Towards the automatic scanning of indoors with robots

Proposing 3D Thermal Technology for Heritage Building Energy Monitoring

The energy monitoring of heritage buildings has, to date, been governed by methodologies and standards that have been defined in terms of sensors that record scalar magnitudes and that are placed in specific positions in the scene, thus recording only some of the values sampled in that space. In this paper, however, we present an alternative to the aforementioned technologies in the form of new sensors based on 3D computer vision that are able to record dense thermal information in a three-dimensional space. These thermal computer vision-based technologies (3D-TCV) entail a revision and updating of the current building energy monitoring methodologies. This paper provides a detailed definition of the most significant aspects of this new extended methodology and presents a case study showing the potential of 3D-TCV techniques and how they may complement current techniques. The results obtained lead us to believe that 3D computer vision can provide the field of building monitoring with a decisive boost, particularly in the case of heritage buildings.

From BIM to Scan Planning and Optimization for Construction Control

Scan planning of buildings under construction is a key issue for an efficient assessment of work progress. This work presents an automatic method aimed to determinate the optimal scan positions and the optimal route based on the use of Building Information Models (BIM) and considering data completeness as stopping criteria. The method is considered for a Terrestrial Laser Scanner mounted on a mobile robot following a stop & go procedure. The method starts by extracting floor plans from the BIM model according to the planned construction status, and including geometry and semantics of the building elements considered for construction control. The navigable space is defined from a binary map considering a security distance to building elements. After a grid-based and a triangulation-based distribution are implemented for generating scan position candidates, a visibility analysis is carried out to determine the optimal number and position of scans. The optimal route to visit all scan positions is addressed by using a probabilistic ant colony optimization algorithm. The method has been tested in simulated and real buildings under very dissimilar conditions and structural construction elements. The two approaches for generating scan position candidates are evaluated and results show the triangulation-based distribution as the more efficient approach in terms of processing and acquisition time, especially for large-scale buildings.

New discretization method applied to NBV problem: Semioctree

This paper presents a discretization methodology applied to the NBV (Next Best View) problem, which consists of determining the heuristical best position of the next scan. This new methodology is a hybrid process between a homogenous voxelization and an octree structure that preserves the advantages of both methods. An octree structure is not directly applicable to the NBV problem: as the point cloud grows with every successive scanning, the limits and position of the discretization, octree structure must coincide, in order to transfer the information from one scan to the next. This problem is solved by applying a first coarse voxelization, followed by the division of each voxel in an octree structure. In addition, a previous methodology for solving the NBV problem has been adapted to make use of this novel approach. Results show that the new method is three times faster than the homogenous voxelization for a maximum resolution of 0.2m. For this target resolution of 0.2m, the number of voxels/octants in the discretization is reduced approximately by a 400%, from 35.360 to 8.937 for the study case presented.

Reconstruction of Three-Dimensional (3D) Indoor Interiors with Multiple Stories via Comprehensive Segmentation

The fast and stable reconstruction of building interiors from scanned point clouds has recently attracted considerable research interest. However, reconstructing long corridors and connected areas across multiple floors has emerged as a substantial challenge. This paper presents a comprehensive segmentation method for reconstructing a three-dimensional (3D) indoor structure with multiple stories. With this method, the over-segmentation that usually occurs in the reconstruction of long corridors in a complex indoor environment is overcome by morphologically eroding the floor space to segment rooms and by overlapping the segmented room-space with partitioned cells via extracted wall lines. Such segmentation ensures both the integrity of the room-space partitions and the geometric regularity of the rooms. For spaces across floors in a multistory building, a peak-nadir-peak strategy in the distribution of points along the z-axis is proposed in order to extract connected areas across multiple floors. A series of experimental tests while using seven real-world 3D scans and eight synthetic models of indoor environments show the effectiveness and feasibility of the proposed method.

A Monocular Vision Sensor-Based Obstacle Detection Algorithm for Autonomous Robots

This paper presents a monocular vision sensor-based obstacle detection algorithm for autonomous robots. Each individual image pixel at the bottom region of interest is labeled as belonging either to an obstacle or the floor. While conventional methods depend on point tracking for geometric cues for obstacle detection, the proposed algorithm uses the inverse perspective mapping (IPM) method. This method is much more advantageous when the camera is not high off the floor, which makes point tracking near the floor difficult. Markov random field-based obstacle segmentation is then performed using the IPM results and a floor appearance model. Next, the shortest distance between the robot and the obstacle is calculated. The algorithm is tested by applying it to 70 datasets, 20 of which include nonobstacle images where considerable changes in floor appearance occur. The obstacle segmentation accuracies and the distance estimation error are quantitatively analyzed. For obstacle datasets, the segmentation precision and the average distance estimation error of the proposed method are 81.4% and 1.6 cm, respectively, whereas those for a conventional method are 57.5% and 9.9 cm, respectively. For nonobstacle datasets, the proposed method gives 0.0% false positive rates, while the conventional method gives 17.6%.