Various classification methods have been developed to extract meaningful information from Airborne Laser Scanner (ALS) point clouds. However, the accuracy and the computational efficiency of the existing methods need to be improved, especially for the analysis of large datasets (e.g., at regional or national levels). In this paper, we present a novel deep learning approach to ground classification for Digital Terrain Model (DTM) extraction as well as for multi-class land-cover classification, delivering highly accurate classification results in a computationally efficient manner. Considering the top-down acquisition angle of ALS data, the point cloud is initially projected on the horizontal plane and converted into a multi-dimensional image. Then, classification techniques based on Fully Convolutional Networks (FCN) with dilated kernels are designed to perform pixel-wise image classification. Finally, labels are transferred from pixels to the original ALS points. We also designed a Multi-Scale FCN (MS-FCN) architecture to minimize the loss of information during the point-to-image conversion. In the ground classification experiment, we compared our method to a Convolutional Neural Network (CNN)-based method and LAStools software. We obtained a lower total error on both the International Society for Photogrammetry and Remote Sensing (ISPRS) filter test benchmark dataset and AHN-3 dataset in the Netherlands. In the multi-class classification experiment, our method resulted in higher precision and recall values compared to the traditional machine learning technique using Random Forest (RF); it accurately detected small buildings. The FCN achieved precision and recall values of 0.93 and 0.94 when RF obtained 0.91 and 0.92, respectively. Moreover, our strategy significantly improved the computational efficiency of state-of-the-art CNN-based methods, reducing the point-to-image conversion time from 47 h to 36 min in our experiments on the ISPRS filter test dataset. Misclassification errors remained in situations that were not included in the training dataset, such as large buildings and bridges, or contained noisy measurements.As a result, points' features are represented by pixel values in the extracted image. Consequently, the point classification task is transformed to a pixel-wise image classification task. To address this task, we introduce a Fully Convolutional Network (FCN), which is a CNN variant that can predict the classification labels of every pixel in the image directly. We adopt FCN with dilated kernel (FCN-DK) for the classification [15]. FCN-DK is a no down-sampling network architecture that maintains the spatial size of the feature maps of each layer to be the same as the input. It uses dilated kernels to capture larger spatial contextual information, and therefore increases the receptive field of the network without increasing the number of parameters. We modify the FCN-DK network to perform ground and multi-class classification of an ALS point cloud. We also propose Multi-Scale FCN (MS-FCN) architectu...

Deep Learning has been massively used for image classification in recent years. The use of deep learning for ground classification from LIDAR point clouds has also been recently studied. However, point clouds need to be converted into an image in order to use Convolutional Neural Networks (CNNs). In state-of-the-art techniques, this conversion is slow because each point is converted into a separate image. This approach leads to highly redundant computation during conversion and classification. The goal of this study is to design a more efficient data conversion and ground classification. This goal is achieved by first converting the whole point cloud into a single image. The classification is then performed by a Fully Convolutional Network (FCN), a modified version of CNN designed for pixel-wise image classification. The proposed method is significantly faster than state-of-the-art techniques. On the ISPRS Filter Test dataset, it is 78 times faster for conversion and 16 times faster for classification. Our experimental analysis on the same dataset shows that the proposed method results in 5.22 % of total error, 4.10 % of type I error, and 15.07 % of type II error. Compared to the previous CNN-based technique and LAStools software, the proposed method reduces the total error and type I error (while type II error is slightly higher). The method was also tested on a very high point density LIDAR point clouds resulting in 4.02 % of total error, 2.15 % of type I error and 6.14 % of type II error.

ABSTRACT:Direct georeferencing is a new method in photogrammetry, especially in the digital camera era. Theoretically, this method does not require ground control points (GCP) and the Aerial Triangulation (AT), to process aerial photography into ground coordinates. Compared with the old method, this method has three main advantages: faster data processing, simple workflow and less expensive project, at the same accuracy. Direct georeferencing using two devices, GPS and IMU. GPS recording the camera coordinates (X, Y, Z), and IMU recording the camera orientation (omega, phi, kappa). Both parameters merged into Exterior Orientation (EO) parameter. This parameters required for next steps in the photogrammetric projects, such as stereocompilation, DSM generation, orthorectification and mosaic. Accuracy of this method was tested on topographic map project in Medan, Indonesia. Large-format digital camera Ultracam X from Vexcel is used, while the GPS / IMU is IGI AeroControl. 19 Independent Check Point (ICP) were used to determine the accuracy. Horizontal accuracy is 0.356 meters and vertical accuracy is 0.483 meters. Data with this accuracy can be used for 1:2.500 map scale project.

ABSTRACT:Nowadays DTM LIDAR was used extensively for generating contour line in Topographic Map. This method is very superior compared to traditionally stereomodel compilation from aerial images that consume large resource of human operator and very time consuming. Since the improvement of computer vision and digital image processing, it is possible to generate point cloud DSM from aerial images using image matching algorithm. It is also possible to classify point cloud DSM to DTM using the same technique with LIDAR classification and producing DTM which is comparable to DTM LIDAR. This research will study the accuracy difference of both DTMs and the result of DTM in several different condition including urban area and forest area, flat terrain and mountainous terrain, also time calculation for mass production Topographic Map. From statistical data, both methods are able to produce 1:5.000 Topographic Map scale.