A Review of Spatial Enhancement of Hyperspectral Remote Sensing Imaging Techniques

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Journal Year: 2023, Volume and Issue: 16, P. 2275 - 2300

Published: Jan. 1, 2023

Remote sensing technology has undeniable importance in various industrial applications, such as mineral exploration, plant detection, defect detection aerospace and shipbuilding, optical gas imaging, to name a few. been continuously evolving, offering range of image modalities that can facilitate the aforementioned applications. One modality is Hyperspectral Imaging (HSI). Unlike Multispectral Images (MSI) natural images, HSI consist hundreds bands. Despite their high spectral resolution, suffer from low spatial resolution comparison MSI counterpart, which hinders utilization full potential. Therefore, enhancement, or Super Resolution (SR), classical problem gaining rapid attention over past two decades. The literature rich with SR algorithms enhance while preserving fidelity. This paper reviews discusses most important relevant this area research between 2002-2022, along frequently used datasets, sensors, quality metrics. Meta-analysis are drawn based on information, foundation summarizes state field way bridges present, identifies current gap it, recommends possible future directions.

Language: Английский

---

Single image super-resolution: a comprehensive review and recent insight

Frontiers of Computer Science, Journal Year: 2023, Volume and Issue: 18(1)

Published: Sept. 4, 2023

Language: Английский

---

Advancing paleontology: a survey on deep learning methodologies in fossil image analysis

Artificial Intelligence Review, Journal Year: 2025, Volume and Issue: 58(3)

Published: Jan. 6, 2025

Abstract Understanding ancient organisms and their interactions with paleoenvironments through the study of body fossils is a central tenet paleontology. Advances in digital image capture now allow for efficient accurate documentation, curation, interrogation fossil forms structures two three dimensions, extending from microfossils to larger specimens. Despite these developments, key processing analysis tasks, such as segmentation classification, still require significant user intervention, which can be labor-intensive subject human bias. Recent advances deep learning offer potential automate analysis, improving throughput limiting operator emergence within paleontology last decade, challenges scarcity diverse, high quality datasets complexity morphology necessitate further advancement will aided by adoption concepts other scientific domains. Here, we comprehensively review state-of-the-art based methodologies applied grouping studies on type nature task. Furthermore, analyze existing literature tabulate dataset information, neural network architecture type, results, provide textual summaries. Finally, discuss novel techniques data augmentation enhancements, combined advanced architectures, diffusion models, generative hybrid networks, transformers, graph improve analysis.

Language: Английский

---

Deep Learning for Downscaling Remote Sensing Images: Fusion and super-resolution

IEEE Geoscience and Remote Sensing Magazine, Journal Year: 2022, Volume and Issue: 10(3), P. 202 - 255

Published: June 2, 2022

The past few years have seen an accelerating integration of deep learning (DL) techniques into various remote sensing (RS) applications, highlighting their power to adapt and achieving unprecedented advancements. In the present review, we provide exhaustive exploration DL approaches proposed specifically for spatial downscaling RS imagery. A key contribution our work is presentation major architectural components models, metrics, data sets available this task as well construction a compact taxonomy navigating through methods. Furthermore, analyze limitations current modeling brief discussion on promising directions image enhancement, following paradigm general computer vision (CV) practitioners researchers source inspiration constructive insight.

Language: Английский

---

Mapping invasive alien plant species with very high spatial resolution and multi-date satellite imagery using object-based and machine learning techniques: A comparative study

GIScience & Remote Sensing, Journal Year: 2023, Volume and Issue: 60(1)

Published: March 24, 2023

Invasive alien plant species (IAPS) have negative impacts on ecosystems, including the loss of biodiversity and alteration ecosystem functions. The strategy for mitigating these requires knowledge species' spatial distribution level infestation. In situ inventories or aerial photo interpretation can be used to collect data but they are labor-intensive, time-consuming, incomplete, especially when dealing with large inaccessible areas. Remote sensing may an effective method mapping IAPS a better management strategy. Several studies using remote map focused single detection were conducted in relatively homogeneous natural environments, while other common, more heterogeneous such as urban areas, often invaded by multiple IAPS, posing challenges. main objective this study was develop three major observed agglomeration Quebec City (Canada), namely Japanese knotweed (Fallopia japonica); giant hogweed (Heracleum mantegazzianum); phragmites (Phragmites australis). Mono-date multi-date classification approaches WorldView-3 SPOT-7 satellite imagery, acquired summer 2020 autumn 2019, respectively. To estimate presence probability, object-based image analysis (OBIA) nonparametric classifiers Support Vector Machine (SVM), Random Forest (RF), Extreme Gradient Boosting (XGBoost) used. Overall, images produced best results, Kappa coefficient 0.85 overall accuracy 91% RF. For XGBoost, 0.81 89%, whereas 0.80 88% SVM classifier, Individual class performances based F1-score revealed that had highest maximum value (0.95), followed (0.91), (0.87). These results confirmed potential accurately simultaneously monitor environment approach. Although approach is limited reference availability, it provides new tools managers invasion control.

Language: Английский

---

Reconstruction of sub‐mm 3D pavement images using recursive generative adversarial network for faster texture measurement

Computer-Aided Civil and Infrastructure Engineering, Journal Year: 2023, Volume and Issue: 38(16), P. 2206 - 2224

Published: May 17, 2023

Abstract It is challenging to collect 3D pavement images with desired resolution for accurate texture measurement at driving speeds current devices, particularly in the longitudinal direction. This paper presents a novel superresolution technique recursive generative adversarial network, called Pavement Texture Super Resolution Generative Adversarial Network (PT‐SRGAN), reconstruct 0.1‐mm image from low‐resolution data faster measurement. With proposed pseudo‐Laplacian pyramid and an array of learning strategies, developed PT‐SRGAN reconstructs multiple upscaling factors Combined evaluation mask, method substantially superior other methods terms three metrics when comparing quality reconstructed against ground truth. The preliminary results indicate that enables collection up 24 mph sub‐mm

Language: Английский

---

Generative Adversarial Network Applications in Industry 4.0: A Review

International Journal of Computer Vision, Journal Year: 2024, Volume and Issue: 132(6), P. 2195 - 2254

Published: Jan. 12, 2024

Language: Английский

---

Waving Goodbye to Low-Res: A Diffusion-Wavelet Approach for Image Super-Resolution

2022 International Joint Conference on Neural Networks (IJCNN), Journal Year: 2024, Volume and Issue: 14, P. 1 - 8

Published: June 30, 2024

Language: Английский

---

A Review of Object Detection in Traffic Scenes Based on Deep Learning

Applied Mathematics and Nonlinear Sciences, Journal Year: 2024, Volume and Issue: 9(1)

Published: Jan. 1, 2024

Abstract At the current stage, rapid Development of autonomous driving has made object detection in traffic scenarios a vital research task. Object is most critical and challenging task computer vision. Deep learning, with its powerful feature extraction capabilities, found widespread applications safety, military, medical fields, recent years expanded into field transportation, achieving significant breakthroughs. This survey based on theory deep learning. It systematically summarizes status algorithms, compare characteristics, advantages disadvantages two types algorithms. With focus signs, vehicle detection, pedestrian it scenarios, highlighting strengths, limitations, applicable various methods. introduces techniques for optimizing commonly used datasets scene datasets, along evaluation criteria, performs comparative analysis performance learning Finally, concludes development trends algorithms providing directions intelligent transportation driving.

Language: Английский

---

Improving deep learning-based image super-resolution with residual learning and perceptual loss using SRGAN model

Soft Computing, Journal Year: 2023, Volume and Issue: 27(21), P. 16041 - 16057

Published: Sept. 7, 2023

Language: Английский

---