Semantic Segmentation of Unmanned Aerial Vehicle Remote Sensing Images Using SegFormer

Communications in computer and information science, Journal Year: 2025, Volume and Issue: unknown, P. 108 - 122

Published: Jan. 1, 2025

Language: Английский

---

CTSeg: CNN and ViT collaborated segmentation framework for efficient land-use/land-cover mapping with high-resolution remote sensing images

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2025, Volume and Issue: 139, P. 104546 - 104546

Published: April 28, 2025

Language: Английский

---

The Identification of Exposed Beachrocks on South China Sea Islands Based on UAV Images

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(9), P. 1647 - 1647

Published: May 7, 2025

Beachrocks are common coastal sedimentary rocks in tropical and subtropical seas. They widely spread especially islands areas. These important for island geological evolution research. Research on beachrocks aids protecting ecosystems enhances islands’ ability to prevent mitigate damage from natural disasters. This study uses unmanned aerial vehicle (UAV) images the U-Net model based deep learning identify beachrocks. To enhance identification accuracy, efficient channel attention (ECA) mechanism was integrated, leading improvements of 0.49% overall 1.41% precision, 0.97% recall, 1.10% F1-score, 2.09% intersection over union (IoU) compared baseline model. The final results demonstrate that effectively identified beachrocks, achieving 97.47% 93.27% 94.73% 93.95% 88.65% IoU. offers a valuable tool research supports development large-scale conservation efforts.

Language: Английский

---

LandslideSegNet: an effective deep learning network for landslide segmentation using remote sensing imagery

Earth Science Informatics, Journal Year: 2024, Volume and Issue: 17(5), P. 3963 - 3977

Published: Aug. 9, 2024

Abstract In recent years, remote sensing technologies have played a crucial role in the detection and management of natural disasters. this context, deep learning models are great importance for early disasters such as landslides. Landslide segmentation is fundamental tool development geographic information systems, disaster risk mitigation strategies. study, we propose new semantic model called LandslideSegNet to improve intervention capabilities potential landslide scenarios. incorporates an encoder-decoder architecture that integrates local contextual information, advanced residual blocks Efficient Hybrid Attentional Atrous Convolution. Thanks structure, able extract high-resolution feature maps from imagery, accurately delineate areas minimize loss information. The developed has shown significantly higher accuracy rates with fewer parameters compared existing image models. was trained tested using Landslide4Sense dataset specially prepared detection. achieved 97.60% 73.65% mean Intersection over Union 73.65 on dataset, demonstrating its efficiency. These results indicate usability related applications.

Language: Английский

---

Research Advances in Deep Learning for Image Semantic Segmentation Techniques

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 175715 - 175741

Published: Jan. 1, 2024

Language: Английский

---

Gaussian-based R-CNN with large selective kernel for rotated object detection in remote sensing images

Neurocomputing, Journal Year: 2024, Volume and Issue: 620, P. 129248 - 129248

Published: Dec. 27, 2024

Language: Английский

---

Path Planning of UAV Formations Based on Semantic Maps

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(16), P. 3096 - 3096

Published: Aug. 22, 2024

This paper primarily studies the path planning problem for UAV formations guided by semantic map information. Our aim is to integrate prior information from maps provide initial on task points formations, thereby formation paths that meet practical requirements. Firstly, a segmentation network model based multi-scale feature extraction and fusion employed obtain aerial containing environmental Secondly, maps, three-point optimization optimal trajectory established, general formula calculating heading angle proposed approximately decouple triangular equation of trajectory. For large-scale points, an improved fuzzy clustering algorithm classify distance constraints clusters, reducing computational scale single samples without changing sample size improving allocation efficiency model. Experimental data show cluster method using angle-optimized achieves 8.6% improvement in total flight range compared other algorithms 17.4% reduction number large-angle turns.

Language: Английский

---

Geocomplexity Statistical Indicator to Enhance Multiclass Semantic Segmentation of Remotely Sensed Data with Less Sampling Bias

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(11), P. 1987 - 1987

Published: May 31, 2024

Challenges in enhancing the multiclass segmentation of remotely sensed data include expensive and scarce labeled samples, complex geo-surface scenes, resulting biases. The intricate nature geographical surfaces, comprising varying elements features, introduces significant complexity to task segmentation. limited label used train models may exhibit biases due imbalances or inadequate representation certain surface types features. For applications like land use/cover monitoring, assumption evenly distributed simple random sampling be not satisfied spatial stratified heterogeneity, introducing that can adversely impact model’s ability generalize effectively across diverse areas. We introduced two statistical indicators encode geo-features under scenes designed a corresponding optimal scheme select representative samples reduce bias during machine learning model training, especially deep models. results scores showed entropy-based gray-based detected from scenes: indicator was sensitive boundaries different classes contours objects, while Moran’s I had better performance identifying structure information objects remote sensing images. According scores, methods appropriately adapted distribution training geo-context enhanced their representativeness relative population. single-score method achieved highest improvement DeepLab-V3 (increasing pixel accuracy by 0.3% MIoU 5.5%), multi-score SegFormer ACC 0.2% 2.4%). These findings carry implications for quantifying hence enhance semantic high-resolution images with less bias.

Language: Английский

---

LOD2-Level+ Low-Rise Building Model Extraction Method for Oblique Photography Data Using U-NET and a Multi-Decision RANSAC Segmentation Algorithm

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(13), P. 2404 - 2404

Published: June 30, 2024

Oblique photography is a regional digital surface model generation technique that can be widely used for building 3D construction. However, due to the lack of geometric and semantic information about building, these models make it difficult differentiate more detailed components in such as roofs balconies. This paper proposes deep learning-based method (U-NET) constructing low-rise buildings address issues. The ensures complete conforms LOD2 level. First, orthophotos are perform extraction based on U-NET, then contour optimization main direction center gravity obtain regular contour. Second, pure point cloud representing single extracted from whole scene acquired Finally, multi-decision RANSAC algorithm segment detail construct triangular mesh components, followed by fusion splicing achieve monolithic components. presents experimental evidence 90.3% success rate resulting contains which contain information.

Language: Английский

---

A Mission Planning Method for Long-Endurance Unmanned Aerial Vehicles: Integrating Heterogeneous Ground Control Resource Allocation

Drones, Journal Year: 2024, Volume and Issue: 8(8), P. 385 - 385

Published: Aug. 8, 2024

Long-endurance unmanned aerial vehicles (LE-UAVs) are extensively used due to their vast coverage and significant payload capacities. However, limited autonomous intelligence necessitates the intervention of ground control resources (GCRs), which include one or more operators, during mission execution. The performance these missions is notably affected by varying effectiveness different GCRs fatigue levels. Current research on multi-UAV planning inadequately addresses critical factors. To tackle this practical issue, we present an integrated optimization problem for multi-LE-UAV combined with heterogeneous GCR allocation. This extends traditional cooperative incorporating allocation decisions. coupling decisions increases dimensionality decision space, rendering complex. By analyzing problem’s characteristics, develop a mixed-integer linear programming model. effectively solve problem, propose bilevel algorithm based hybrid genetic framework. Numerical experiments demonstrate that our proposed solves outperforming advanced toolkit CPLEX. Remarkably, larger-scale instances, achieves superior solutions within 10 s compared CPLEX’s 2 h runtime.

Language: Английский

---