Research

14 pages, 458 KiB

Open AccessArticle

Violent Video Recognition by Using Sequential Image Collage

by Yueh-Shen Tu, Yu-Shian Shen, Yuk Yii Chan, Lei Wang and Jenhui Chen

Sensors 2024, 24(6), 1844; https://doi.org/10.3390/s24061844 - 13 Mar 2024

Viewed by 468

Identifying violent activities is important for ensuring the safety of society. Although the Transformer model contributes significantly to the field of behavior recognition, it often requires a substantial volume of data to perform well. Since existing datasets on violent behavior are currently lacking, [...] Read more.

Identifying violent activities is important for ensuring the safety of society. Although the Transformer model contributes significantly to the field of behavior recognition, it often requires a substantial volume of data to perform well. Since existing datasets on violent behavior are currently lacking, it will be a challenge for Transformers to identify violent behavior with insufficient datasets. Additionally, Transformers are known to be computationally heavy and can sometimes overlook temporal features. To overcome these issues, an architecture named MLP-Mixer can be used to achieve comparable results with a smaller dataset. In this research, a special type of dataset to be fed into the MLP-Mixer called a sequential image collage (SIC) is proposed. This dataset is created by aggregating frames of video clips into image collages sequentially for the model to better understand the temporal features of violent behavior in videos. Three different public datasets, namely, the dataset of National Hockey League hockey fights, the dataset of smart-city CCTV violence detection, and the dataset of real-life violence situations were used to train the model. The results of the experiments proved that the model trained using the proposed SIC is capable of achieving high performance in violent behavior recognition with fewer parameters and FLOPs needed compared to other state-of-the-art models. Full article

(This article belongs to the Special Issue Data Fusion and Artificial Intelligence Applications in Remote Sensing)

► Show Figures

Figure 1

19 pages, 61147 KiB

Open AccessArticle

Assessing the Efficacy of Pixel-Level Fusion Techniques for Ultra-High-Resolution Imagery: A Case Study of BJ-3A

by Yueyang Wang, Zhihui Mao, Zhining Xin, Xinyi Liu, Zhangmai Li, Yakun Dong and Lei Deng

Sensors 2024, 24(5), 1410; https://doi.org/10.3390/s24051410 - 22 Feb 2024

Viewed by 422

Abstract

Beijing Satellite 3 is a high-performance optical remote sensing satellite with a spatial resolution of 0.3–0.5 m. It can provide timely and independent ultra-high-resolution spatial big data and comprehensive spatial information application services. At present, there is no relevant research on the fusion [...] Read more.

Beijing Satellite 3 is a high-performance optical remote sensing satellite with a spatial resolution of 0.3–0.5 m. It can provide timely and independent ultra-high-resolution spatial big data and comprehensive spatial information application services. At present, there is no relevant research on the fusion method of BJ-3A satellite images. In many applications, high-resolution panchromatic images alone are insufficient. Therefore, it is necessary to fuse them with multispectral images that contain spectral color information. Currently, there is a lack of research on the fusion method of BJ-3A satellite images. This article explores six traditional pixel-level fusion methods (HPF, HCS, wavelet, modified-IHS, PC, and Brovey) for fusing the panchromatic image and multispectral image of the BJ-3A satellite. The fusion results were analyzed qualitatively from two aspects: spatial detail enhancement capability and spectral fidelity. Five indicators, namely mean, standard deviation, entropy, correlation coefficient, and average gradient, were used for quantitative analysis. Finally, the fusion results were comprehensively evaluated from three aspects: spectral curves of ground objects, absolute error figure, and object-oriented classification effects. The findings of the research suggest that the fusion method known as HPF is the optimum and appropriate technique for fusing panchromatic and multispectral images obtained from BJ-3A. These results can be utilized as a guide for the implementation of BJ-3A panchromatic and multispectral data fusion in real-world scenarios. Full article

(This article belongs to the Special Issue Data Fusion and Artificial Intelligence Applications in Remote Sensing)

► Show Figures

Figure 1

23 pages, 14748 KiB

Open AccessArticle

A Building Extraction Method for High-Resolution Remote Sensing Images with Multiple Attentions and Parallel Encoders Combining Enhanced Spectral Information

by Zhaojun Pang, Rongming Hu, Wu Zhu, Renyi Zhu, Yuxin Liao and Xiying Han

Sensors 2024, 24(3), 1006; https://doi.org/10.3390/s24031006 - 04 Feb 2024

Viewed by 605

Abstract

Accurately extracting pixel-level buildings from high-resolution remote sensing images is significant for various geographical information applications. Influenced by different natural, cultural, and social development levels, buildings may vary in shape and distribution, making it difficult for the network to maintain a stable segmentation [...] Read more.

Accurately extracting pixel-level buildings from high-resolution remote sensing images is significant for various geographical information applications. Influenced by different natural, cultural, and social development levels, buildings may vary in shape and distribution, making it difficult for the network to maintain a stable segmentation effect of buildings in different areas of the image. In addition, the complex spectra of features in remote sensing images can affect the extracted details of multi-scale buildings in different ways. To this end, this study selects parts of Xi’an City, Shaanxi Province, China, as the study area. A parallel encoded building extraction network (MARS-Net) incorporating multiple attention mechanisms is proposed. MARS-Net builds its parallel encoder through DCNN and transformer to take advantage of their extraction of local and global features. According to the different depth positions of the network, coordinate attention (CA) and convolutional block attention module (CBAM) are introduced to bridge the encoder and decoder to retain richer spatial and semantic information during the encoding process, and adding the dense atrous spatial pyramid pooling (DenseASPP) captures multi-scale contextual information during the upsampling of the layers of the decoder. In addition, a spectral information enhancement module (SIEM) is designed in this study. SIEM further enhances building segmentation by blending and enhancing multi-band building information with relationships between bands. The experimental results show that MARS-Net performs better extraction results and obtains more effective enhancement after adding SIEM. The IoU on the self-built Xi’an and WHU building datasets are 87.53% and 89.62%, respectively, while the respective F1 scores are 93.34% and 94.52%. Full article

(This article belongs to the Special Issue Data Fusion and Artificial Intelligence Applications in Remote Sensing)

► Show Figures

Figure 1

18 pages, 15595 KiB

Open AccessArticle

Joint Classification of Hyperspectral Images and LiDAR Data Based on Dual-Branch Transformer

by Qingyan Wang, Binbin Zhou, Junping Zhang, Jinbao Xie and Yujing Wang

Sensors 2024, 24(3), 867; https://doi.org/10.3390/s24030867 - 29 Jan 2024

Viewed by 632

Abstract

In the face of complex scenarios, the information insufficiency of classification tasks dominated by a single modality has led to a bottleneck in classification performance. The joint application of multimodal remote sensing data for surface observation tasks has garnered widespread attention. However, issues [...] Read more.

In the face of complex scenarios, the information insufficiency of classification tasks dominated by a single modality has led to a bottleneck in classification performance. The joint application of multimodal remote sensing data for surface observation tasks has garnered widespread attention. However, issues such as sample differences between modalities and the lack of correlation in physical features have limited the performance of classification tasks. Establishing effective interaction between multimodal data has become another significant challenge. To fully integrate heterogeneous information from multiple modalities and enhance classification performance, this paper proposes a dual-branch cross-Transformer feature fusion network aimed at joint land cover classification of hyperspectral imagery (HSI) and Light Detection and Ranging (LiDAR) data. The core idea is to leverage the potential of convolutional operators to represent spatial features, combined with the advantages of the Transformer architecture in learning remote dependencies. The framework employs an improved self-attention mechanism to aggregate features within each modality, highlighting the spectral information of HSI and the spatial (elevation) information of LiDAR. The feature fusion module based on cross-attention integrates deep features from two modalities, achieving complementary information through cross-modal attention. The classification task is performed using jointly obtained spectral and spatial features. Experiments were conducted on three multi-source remote sensing classification datasets, demonstrating the effectiveness of the proposed model compared to existing methods. Full article

(This article belongs to the Special Issue Data Fusion and Artificial Intelligence Applications in Remote Sensing)

► Show Figures

Figure 1

23 pages, 14400 KiB

Open AccessArticle

A Dual-Branch Fusion Network Based on Reconstructed Transformer for Building Extraction in Remote Sensing Imagery

by Yitong Wang, Shumin Wang and Aixia Dou

Sensors 2024, 24(2), 365; https://doi.org/10.3390/s24020365 - 07 Jan 2024

Cited by 1 | Viewed by 981

Abstract

Automatic extraction of building contours from high-resolution images is of great significance in the fields of urban planning, demographics, and disaster assessment. Network models based on convolutional neural network (CNN) and transformer technology have been widely used for semantic segmentation of buildings from [...] Read more.

Automatic extraction of building contours from high-resolution images is of great significance in the fields of urban planning, demographics, and disaster assessment. Network models based on convolutional neural network (CNN) and transformer technology have been widely used for semantic segmentation of buildings from high resolution remote sensing images (HRSI). However, the fixed geometric structure and the local receptive field of the convolutional kernel are not good at global feature extraction, and the transformer technique with self-attention mechanism introduces computational redundancies and extracts local feature details poorly in the process of modeling the global contextual information. In this paper, a dual-branch fused reconstructive transformer network, DFRTNet, is proposed for efficient and accurate building extraction. In the encoder, the traditional transformer is reconfigured by designing the local and global feature extraction module (LGFE); the branch of global feature extraction (GFE) performs dynamic range attention (DRA) based on the idea of top-k attention for extracting global features; furthermore, the branch of local feature extraction (LFE) is used to obtain fine-grained features. The multilayer perceptron (MLP) is employed to efficiently fuse the local and global features. In the decoder, a simple channel attention module (CAM) is used in the up-sampling part to enhance channel dimension features. Our network achieved the best segmentation accuracy on both the WHU and Massachusetts building datasets when compared to other mainstream and state-of-the-art methods. Full article

(This article belongs to the Special Issue Data Fusion and Artificial Intelligence Applications in Remote Sensing)

► Show Figures

Figure 1

23 pages, 7318 KiB

Open AccessArticle

A Triplet Network Fusing Optical and SAR Images for Colored Steel Building Extraction

by Xiaoyong Zhang, Shuo Yang, Xuan Yang, Cong Li and Yue Xu

Sensors 2024, 24(1), 89; https://doi.org/10.3390/s24010089 - 23 Dec 2023

Viewed by 704

Abstract

The identification of colored steel buildings in images is crucial for managing the construction sector, environmental protection, and sustainable urban development. Current deep learning methods for optical remote sensing images often encounter challenges such as confusion between the roof color or shape of [...] Read more.

The identification of colored steel buildings in images is crucial for managing the construction sector, environmental protection, and sustainable urban development. Current deep learning methods for optical remote sensing images often encounter challenges such as confusion between the roof color or shape of regular buildings and colored steel structures. Additionally, common semantic segmentation networks exhibit poor generalization and inadequate boundary regularization when extracting colored steel buildings. To overcome these limitations, we utilized the metal detection and differentiation capabilities inherent in synthetic aperture radar (SAR) data to develop a network that integrates optical and SAR data. This network, employing a triple-input structure, effectively captures the unique features of colored steel buildings. We designed a multimodal hybrid attention module in the network that discerns the varying importance of each data source depending on the context. Additionally, a boundary refinement (BR) module was introduced to extract the boundaries of the colored steel buildings in a more regular manner, and a deep supervision strategy was implemented to improve the performance of the network in the colored steel building extraction task. A BR module and deep supervision strategy were also implemented to sharpen the extraction of building boundaries, thereby enhancing the network’s accuracy and adaptability. The results indicate that, compared to mainstream semantic segmentation, this method effectively enhances the precision of colored steel building detection, achieving an accuracy rate of 83.19%. This improvement marks a significant advancement in monitoring illegal constructions and supporting the sustainable development of the Beijing–Tianjin–Hebei metropolitan region. Full article

(This article belongs to the Special Issue Data Fusion and Artificial Intelligence Applications in Remote Sensing)

► Show Figures

Figure 1

16 pages, 11253 KiB

Open AccessArticle

Multisensor and Multiscale Data Integration Method of TLS and GPR for Three-Dimensional Detailed Virtual Reconstruction

by Di Zhang, Dinghan Jia, Lili Ren, Jiacun Li, Yan Lu and Haiwei Xu

Sensors 2023, 23(24), 9826; https://doi.org/10.3390/s23249826 - 14 Dec 2023

Viewed by 863

Abstract

Integrated TLS and GPR data can provide multisensor and multiscale spatial data for the comprehensive identification and analysis of surficial and subsurface information, but a reliable systematic methodology associated with data integration of TLS and GPR is still scarce. The aim of this [...] Read more.

Integrated TLS and GPR data can provide multisensor and multiscale spatial data for the comprehensive identification and analysis of surficial and subsurface information, but a reliable systematic methodology associated with data integration of TLS and GPR is still scarce. The aim of this research is to develop a methodology for the data integration of TLS and GPR for detailed, three-dimensional (3D) virtual reconstruction. GPR data and high-precision geographical coordinates at the centimeter level were simultaneously gathered using the GPR system and the Global Navigation Satellite System (GNSS) signal receiver. A time synchronization algorithm was proposed to combine each trace of the GPR data with its position information. In view of the improved propagation model of electromagnetic waves, the GPR data were transformed into dense point clouds in the geodetic coordinate system. Finally, the TLS-based and GPR-derived point clouds were merged into a single point cloud dataset using coordinate transformation. In addition, TLS and GPR (250 MHz and 500 MHz antenna) surveys were conducted in the Litang fault to assess the feasibility and overall accuracy of the proposed methodology. The 3D realistic surface and subsurface geometry of the fault scarp were displayed using the integration data of TLS and GPR. A total of 40 common points between the TLS-based and GPR-derived point clouds were implemented to assess the data fusion accuracy. The difference values in the x and y directions were relatively stable within 2 cm, while the difference values in the z direction had an abrupt fluctuation and the maximum values could be up to 5 cm. The standard deviations (STD) of the common points between the TLS-based and GPR-derived point clouds were 0.9 cm, 0.8 cm, and 2.9 cm. Based on the difference values and the STD in the x, y, and z directions, the field experimental results demonstrate that the GPR-derived point clouds exhibit good consistency with the TLS-based point clouds. Furthermore, this study offers a good future prospect for the integration method of TLS and GPR for comprehensive interpretation and analysis of the surficial and subsurface information in many fields, such as archaeology, urban infrastructure detection, geological investigation, and other fields. Full article

(This article belongs to the Special Issue Data Fusion and Artificial Intelligence Applications in Remote Sensing)

► Show Figures

Figure 1

21 pages, 4064 KiB

Open AccessArticle

Spatially Explicit Modeling of Anthropogenic Heat Intensity in Beijing Center Area: An Investigation of Driving Factors with Urban Spatial Forms

by Meizi Yang, Shisong Cao and Dayu Zhang

Sensors 2023, 23(17), 7608; https://doi.org/10.3390/s23177608 - 01 Sep 2023

Cited by 1 | Viewed by 632

Abstract

The escalation of anthropogenic heat emissions poses a significant threat to the urban thermal environment as cities continue to develop. However, the impact of urban spatial form on anthropogenic heat flux (AHF) in different urban functional zones (UFZ) has received limited attention. In [...] Read more.

The escalation of anthropogenic heat emissions poses a significant threat to the urban thermal environment as cities continue to develop. However, the impact of urban spatial form on anthropogenic heat flux (AHF) in different urban functional zones (UFZ) has received limited attention. In this study, we employed the energy inventory method and remotely sensed technology to estimate AHF in Beijing’s central area and utilized the random forest algorithm for UFZ classification. Subsequently, linear fitting models were developed to analyze the relationship between AHF and urban spatial form indicators across diverse UFZ. The results show that the overall accuracy of the classification was determined to be 87.2%, with a Kappa coefficient of 0.8377, indicating a high level of agreement with the actual situation. The business/commercial zone exhibited the highest average AHF value of 33.13 W m⁻² and the maximum AHF value of 338.07 W m⁻² among the six land functional zones, indicating that business and commercial areas are the primary sources of anthropogenic heat emissions. The findings reveal substantial variations in the influence of urban spatial form on AHF across different UFZ. Consequently, distinct spatial form control requirements and tailored design strategies are essential for each UFZ. This research highlights the significance of considering urban spatial form in mitigating anthropogenic heat emissions and emphasizes the need for customized planning and renewal approaches in diverse UFZ. Full article

(This article belongs to the Special Issue Data Fusion and Artificial Intelligence Applications in Remote Sensing)

► Show Figures

Figure 1

19 pages, 1709 KiB

Open AccessArticle

Pansharpening Model of Transferable Remote Sensing Images Based on Feature Fusion and Attention Modules

by Hui Liu, Liangfeng Deng, Yibo Dou, Xiwu Zhong and Yurong Qian

Sensors 2023, 23(6), 3275; https://doi.org/10.3390/s23063275 - 20 Mar 2023

Cited by 2 | Viewed by 1403

Abstract

The purpose of the panchromatic sharpening of remote sensing images is to generate high-resolution multispectral images through software technology without increasing economic expenditure. The specific method is to fuse the spatial information of a high-resolution panchromatic image and the spectral information of a [...] Read more.

The purpose of the panchromatic sharpening of remote sensing images is to generate high-resolution multispectral images through software technology without increasing economic expenditure. The specific method is to fuse the spatial information of a high-resolution panchromatic image and the spectral information of a low-resolution multispectral image. This work proposes a novel model for generating high-quality multispectral images. This model uses the feature domain of the convolution neural network to fuse multispectral and panchromatic images so that the fused images can generate new features so that the final fused features can restore clear images. Because of the unique feature extraction ability of convolution neural networks, we use the core idea of convolution neural networks to extract global features. To extract the complementary features of the input image at a deeper level, we first designed two subnetworks with the same structure but different weights, and then used single-channel attention to optimize the fused features to improve the final fusion performance. We select the public data set widely used in this field to verify the validity of the model. The experimental results on the GaoFen-2 and SPOT6 data sets show that this method has a better effect in fusing multi-spectral and panchromatic images. Compared with the classical and the latest methods in this field, our model fusion obtained panchromatic sharpened images from both quantitative and qualitative analysis has achieved better results. In addition, to verify the transferability and generalization of our proposed model, we directly apply it to multispectral image sharpening, such as hyperspectral image sharpening. Experiments and tests have been carried out on Pavia Center and Botswana public hyperspectral data sets, and the results show that the model has also achieved good performance in hyperspectral data sets. Full article

(This article belongs to the Special Issue Data Fusion and Artificial Intelligence Applications in Remote Sensing)

► Show Figures

Figure 1

17 pages, 12590 KiB

Open AccessArticle

PCNN Model Guided by Saliency Mechanism for Image Fusion in Transform Domain

by Liqun Liu and Jiuyuan Huo

Sensors 2023, 23(5), 2488; https://doi.org/10.3390/s23052488 - 23 Feb 2023

Cited by 2 | Viewed by 1180

Abstract

In heterogeneous image fusion problems, different imaging mechanisms have always existed between time-of-flight and visible light heterogeneous images which are collected by binocular acquisition systems in orchard environments. Determining how to enhance the fusion quality is key to the solution. A shortcoming of [...] Read more.

In heterogeneous image fusion problems, different imaging mechanisms have always existed between time-of-flight and visible light heterogeneous images which are collected by binocular acquisition systems in orchard environments. Determining how to enhance the fusion quality is key to the solution. A shortcoming of the pulse coupled neural network model is that parameters are limited by manual experience settings and cannot be terminated adaptively. The limitations are obvious during the ignition process, and include ignoring the impact of image changes and fluctuations on the results, pixel artifacts, area blurring, and the occurrence of unclear edges. Aiming at these problems, an image fusion method in a pulse coupled neural network transform domain guided by a saliency mechanism is proposed. A non-subsampled shearlet transform is used to decompose the accurately registered image; the time-of-flight low-frequency component, after multiple lighting segmentation using a pulse coupled neural network, is simplified to a first-order Markov situation. The significance function is defined as first-order Markov mutual information to measure the termination condition. A new momentum-driven multi-objective artificial bee colony algorithm is used to optimize the parameters of the link channel feedback term, link strength, and dynamic threshold attenuation factor. The low-frequency components of time-of-flight and color images, after multiple lighting segmentation using a pulse coupled neural network, are fused using the weighted average rule. The high-frequency components are fused using improved bilateral filters. The results show that the proposed algorithm has the best fusion effect on the time-of-flight confidence image and the corresponding visible light image collected in the natural scene, according to nine objective image evaluation indicators. It is suitable for the heterogeneous image fusion of complex orchard environments in natural landscapes. Full article

(This article belongs to the Special Issue Data Fusion and Artificial Intelligence Applications in Remote Sensing)

► Show Figures

Figure 1

19 pages, 5056 KiB

Open AccessArticle

High-Spatial-Resolution NDVI Reconstruction with GA-ANN

by Yanhong Zhao, Peng Hou, Jinbao Jiang, Jiajun Zhao, Yan Chen and Jun Zhai

Sensors 2023, 23(4), 2040; https://doi.org/10.3390/s23042040 - 11 Feb 2023

Cited by 4 | Viewed by 1597

Abstract

The normalized differential vegetation index (NDVI) for Landsat is not continuous on the time scale due to the long revisit period and the influence of clouds and cloud shadows, such that the Landsat NDVI needs to be filled in and reconstructed. This study [...] Read more.

The normalized differential vegetation index (NDVI) for Landsat is not continuous on the time scale due to the long revisit period and the influence of clouds and cloud shadows, such that the Landsat NDVI needs to be filled in and reconstructed. This study proposed a method based on the genetic algorithm–artificial neural network (GA-ANN) algorithm to reconstruct the Landsat NDVI when it has been affected by clouds, cloud shadows, and uncovered areas by relying on the MODIS characteristics for a wide coverage area. According to the self-validating results of the model test, the RMSE, MAE, and R were 0.0508, 0.0557, and 0.8971, respectively. Compared with the existing research, the reconstruction model based on the GA-ANN algorithm achieved a higher precision than the enhanced spatial and temporal adaptive reflectance fusion model (ESTARFM) and the flexible space–time data fusion algorithm (FSDAF) for complex land use types. The reconstructed method based on the GA-ANN algorithm had a higher root mean square error (RMSE) and mean absolute error (MAE). Then, the Sentinel NDVI data were used to verify the accuracy of the results. The validation results showed that the reconstruction method was superior to other methods in the sample plots with complex land use types. Especially on the time scale, the obtained NDVI results had a strong correlation with the Sentinel NDVI data. The correlation coefficient (R) of the GA-ANN algorithm reconstruction’s NDVI and the Sentinel NDVI data was more than 0.97 for the land use types of cropland, forest, and grassland. Therefore, the reconstruction model based on the GA-ANN algorithm could effectively fill in the clouds, cloud shadows, and uncovered areas, and produce NDVI long-series data with a high spatial resolution. Full article

(This article belongs to the Special Issue Data Fusion and Artificial Intelligence Applications in Remote Sensing)

► Show Figures

Figure 1

15 pages, 3387 KiB

Open AccessArticle

Saliency Detection of Light Field Images by Fusing Focus Degree and GrabCut

by Fuzhou Duan, Yanyan Wu, Hongliang Guan and Chenbo Wu

Sensors 2022, 22(19), 7411; https://doi.org/10.3390/s22197411 - 29 Sep 2022

Cited by 3 | Viewed by 1220

Abstract

In the light field image saliency detection task, redundant cues are introduced due to computational methods. Inevitably, it leads to the inaccurate boundary segmentation of detection results and the problem of the chain block effect. To tackle this issue, we propose a method [...] Read more.

In the light field image saliency detection task, redundant cues are introduced due to computational methods. Inevitably, it leads to the inaccurate boundary segmentation of detection results and the problem of the chain block effect. To tackle this issue, we propose a method for salient object detection (SOD) in light field images that fuses focus and GrabCut. The method improves the light field focus calculation based on the spatial domain by performing secondary blurring processing on the focus image and effectively suppresses the focus information of out-of-focus areas in different focus images. Aiming at the redundancy of focus cues generated by multiple foreground images, we use the optimal single foreground image to generate focus cues. In addition, aiming at the fusion of various cues in the light field in complex scenes, the GrabCut algorithm is combined with the focus cue to guide the generation of color cues, which realizes the automatic saliency target segmentation of the image foreground. Extensive experiments are conducted on the light field dataset to demonstrate that our algorithm can effectively segment the salient target area and background area under the light field image, and the outline of the salient object is clear. Compared with the traditional GrabCut algorithm, the focus degree is used instead of artificial Interactively initialize GrabCut to achieve automatic saliency segmentation. Full article

(This article belongs to the Special Issue Data Fusion and Artificial Intelligence Applications in Remote Sensing)

► Show Figures

Figure 1

14 pages, 5971 KiB

Open AccessArticle

Classification of Building Damage Using a Novel Convolutional Neural Network Based on Post-Disaster Aerial Images

by Zhonghua Hong, Hongzheng Zhong, Haiyan Pan, Jun Liu, Ruyan Zhou, Yun Zhang, Yanling Han, Jing Wang, Shuhu Yang and Changyue Zhong

Sensors 2022, 22(15), 5920; https://doi.org/10.3390/s22155920 - 08 Aug 2022

Cited by 13 | Viewed by 2856

Abstract

The accurate and timely identification of the degree of building damage is critical for disaster emergency response and loss assessment. Although many methods have been proposed, most of them divide damaged buildings into two categories—intact and damaged—which is insufficient to meet practical needs. [...] Read more.

The accurate and timely identification of the degree of building damage is critical for disaster emergency response and loss assessment. Although many methods have been proposed, most of them divide damaged buildings into two categories—intact and damaged—which is insufficient to meet practical needs. To address this issue, we present a novel convolutional neural network—namely, the earthquake building damage classification net (EBDC-Net)—for assessment of building damage based on post-disaster aerial images. The proposed network comprises two components: a feature extraction encoder module, and a damage classification module. The feature extraction encoder module is employed to extract semantic information on building damage and enhance the ability to distinguish between different damage levels, while the classification module improves accuracy by combining global and contextual features. The performance of EBDC-Net was evaluated using a public dataset, and a large-scale damage assessment was performed using a dataset of post-earthquake unmanned aerial vehicle (UAV) images. The results of the experiments indicate that this approach can accurately classify buildings with different damage levels. The overall classification accuracy was 94.44%, 85.53%, and 77.49% when the damage to the buildings was divided into two, three, and four categories, respectively. Full article

(This article belongs to the Special Issue Data Fusion and Artificial Intelligence Applications in Remote Sensing)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Data Fusion and Artificial Intelligence Applications in Remote Sensing

Share This Special Issue

Special Issue Editors

Special Issue Information

Published Papers (13 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI