Sensors

Research

Jump to: Review

20 pages, 4940 KiB

Open AccessArticle

Estimation of Flood Inundation Area Using Soil Moisture Active Passive Fractional Water Data with an LSTM Model

by Rekzi D. Febrian, Wanyub Kim, Yangwon Lee, Jinsoo Kim and Minha Choi

Sensors 2025, 25(8), 2503; https://doi.org/10.3390/s25082503 - 16 Apr 2025

Viewed by 336

Abstract

Accurate flood monitoring and forecasting techniques are important and continue to be developed for improved disaster preparedness and mitigation. Flood estimation using satellite observations with deep learning algorithms is effective in detecting flood patterns and environmental relationships that may be overlooked by conventional [...] Read more.

Accurate flood monitoring and forecasting techniques are important and continue to be developed for improved disaster preparedness and mitigation. Flood estimation using satellite observations with deep learning algorithms is effective in detecting flood patterns and environmental relationships that may be overlooked by conventional methods. Soil Moisture Active Passive (SMAP) fractional water (FW) was used as a reference to estimate flood areas in a long short-term memory (LSTM) model using a combination of soil moisture information, rainfall forecasts, and floodplain topography. To perform flood modeling in LSTM, datasets with different spatial resolutions were resampled to 30 m spatial resolution using bicubic interpolation. The model’s efficacy was quantified by validating the LSTM-based flood inundation area with a water mask from Senti-nel-1 SAR images for regions with different topographic characteristics. The average area under the curve (AUC) value of the LSTM model was 0.93, indicating a high accuracy estimation of FW. The confusion matrix-derived metrics were used to validate the flood inundation area and had a high-performance accuracy of ~0.9. SMAP FW showed optimal performance in low-covered vegetation, seasonal water variations and flat regions. The estimates of flood inundation areas show the methodological promise of the proposed framework for improved disaster preparedness and resilience. Full article

(This article belongs to the Special Issue Deep Learning-Based Image and Signal Sensing and Processing: 2nd Edition)

► Show Figures

Figure 1

14 pages, 3664 KiB

Open AccessArticle

Construction of a Real-Time Detection for Floating Plastics in a Stream Using Video Cameras and Deep Learning

by Hankyu Lee, Seohyun Byeon, Jin Hwi Kim, Jae-Ki Shin and Yongeun Park

Sensors 2025, 25(7), 2225; https://doi.org/10.3390/s25072225 - 1 Apr 2025

Viewed by 387

Abstract

Rivers act as natural conduits for the transport of plastic debris from terrestrial sources to marine environments. Accurately quantifying plastic debris in surface waters is essential for comprehensive environmental impact assessments. However, research on the detection of plastic debris in surface waters remains [...] Read more.

Rivers act as natural conduits for the transport of plastic debris from terrestrial sources to marine environments. Accurately quantifying plastic debris in surface waters is essential for comprehensive environmental impact assessments. However, research on the detection of plastic debris in surface waters remains limited, particularly regarding real-time monitoring in natural environments following heavy rainfall events. This study aims to develop a real-time visual recognition model for floating plastic debris detection using deep learning with multi-class classification. A YOLOv8 algorithm was trained using field video data to automatically detect and count four types of floating plastic debris such as common plastics, plastic bottles, plastic film and vinyl, and fragmented plastics. Among the various YOLOv8 algorithms, YOLOv8-nano was selected to evaluate its practical applicability in real-time detection and portability. The results showed that the trained YOLOv8 model achieved an overall F1-score of 0.982 in the validation step and 0.980 in the testing step. Detection performance yielded mAP scores of 0.992 (IoU = 0.5) and 0.714 (IoU = 0.5:0.05:0.95). These findings demonstrate the model’s robust classification and detection capabilities, underscoring its potential for assessing plastic debris discharge and informing effective management strategies. Tracking and counting performance in an unknown video was limited, with only 6 of 32 observed debris items detected at the counting line. Improving tracking labels and refining data collection are recommended to enhance precision for applications in freshwater pollution monitoring. Full article

(This article belongs to the Special Issue Deep Learning-Based Image and Signal Sensing and Processing: 2nd Edition)

► Show Figures

Figure 1

19 pages, 3422 KiB

Open AccessArticle

Dual-Ascent-Inspired Transformer for Compressed Sensing

by Rui Lin, Yue Shen and Yu Chen

Sensors 2025, 25(7), 2157; https://doi.org/10.3390/s25072157 - 28 Mar 2025

Viewed by 249

Abstract

Deep learning has revolutionized image compressed sensing (CS) by enabling lightweight models that achieve high-quality reconstruction with low latency. However, most deep neural network-based CS models are pre-trained for specific compression ratios (CS ratios), limiting their flexibility compared to traditional iterative algorithms. To [...] Read more.

Deep learning has revolutionized image compressed sensing (CS) by enabling lightweight models that achieve high-quality reconstruction with low latency. However, most deep neural network-based CS models are pre-trained for specific compression ratios (CS ratios), limiting their flexibility compared to traditional iterative algorithms. To address this limitation, we propose the Dual-Ascent-Inspired Transformer (DAT), a novel architecture that maintains stable performance across different compression ratios with minimal training costs. DAT’s design incorporates the mathematical properties of the dual ascent method (DAM), leading to accelerated training convergence. The architecture features an innovative asymmetric primal–dual space at each iteration layer, enabling dimension-specific operations that balance reconstruction quality with computational efficiency. We also optimize the Cross Attention module through parameter sharing, effectively reducing its training complexity. Experimental results demonstrate DAT’s superior performance in two key aspects: First, during early-stage training (within 10 epochs), DAT consistently outperforms existing methods across multiple CS ratios (10%, 30%, and 50%). Notably, DAT achieves comparable PSNR to the ISTA-Net+ baseline within just one epoch, while competing methods require significantly more training time. Second, DAT exhibits enhanced robustness to variations in initial learning rates, as evidenced by loss function analysis during training. Full article

(This article belongs to the Special Issue Deep Learning-Based Image and Signal Sensing and Processing: 2nd Edition)

► Show Figures

Figure 1

13 pages, 1130 KiB

Open AccessArticle

Content-Based Histopathological Image Retrieval

by Camilo Nuñez-Fernández , Humberto Farias and Mauricio Solar

Sensors 2025, 25(5), 1350; https://doi.org/10.3390/s25051350 - 22 Feb 2025

Viewed by 479

Abstract

Feature descriptors in histopathological images are an important challenge for the implementation of Content-Based Image Retrieval (CBIR) systems, an essential tool to support pathologists. Deep learning models like Convolutional Neural Networks and Vision Transformers improve the extraction of these feature descriptors. These models [...] Read more.

Feature descriptors in histopathological images are an important challenge for the implementation of Content-Based Image Retrieval (CBIR) systems, an essential tool to support pathologists. Deep learning models like Convolutional Neural Networks and Vision Transformers improve the extraction of these feature descriptors. These models typically generate embeddings by leveraging deeper single-scale linear layers or advanced pooling layers. However, these embeddings, by focusing on local spatial details at a single scale, miss out on the richer spatial context from earlier layers. This gap suggests the development of methods that incorporate multi-scale information to enhance the depth and utility of feature descriptors in histopathological image analysis. In this work, we propose the Local–Global Feature Fusion Embedding Model. This proposal is composed of three elements: (1) a pre-trained backbone for feature extraction from multi-scales, (2) a neck branch for local–global feature fusion, and (3) a Generalized Mean (GeM)-based pooling head for feature descriptors. Based on our experiments, the model’s neck and head were trained on ImageNet-1k and PanNuke datasets employing the Sub-center ArcFace loss and compared with the state-of-the-art Kimia Path24C dataset for histopathological image retrieval, achieving a Recall@1 of 99.40% for test patches. Full article

(This article belongs to the Special Issue Deep Learning-Based Image and Signal Sensing and Processing: 2nd Edition)

► Show Figures

Figure 1

19 pages, 3507 KiB

Open AccessArticle

Cross-Modal Collaboration and Robust Feature Classifier for Open-Vocabulary 3D Object Detection

by Hengsong Liu and Tongle Duan

Sensors 2025, 25(2), 553; https://doi.org/10.3390/s25020553 - 19 Jan 2025

Cited by 1 | Viewed by 1076

Abstract

The multi-sensor fusion, such as LiDAR and camera-based 3D object detection, is a key technology in autonomous driving and robotics. However, traditional 3D detection models are limited to recognizing predefined categories and struggle with unknown or novel objects. Given the complexity of real-world [...] Read more.

The multi-sensor fusion, such as LiDAR and camera-based 3D object detection, is a key technology in autonomous driving and robotics. However, traditional 3D detection models are limited to recognizing predefined categories and struggle with unknown or novel objects. Given the complexity of real-world environments, research into open-vocabulary 3D object detection is essential. Therefore, this paper aims to address two key issues in this area: how to localize and classify novel objects. We propose Cross-modal Collaboration and Robust Feature Classifier to improve localization accuracy and classification robustness for novel objects. The Cross-modal Collaboration involves the collaborative localization between LiDAR and camera. In this approach, 2D images provide preliminary regions of interest for novel objects in the 3D point cloud, while the 3D point cloud offers more precise positional information to the 2D images. Through iterative updates between two modalities, the preliminary region and positional information are refined, achieving the accurate localization of novel objects. The Robust Feature Classifier aims to accurately classify novel objects. To prevent them from being misidentified as background or other incorrect categories, this method maps the semantic vectors of new categories into multiple sets of visual features distinguished from the background. And it clusters these visual features based on each individual semantic vector to maintain inter-class separability. Our method achieves state-of-the-art performance on various scenarios and datasets. Full article

(This article belongs to the Special Issue Deep Learning-Based Image and Signal Sensing and Processing: 2nd Edition)

► Show Figures

Figure 1

17 pages, 5226 KiB

Open AccessArticle

Adaptive Memory-Augmented Unfolding Network for Compressed Sensing

by Mingkun Feng, Dongcan Ning and Shengying Yang

Sensors 2024, 24(24), 8085; https://doi.org/10.3390/s24248085 - 18 Dec 2024

Viewed by 607

Abstract

Deep unfolding networks (DUNs) have attracted growing attention in compressed sensing (CS) due to their good interpretability and high performance. However, many DUNs often improve the reconstruction effect at the price of a large number of parameters and have the problem of feature [...] Read more.

Deep unfolding networks (DUNs) have attracted growing attention in compressed sensing (CS) due to their good interpretability and high performance. However, many DUNs often improve the reconstruction effect at the price of a large number of parameters and have the problem of feature information loss during iteration. This paper proposes a novel adaptive memory-augmented unfolding network for compressed sensing (AMAUN-CS). Concretely, without loss of interpretability, we integrate an adaptive content-aware strategy into the gradient descent step of the proximal gradient descent (PGD) algorithm, driving it to adaptively capture the adequate features. In addition, we extended AMAUN-CS based on the memory storage mechanism of the human brain and propose AMAUN-CS⁺ to develop the dependency of deep information across cascading stages. The experimental results show that the AMAUN-CS model surpasses other advanced methods on various public benchmark datasets while having lower complexity in training. Full article

(This article belongs to the Special Issue Deep Learning-Based Image and Signal Sensing and Processing: 2nd Edition)

► Show Figures

Figure 1

21 pages, 46218 KiB

Open AccessArticle

Lightweight Single Image Super-Resolution via Efficient Mixture of Transformers and Convolutional Networks

by Luyang Xiao, Xiangyu Liao and Chao Ren

Sensors 2024, 24(16), 5098; https://doi.org/10.3390/s24165098 - 6 Aug 2024

Cited by 1 | Viewed by 1548

Abstract

In this paper, we propose a Local Global Union Network (LGUN), which effectively combines the strengths of Transformers and Convolutional Networks to develop a lightweight and high-performance network suitable for Single Image Super-Resolution (SISR). Specifically, we make use of the advantages of Transformers [...] Read more.

In this paper, we propose a Local Global Union Network (LGUN), which effectively combines the strengths of Transformers and Convolutional Networks to develop a lightweight and high-performance network suitable for Single Image Super-Resolution (SISR). Specifically, we make use of the advantages of Transformers to provide input-adaptation weighting and global context interaction. We also make use of the advantages of Convolutional Networks to include spatial inductive biases and local connectivity. In the shallow layer, the local spatial information is encoded by Multi-order Local Hierarchical Attention (MLHA). In the deeper layer, we utilize Dynamic Global Sparse Attention (DGSA), which is based on the Multi-stage Token Selection (MTS) strategy to model global context dependencies. Moreover, we also conduct extensive experiments on both natural and satellite datasets, acquired through optical and satellite sensors, respectively, demonstrating that LGUN outperforms existing methods. Full article

(This article belongs to the Special Issue Deep Learning-Based Image and Signal Sensing and Processing: 2nd Edition)

► Show Figures

Figure 1

Review

Jump to: Research

46 pages, 615 KiB

Open AccessReview

A Comprehensive Survey of Deep Learning Approaches in Image Processing

by Maria Trigka and Elias Dritsas

Sensors 2025, 25(2), 531; https://doi.org/10.3390/s25020531 - 17 Jan 2025

Cited by 3 | Viewed by 4668

Abstract

The integration of deep learning (DL) into image processing has driven transformative advancements, enabling capabilities far beyond the reach of traditional methodologies. This survey offers an in-depth exploration of the DL approaches that have redefined image processing, tracing their evolution from early innovations [...] Read more.

The integration of deep learning (DL) into image processing has driven transformative advancements, enabling capabilities far beyond the reach of traditional methodologies. This survey offers an in-depth exploration of the DL approaches that have redefined image processing, tracing their evolution from early innovations to the latest state-of-the-art developments. It also analyzes the progression of architectural designs and learning paradigms that have significantly enhanced the ability to process and interpret complex visual data. Key advancements, such as techniques improving model efficiency, generalization, and robustness, are examined, showcasing DL’s ability to address increasingly sophisticated image-processing tasks across diverse domains. Metrics used for rigorous model evaluation are also discussed, underscoring the importance of performance assessment in varied application contexts. The impact of DL in image processing is highlighted through its ability to tackle complex challenges and generate actionable insights. Finally, this survey identifies potential future directions, including the integration of emerging technologies like quantum computing and neuromorphic architectures for enhanced efficiency and federated learning for privacy-preserving training. Additionally, it highlights the potential of combining DL with emerging technologies such as edge computing and explainable artificial intelligence (AI) to address scalability and interpretability challenges. These advancements are positioned to further extend the capabilities and applications of DL, driving innovation in image processing. Full article

(This article belongs to the Special Issue Deep Learning-Based Image and Signal Sensing and Processing: 2nd Edition)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Deep Learning-Based Image and Signal Sensing and Processing: 2nd Edition

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Related Special Issue

Published Papers (8 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI