic relationship of space power stations. In this paper, a research method for power generation prediction of hydropower in river basin hydropower stations based on multi-head attention map convolutional neural network is proposed. This method establishes a first-level node neighborhood feature map based on the spatial geographic distribution information of hydropower stations in the basin, and uses the method of graph convolution to carry out node feature mining and feature learning, so as to transform the power generation capacity evaluation problem of the hydropower station in the basin into the node prediction problem in the graph, which is different from the global normalization rule. the multi-head attention mechanism introduced further improves the information aggregation quality of the graph node, and uses the historical temperature, power generation, electricity price, unit status and other data of each hydropower station in the basin for training. The reasoning results show that the proposed method achieves higher accuracy than other schemes, and the power prediction method is conducive to the formulation of power plans of hydropower stations in the basin, and can also play a positive role in guiding the site selection of hydropower plants.