Figure 1 - uploaded by Jeremy P. Metcalf
Content may be subject to copyright.
![Teledyne Optech Titan Multispectral Lidar System (from [2]).](profile/Jeremy-Metcalf/publication/303099493/figure/fig11/AS:668786533351428@1536462543335/Teledyne-Optech-Titan-Multispectral-Lidar-System-from-2.png)
Source publication
![Figure 1. Teledyne Optech Titan Multispectral Lidar System (from [2]).](profile/Jeremy-Metcalf/publication/303099493/figure/fig11/AS:668786533351428@1536462543335/Teledyne-Optech-Titan-Multispectral-Lidar-System-from-2_Q320.jpg)
Data from Optech Titan are analyzed here for purposes of terrain classification, adding the spectral data component to the lidar point cloud analysis. Nearest-neighbor sorting techniques are used to create the merged point cloud from the three channels. The merged point cloud is analyzed using spectral analysis techniques that allow for the exploit...
Contexts in source publication
Context 1
... Teledyne Optech Titan Multispectral Lidar System (Figure 1) takes the ability to seamlessly collect topography and bathymetry found in previous dual-wavelength sensors with near-infrared (NIR) and green lasers, and adds a third shortwave infrared (SWIR) laser. The three lasers are not co-aligned. ...
Context 2
... turning on the X attribute and the lasclassify classification attribute, the Unclassified, Ground, Vegetation, and Building classes were easily separated. With the Z attribute and the Height attribute turned on, determination of the land/water/bathymetry interface was trivial (Figure 10). With the RGB attributes turned on, it was possible to determine 7 ground sub-classes: Railroad Tracks, Pavement Marking, Grass, Major Streets, Minor Streets, Sidewalks, and Soil and 4 building sub-classes: Roof 1-4. ...
Context 3
... the addition of the Vegetation and Water classes, 15 total training classes were identified. Figure 10. Two-dimensional scatterplot of the Titan point cloud in the ENVI n-Dimensional Visualizer tool using the Z and Height attributes to classify the land/water/bathymetry interface. ...
Context 4
... Likelihood supervised classification was performed on the Titan derived multispectral raster image ( Figure 11) and on the RGB attributes of the entire Titan point cloud ( Figure 12) using a probability threshold of 0.5 and the 13 training classes identified using the point cloud within the n-D Visualizer tool. Maximum Likelihood classification is the most common supervised classification method used with remote sensing image data [9] and calculates the probability that a given pixel, or lidar point, belongs to a specific class providing that the probability is above the probability threshold [10]. ...
Context 5
... Likelihood supervised classification was performed on the Titan derived multispectral raster image ( Figure 11) and on the RGB attributes of the entire Titan point cloud ( Figure 12) using a probability threshold of 0.5 and the 13 training classes identified using the point cloud within the n-D Visualizer tool. Maximum Likelihood classification is the most common supervised classification method used with remote sensing image data [9] and calculates the probability that a given pixel, or lidar point, belongs to a specific class providing that the probability is above the probability threshold [10]. ...
Similar publications
Accurate geometrical and spatial information of the built environment can be accurately acquired and the resulting 3D point cloud data is required to be processed to construct the digital model, Building Information Modelling (BIM) for existing facilities. Point cloud by laser scanning over the buildings and facilities has been commonly used, but t...
Citations
... Additionally, Miller and his partners took screenshots of the point cloud by frame and detected the screenshots with a visual method. However, this method can only obtain obstacle information on a twodimensional plane [32]. In Ref. [33], the authors illustrated the extraction and classification of 3D point cloud features with the help of machine learning algorithms and achieved the purpose of identifying obstacles. ...
An efficient obstacle detection system is one of the most important guarantees for improving the active safety performance of autonomous vehicles. This paper proposes an obstacle detection method based on high-precision positioning applied to blocked zones to solve the problems of the high complexity of detection results, low computational efficiency, and high load in traditional obstacle detection methods. Firstly, an NDT registration method which uses the likelihood function as the optimal value of the registration score function to calculate the registration parameters is designed to match the scanning point cloud and the target point cloud. Secondly, a target reduction method combined with threshold judgment and the binary tree search algorithm is designed to filter the point cloud of non-road obstacles to improve the processing speed of the computing platform. Meanwhile, KD-tree is used to speed up the clustering process. Finally, a vehicle remote control simulation platform with the combination of a cloud platform and mobile terminal is designed to verify the effectiveness of the strategy in practical application. The results prove that the proposed obstacle detection method can improve the efficiency and accuracy of detection.
... Removing ULBG points to extract targets can be accomplished based on distance and spectral difference. Laser spectral ratios such as the normalized difference veg-etation index (NDVI) have been used for object classification of multispectral/hyperspectral LiDAR point clouds [57][58][59]. An alternative method is to use Spectral Angle Mapping (SAM), which quantifies the spectral similarity between distinct spectral curves and is insensitive to spectral brightness resulting from variations in incident angle [32]. ...
The hyperspectral full-waveform LiDAR (HSL) system based on the supercontinuum laser can obtain spatial and spectral information of the target synchronously and outperform traditional LiDAR or imaging spectrometers in target classification and other applications. However, low detection efficiency caused by the detection of useless background points (ULBG) hinders its practical applications, especially when the target is small compared with the large field of view (FOV) of the HSL system. A novel vision-aided hyperspectral full-waveform LiDAR system (V-HSL) was proposed to solve the problem and improve detection efficiency. First, we established the framework and developed preliminary algorithms for the V-HSL system. Next, we experimentally compared the performance of the V-HSL system with the HSL system. The results revealed that the proposed V-HSL system could reduce the detection of ULBG points and improve detection efficiency with enhanced detection performance. The V-HSL system is a promising development direction, and the study results will help researchers and engineers develop and optimize their design of the HSL system and ensure high detection efficiency of spatial and spectral information of the target.
... Furthermore, to demonstrate the distinguishing capabilities of MS-LiDAR systems, Ekhtari et al. (2017) provided finer discrimination for ten classes (3 types of asphalt pavements, 2 types of soils, and 2 types of rooftop materials). Some studies have proved that 3D multispectral point cloud-based methods are superior to the 2D multispectral feature images-based methods with 10% higher accuracy in (Miller et al., 2016) and 3.8% in (Morsy et al. 2017). As mentioned in the review of 2D feature image-based methods, it is tedious to design handcrafted features to obtain satisfactory classification results. ...
This paper presents a feature reasoning-based graph convolution network (FR-GCNet) to improve the classification accuracy of airborne multispectral LiDAR (MS-LiDAR) point clouds. In the FR-GCNet, we directly assign semantic labels to all points by exploring representative features both globally and locally. Based on the graph convolution network (GCN), a global reasoning unit is embedded to obtain the global contextual feature by revealing spatial relationships of points, while a local reasoning unit is integrated to dynamically learn edge features with attention weights in each local graph. Extensive experiments on the Titan MS-LiDAR data showed that the proposed FR-GCNet achieved a promising classification performance with an overall accuracy of 93.55%, an average F1-score of 78.61%, and a mean Intersection over Union (IoU) of 66.78%. Comparative experimental results demonstrated the superiority of the FR-GCNet against other state-of-the-art approaches.
... Ekhtari et al. [31] performed an eleven-class classification task and achieved an OA of 79.7%. In addition, some multispectral point clouds classification studies have demonstrated that 3-D multispectral LiDAR point cloud based methods were superior to 2-D multispectral feature image based methods by an OA improvement of 10% in [32], and 3.8% in [33]. Recently, Wang et al. [34] extracted the geometric-and-spectral features from multispectral LiDAR point clouds by a tensor representation. ...
A multispectral light detection and ranging (LiDAR) system, which simultaneously collects spatial geometric data and multi-wavelength intensity information, opens the door to three-dimensional (3-D) point cloud classification and object recognition. Because of the irregular distribution property of point clouds and the massive data volume, point cloud classification directly from multispectral LiDAR data is still challengeable and questionable. In this paper, a point-wise multispectral LiDAR point cloud classification architecture termed as SE-PointNet++ is proposed via integrating a Squeeze-and-Excitation (SE) block with an improved PointNet++ semantic segmentation network. PointNet++ extracts local features from unevenly sampled points and represents local geometrical relationships among the points through multi-scale grouping. The SE block is embedded into PointNet++ to strengthen important channels to increase feature saliency for better point cloud classification. Our SE-PointNet++ architecture has been evaluated on the Titan multispectral LiDAR test datasets and achieved an overall accuracy, a mean Intersection over Union (mIoU), an F1-score, and a Kappa coefficient of 91.16%, 60.15%, 73.14%, and 0.86, respectively. Comparative studies with five established deep learning models confirmed that our proposed SE-PointNet++ achieves promising performance in multispectral LiDAR point cloud classification tasks.
... Currently, by using multi-spectral LiDAR data, many land-cover classification studies have been increasingly presented (Fernandez-Diaz et al., 2016;Hopkinson et al., 2016;Miller et al., 2016;Morsy et al., 2017;Chen et al., 2018). These land-cover classification methods are generally performed on either three-dimensional (3D) LiDAR points (Kumar et al., 2019b) or two-dimensional (2D) feature images interpolated from 3D points (Teo and Wu, 2017). ...
Multispectral LiDAR (Light Detection And Ranging) is characterized of the completeness and consistency of its spectrum and spatial geometric data, which provides a new data source for land-cover classification. In recent years, the convolutional neural network (CNN), compared with traditional machine learning methods, has made a series of breakthroughs in image classification, object detection, and image semantic segmentation due to its stronger feature learning and feature expression abilities. However, traditional CNN models suffer from some issues, such as a large number of layers, leading to higher computational cost. To address this problem, we propose a CNN-based multi-spectral LiDAR land-cover classification framework and analyze its optimal parameters to improve classification accuracy. This framework starts with the preprocessing of multi-spectral 3D LiDAR data into 2D images. Next, a CNN model is constructed with seven fundamental functional layers, and its hyper-parameters are comprehensively discussed and optimized. The constructed CNN model with the optimized hyper-parameters was tested on the Titan multi-spectral LiDAR data, which include three wavelengths of 532 nm, 1064 nm, and 1550 nm. Extensive experiments demonstrated that the constructed CNN with the optimized hyper-parameters is feasible for multi-spectral LiDAR land-cover classification tasks. Compared with the classical CNN models (i.e., AlexNet, VGG16 and ResNet50) and our previous studies, our constructed CNN model with the optimized hyper-parameters is superior in computational performance and classification accuracies.
... However, current MSL/HSL data application research mainly focuses on the inversion of vegetation biochemical parameters and target classification [23][24][25]. False-color 3D imaging has been realized based on MSL data [26], but color point clouds have yet to be fully explored. In particular, true-color 3D imaging is useful for accurate object classification, and has not been realized based on LiDAR data. ...
True-color three-dimensional (3D) imaging exploits spatial and spectral information and can enable accurate feature extraction and object classification. The existing methods, however, are limited by data collection mechanisms when realizing true-color 3D imaging. We overcome this problem and present a novel true-color 3D imaging method based on a 32-channel hyperspectral LiDAR (HSL) covering a 431–751 nm spectral range. We conducted two experiments, one with nine-color card papers and the other with seven different colored objects. We used the former to investigate the effect of true-color 3D imaging and determine the optimal spectral bands for compositing true-color, and the latter to explore the classification potential based on the true-color feature using polynomial support vector machine (SVM) and Gaussian naive Bayes (NB) classifiers. Since using all bands of HSL will cause color distortions, the optimal spectral band combination for better compositing the true-color were selected by principal component analysis (PCA) and spectral correlation measure (SCM); PCA emphasizes the amount of information in band combinations, while SCM focuses on correlation between bands. The results show that the true-color 3D imaging can be realized based on HSL measurements, and three spectral bands of 466, 546, and 626 nm were determined. Comparing reflectance of the three selected bands, the overall classification accuracy of seven different colored objects was improved by 14.6% and 8.25% based on SVM and NB, respectively, classifiers after converting spectral intensities into true-color information. Overall, this study demonstrated the potential of HSL system in retrieving true-color and facilitating target recognition, and can serve as a guide in developing future three-channel or multi-channel true-color LiDAR.
... Most approaches rasterize the multispectral point clouds prior to classification [2], [7], [8], [11]- [15] because "it is well suited for land cover classification of large areas" [2], while others attempt to directly classify the point clouds [16]- [18]. A comparison was made between the classification accuracy of point clouds versus raster in [17]. It was shown that direct classification of multispectral point clouds can improve the overall accuracy of classification by ∼10% [17]. ...
... A comparison was made between the classification accuracy of point clouds versus raster in [17]. It was shown that direct classification of multispectral point clouds can improve the overall accuracy of classification by ∼10% [17]. Classifying raster datasets directly results in a rasterized land cover map whereas such a map is a byproduct of a classified point cloud (classes of interest are binned into a raster map). ...
... In addition to classification accuracy, class diversity (number of classes used) is another metric to consider when assessing approaches for land cover mapping using multispectral lidar data. Some of the previously published research used very basic classes (such as water, ground, trees, and buildings) [7], [17], [18]. These classes could be separated based only on geometric information obtained from the point cloud. ...
Airborne light detection and ranging (lidar) data are widely used for high-resolution land cover mapping. The lidar elevation data are typically used as complementary information to passive multispectral or hyperspectral imagery to enable higher land cover classification accuracy. In this paper, we examine the capabilities of a recently developed multispectral airborne laser scanner, manufactured by Teledyne Optech, for direct classification of multispectral point clouds into ten land cover classes including grass, trees, two classes of soil, four classes of pavement, and two classes of buildings. The scanner, Titan MW, collects point clouds at three different laser wavelengths simultaneously, opening the door to new possibilities in land cover classification using only lidar data. We show that the recorded intensities of laser returns together with spatial metrics calculated from the three-dimensional (3D) locations of laser returns are sufficient for classifying the point cloud into ten distinct land cover classes. Our classification methods achieved an overall accuracy of 94.7% with a kappa coefficient of 0.94 using the support vector machine (SVM) method to classify single-return points and an overall accuracy of 79.7% and kappa coefficient of 0.77 using a rule-based classifier on multireturn points. A land cover map is then generated from the classified point cloud. We show that our results outperform the common approach of rasterizing the point cloud prior to classification by ∼4% in overall accuracy, 0.04 in kappa coefficient, and by up to 16% in commission and omission errors. This improvement however comes at the price of increased complexity and computational burden.
... Morsy et al. (2016) applied three normalized difference feature indices calculated from the Titan channels for land-water and vegetationbuilt-up separation. Classification experiments with data from the same area were also reported by Miller et al. (2016). Zou et al. (2016) used Titan data acquired from Ontario in 2015. ...
During the last 20 years, airborne laser scanning (ALS), often combined with passive multispectral information from aerial images, has shown its high feasibility for automated mapping processes. The main benefits have been achieved in the mapping of elevated objects such as buildings and trees. Recently, the first multispectral airborne laser scanners have been launched, and active multispectral information is for the first time available for 3D ALS point clouds from a single sensor. This article discusses the potential of this new technology in map updating, especially in automated object-based land cover classification and change detection in a suburban area. For our study, Optech Titan multispectral ALS data over a suburban area in Finland were acquired. Results from an object-based random forests analysis suggest that the multispectral ALS data are very useful for land cover classification, considering both elevated classes and ground-level classes. The overall accuracy of the land cover classification results with six classes was 96% compared with validation points. The classes under study included building, tree, asphalt, gravel, rocky area and low vegetation. Compared to classification of single-channel data, the main improvements were achieved for ground-level classes. According to feature importance analyses, multispectral intensity features based on several channels were more useful than those based on one channel. Automatic change detection for buildings and roads was also demonstrated by utilising the new multispectral ALS data in combination with old map vectors. In change detection of buildings, an old digital surface model (DSM) based on single-channel ALS data was also used. Overall, our analyses suggest that the new data have high potential for further increasing the automation level in mapping. Unlike passive aerial imaging commonly used in mapping, the multispectral ALS technology is independent of external illumination conditions, and there are no shadows on intensity images produced from the data. These are significant advantages in developing automated classification and change detection procedures.
Arsenic contamination not only complicates mineral processing but also poses environmental and health risks. To address these challenges, this research investigates the feasibility of utilizing Hyperspectral imaging combined with machine learning techniques for the identification of arsenic-containing minerals in copper ore samples, with a focus on practical application in sorting and processing operations. Through experimentation with various copper sulfide ores, Neighborhood Component Analysis (NCA) was employed to select essential wavelength bands from Hyperspectral data, subsequently used as inputs for machine learning algorithms to identify arsenic concentrations. Results demonstrate that by selecting a subset of informative bands using NCA, accurate mineral identification can be achieved with a significantly reduced the size of dataset, enabling efficient processing and analysis. Comparison with other wavelength selection methods highlights the superiority of NCA in optimizing classification accuracy. Specifically, the identification accuracy showed 91.9% or more when utilizing 8 or more bands selected by NCA and was comparable to hyperspectral data analysis with 204 bands. The findings suggest potential for cost-effective implementation of multispectral cameras in mineral processing operations. Future research directions include refining machine learning algorithms, exploring broader applications across diverse ore types, and integrating hyperspectral imaging with emerging sensor technologies for enhanced mineral processing capabilities.
