Multitemporal Feature-Level Fusion on Hyperspectral and LiDAR Data in the Urban Environment

Kuras, Agnieszka; Brell, Maximilian; Liland, Kristian Hovde; Burud, I.

doi:10.3390/rs15030632

Cited by 12 publications

(4 citation statements)

References 63 publications

(76 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, hyperspectral images can store and acquire comprehensive and in-depth feature information. This characteristic allows hyperspectral images to be effectively applied in various fields, such as resources [2,3], environment [4], urban planning [5], ecology [6], and geology [7,8]. Especially in geology, the identification and classification of surface lithology is fundamental.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Image Classification Based on Double-Branch Multi-Scale Dual-Attention Network

Zhang,

Liu,

Yang

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Although extensive research shows that CNNs achieve good classification results in HSI classification, they still struggle to effectively extract spectral sequence information from HSIs. Additionally, the high-dimensional features of HSIs, the limited number of labeled samples, and the common sample imbalance significantly restrict classification performance improvement. To address these issues, this article proposes a double-branch multi-scale dual-attention (DBMSDA) network that fully extracts spectral and spatial information from HSIs and fuses them for classification. The designed multi-scale spectral residual self-attention (MSeRA), as a fundamental component of dense connections, can fully extract high-dimensional and intricate spectral information from HSIs, even with limited labeled samples and imbalanced distributions. Additionally, this article adopts a dataset partitioning strategy to prevent information leakage. Finally, this article introduces a hyperspectral geological lithology dataset to evaluate the accuracy and applicability of deep learning methods in geology. Experimental results on the geological lithology hyperspectral dataset and three other public datasets demonstrate that the DBMSDA method exhibits superior classification performance and robust generalization ability compared to existing methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Hyperspectral Image Classification Based on Double-Branch Multi-Scale Dual-Attention Network

Zhang,

Liu,

Yang

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…These challenges are exacerbated when proposals contain only a few points (1)(2)(3)(4)(5), from which it is challenging to obtain enough semantic information. In urban scenarios, multi-sensor fusion performs better than single sensors in various tasks such as remote sensing [9,10]. Fortunately, cameras provide dense texture information and are complementary to LiDAR.…”

Section: Introductionmentioning

confidence: 99%

FusionRCNN: LiDAR-Camera Fusion for Two-Stage 3D Object Detection

Dong

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Accurate and reliable perception systems are essential for autonomous driving and robotics. To achieve this, 3D object detection with multi-sensors is necessary. Existing 3D detectors have significantly improved accuracy by adopting a two-stage paradigm that relies solely on LiDAR point clouds for 3D proposal refinement. However, the sparsity of point clouds, particularly for faraway points, makes it difficult for the LiDAR-only refinement module to recognize and locate objects accurately. To address this issue, we propose a novel multi-modality two-stage approach called FusionRCNN. This approach effectively and efficiently fuses point clouds and camera images in the Regions of Interest (RoI). The FusionRCNN adaptively integrates both sparse geometry information from LiDAR and dense texture information from the camera in a unified attention mechanism. Specifically, FusionRCNN first utilizes RoIPooling to obtain an image set with a unified size and gets the point set by sampling raw points within proposals in the RoI extraction step. Then, it leverages an intra-modality self-attention to enhance the domain-specific features, followed by a well-designed cross-attention to fuse the information from two modalities. FusionRCNN is fundamentally plug-and-play and supports different one-stage methods with almost no architectural changes. Extensive experiments on KITTI and Waymo benchmarks demonstrate that our method significantly boosts the performances of popular detectors. Remarkably, FusionRCNN improves the strong SECOND baseline by 6.14% mAP on Waymo and outperforms competing two-stage approaches.

show abstract

“…Due to the fragmentation of information from a single data source, more and more scholars begin to pay attention to the fusion of information from different data sources to reflect the evolution of urban built-up areas and its influencing factors. Data fusion refers to combining and transforming information from single or multiple sources obtained from different channels [34], and the fused information not only provides more accurate estimation and judgment than information from a single source, but also greatly improves data and information validity and reliability [35]. As a key direction of data fusion, image fusion has been widely used in remote sensing, vision, urban observation and other fields [36].…”

Section: Introductionmentioning

confidence: 99%

Evolution and Influencing Factors of Urban Built-Up Areas in the Yangtze River Delta Urban Agglomeration

Chen,

Deng

2023

IEEE Access

View full text Add to dashboard Cite

The scale of urban built-up areas is one of the important indicators for measuring urban development, understanding the evolution and underlying mechanisms of urban built-up areas is of significant value for the development and planning of urban agglomerations. Based on Nighttime Light (NTL) data, Point of Interest (POI) data and LnadScan data, this study constructs a new index to extract the built-up area through multi-source big data fusion, automatically extracts the built-up area of urban agglomerations in a long time series based on U-net neural network, and finally analyzes the dominant factors driving the evolution of built-up area of urban agglomerations in different periods. The results indicate that the fusion of multi-source big data can accurately extract urban built-up areas and analyze their evolution process. The dominant factors driving the evolution of built-up areas vary across different periods, with a weakening influence of the per GDP factors and population dynamics, while the driving force of urban planning for the evolution of built-up areas is strengthened. This study, through the analysis of the evolution process and influencing factors of urban built-up areas in the Yangtze River Delta (YRD) urban agglomeration, contributes to the accurate identification of the internal urban development within the YRD urban agglomeration, assisting in the formulation of subsequent development plans. Furthermore, it provides relevant references for the development of urban areas in other regions.

show abstract

Multitemporal Feature-Level Fusion on Hyperspectral and LiDAR Data in the Urban Environment

Cited by 12 publications

References 63 publications

Hyperspectral Image Classification Based on Double-Branch Multi-Scale Dual-Attention Network

Hyperspectral Image Classification Based on Double-Branch Multi-Scale Dual-Attention Network

FusionRCNN: LiDAR-Camera Fusion for Two-Stage 3D Object Detection

Evolution and Influencing Factors of Urban Built-Up Areas in the Yangtze River Delta Urban Agglomeration

Contact Info

Product

Resources

About