Alireza Safdarinezhad; Mahdi Mokhtarzadeh; Mohammadjavad Valadanzouj
Abstract
Abstract
3D point clouds obtained by Airborne Laser Scanner Systems provide a varied and unique geometric information of the physical terrain surfaces due to advantages such as relatively high geometric accuracy and high spatial density of the points. Classification ...
Read More
Abstract
3D point clouds obtained by Airborne Laser Scanner Systems provide a varied and unique geometric information of the physical terrain surfaces due to advantages such as relatively high geometric accuracy and high spatial density of the points. Classification and separation of cloud point data to environmental constructive terrains plays an important role in the process of 3D modeling of terrains. In this procedure, point cloud clustering is a fundamental step in the procedure of information extraction form LiDAR's data. In this paper, a novel method is proposed for supervised classification of LiDAR cloud of points based on contextual analysis of LiDAR points. The proposed method consists of three main steps. In the first step, a set of features based on contextual analyses are produced for each point in LiDAR data. In the second step, the optimum feature selection is done in the modified prototype space using a new strategy. The last step is conducted by a simple k-means clustering in the feature space spanned by optimum contextual clusters. An urban area with the residential texture has been used as the case study to evaluate the proposed method. The results indicate proper classification accuracies. The overall accuracies and kappa coefficients were 93.15% and 0.89 respectively.
Hadi Babapour; Mahdi Mokhtarzadeh; Mohammad Javad Valadanzoj; Mahdi Modiri
Abstract
The importance of spatial-referenceddata in all developmental and research affairs is not overlooked. Among the methods for the preparation and production of spatial data, the photogrammetry method has a unique position due to speed, cost-effectiveness and above all, the lack of need to direct human ...
Read More
The importance of spatial-referenceddata in all developmental and research affairs is not overlooked. Among the methods for the preparation and production of spatial data, the photogrammetry method has a unique position due to speed, cost-effectiveness and above all, the lack of need to direct human presence on the site. In photogrammetric method, airborne cameras play a key role in the success and achievements of other stages, as the main means of providing input data and the first operational loop. Today, technological advances have led to the presentation of high quality digital cameras that promise the provision of the required spatial information by photogrammetric method with high accuracy, speed and efficiency. Given the emergence of new digital cameras and the variety of construction and technology used in these types of cameras, the need for their calibration is recognized as a primary requirement. Considering the high costs and executive problems with performing laboratory calibration, the use of self-calibration equations is considered as one of the most useful solutions in this field. For this purpose, in this paper, the use of Fourier equations with optimal terms derived from the genetic algorithm was proposed, and was evaluated and compared with previous models on the simulated data. Based on the results, this model is able to model multiple distortions with minimal dependency. The accuracy presented for modeling multiple distortions in simulated images of the Ultra Cam digital camerashows an about 30% improvement in modeling accuracy with the least dependency,compared with other additional parameters.