Fusion of Hyperspectral and LiDAR Data Using Discriminant Correlation Analysis for Land Cover Classification

Jahan, Farah; Zhou, Jun; Awrangjeb, Mohammad; Gao, Yongsheng

doi:10.1109/jstars.2018.2868142

Cited by 19 publications

(22 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Due to the quality of UAV images nowadays, extracting reliable features to form a dataset becomes less of a problem. Example of such features are land cover characteristics (geometrical and spectral) from Light Detection and Ranging (LiDAR) and hyperspectral data [11]. Moreover, to enhance land cover classification, the combination of multisource (active/passive sensors) or multimodal data (data with different characteristics) is recommended [12,13].…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, to enhance land cover classification, the combination of multisource (active/passive sensors) or multimodal data (data with different characteristics) is recommended [12,13]. For example, Jahan et al [11] fused different LiDAR and hyperspectral datasets, and their derivatives, and proved that the overall accuracy of the fused datasets are higher than the single dataset. Another fusion of LiDAR and aerial colour images was performed to enhance building and vegetation detection [11].…”

Section: Introductionmentioning

confidence: 99%

“…For example, Jahan et al [11] fused different LiDAR and hyperspectral datasets, and their derivatives, and proved that the overall accuracy of the fused datasets are higher than the single dataset. Another fusion of LiDAR and aerial colour images was performed to enhance building and vegetation detection [11]. These additional features can sometimes improve the classification accuracy for specific domains and use cases.…”

Section: Introductionmentioning

confidence: 99%

“…These additional features can sometimes improve the classification accuracy for specific domains and use cases. For example, dataset fusion of RGB (Red, Green and Blue) images obtained from UAVs or other sources together with elevation information from digital surface models (DSM) provided a more holistic representation for the construction of accurate maps [11]. Considering DSMs as additional features was shown to improve classification results for image segmentation [14].…”

Section: Introductionmentioning

confidence: 99%

“…Based on the success of previous studies [11,[15][16][17], this paper also examines feature fusion but for the specific task of land cover classification taking advantage of fused DSM-UAV images. Specifically, we investigated the effectiveness of using a single feature modality (RGB data only) versus the fusion of RGB and DSM data.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Land Cover Classification from fused DSM and UAV Images Using Convolutional Neural Networks

et al. 2019

View full text Add to dashboard Cite

In recent years, remote sensing researchers have investigated the use of different modalities (or combinations of modalities) for classification tasks. Such modalities can be extracted via a diverse range of sensors and images. Currently, there are no (or only a few) studies that have been done to increase the land cover classification accuracy via unmanned aerial vehicle (UAV)-digital surface model (DSM) fused datasets. Therefore, this study looks at improving the accuracy of these datasets by exploiting convolutional neural networks (CNNs). In this work, we focus on the fusion of DSM and UAV images for land use/land cover mapping via classification into seven classes: bare land, buildings, dense vegetation/trees, grassland, paved roads, shadows, and water bodies. Specifically, we investigated the effectiveness of the two datasets with the aim of inspecting whether the fused DSM yields remarkable outcomes for land cover classification. The datasets were: (i) only orthomosaic image data (Red, Green and Blue channel data), and (ii) a fusion of the orthomosaic image and DSM data, where the final classification was performed using a CNN. CNN, as a classification method, is promising due to hierarchical learning structure, regulating and weight sharing with respect to training data, generalization, optimization and parameters reduction, automatic feature extraction and robust discrimination ability with high performance. The experimental results show that a CNN trained on the fused dataset obtains better results with Kappa index of~0.98, an average accuracy of 0.97 and final overall accuracy of 0.98. Comparing accuracies between the CNN with DSM result and the CNN without DSM result for the overall accuracy, average accuracy and Kappa index revealed an improvement of 1.2%, 1.8% and 1.5%, respectively. Accordingly, adding the heights of features such as buildings and trees improved the differentiation between vegetation specifically where plants were dense.

show abstract

Section: Introductionmentioning

confidence: 99%