Dinko Osmankovic

A mobile robot based system for fully automated thermal 3D mapping

Display Omitted We propose a fully autonomous system for 3D thermal modeling of buildings.A robot finds the positions for data acquisition using 3D sensor placement planning.Data from a laser scanner, a thermal camera, and a photo camera are automatically joined into one full model.Post-processing prepares the data for inspection in a viewer and points out interesting parts in the environment to experts. It is hard to imagine living in a building without electricity and a heating or cooling system these days. Factories and data centers are equally dependent on a continuous functioning of these systems. As beneficial as this development is for our daily life, the consequences of a failure are critical. Malfunctioning power supplies or temperature regulation systems can cause the close-down of an entire factory or data center. Heat and air conditioning losses in buildings lead to a large waste of the limited energy resources and pollute the environment unnecessarily. To detect these flaws as quickly as possible and to prevent the negative consequences constant monitoring of power lines and heat sources is necessary. To this end, we propose a fully automatic system that creates 3D thermal models of indoor environments. The proposed system consists of a mobile platform that is equipped with a 3D laser scanner, an RGB camera and a thermal camera. A novel 3D exploration algorithm ensures efficient data collection that covers the entire scene. The data from all sensors collected at different positions is joined into one common reference frame using calibration and scan matching. In the post-processing step a model is built and points of interest are automatically detected. A viewer is presented that aids experts in analyzing the heat flow and localizing and identifying heat leaks. Results are shown that demonstrate the functionality of the system.

The Project ThermalMapper - Thermal 3D Mapping of Indoor Environments for Saving Energy

Abstract Heat and air conditioning losses in buildings and factories lead to a large amount of wasted energy. The Action Plan for Energy Efficiency of the Commission of the European Communities (2008) estimates that the largest cost-effective energy savings potential lies in residential (≈ 27%) and commercial (≈ 30%) buildings. Imagine a technology that creates a precise digital 3D model of heat distribution and heat flow enabling one to detect all sources of wasted energy and to modify buildings to reach these savings. This paper presents our overall approach to map indoor environments with thermal data in 3D.

Neuro-fuzzy classification of asthma and chronic obstructive pulmonary disease.

BackgroundThis paper presents a system for classification of asthma and chronic obstructive pulmonary disease (COPD) based on fuzzy rules and the trained neural network.MethodsFuzzy rules and neural network parameters are defined according to Global Initiative for Asthma (GINA) and Global Initiative for chronic Obstructive Lung Disease (GOLD) guidelines. For neural network training more than one thousand medical reports obtained from database of the company CareFusion were used. Afterwards the system was validated on 455 patients by physicians from the Clinical Centre University of Sarajevo.ResultsOut of 170 patients with asthma, 99.41% of patients were correctly classified. In addition, 99.19% of the 248 COPD patients were correctly classified. The system was 100% successful on 37 patients with normal lung function. Sensitivity of 99.28% and specificity of 100% in asthma and COPD classification were obtained.ConclusionOur neuro-fuzzy system for classification of asthma and COPD uses a combination of spirometry and Impulse Oscillometry System (IOS) test results, which in the very beginning enables more accurate classification.Additionally, using bronchodilatation and bronhoprovocation tests we get a complete patients dynamic assessment, as opposed to the solution that provides a static assessment of the patient.

Reconstructing the 3D thermal model of indoor environment from unorganized data set acquired by 3D laser scans and thermal imaging camera

After recording data sets using a 3D laser scanner, the logical step would be to reconstruct 3D model from given points. This paper proposes one solution to the reconstruction of 3D model. It combines splatting methods with polygonalization to achieve most accurate 3D model of an indoor mobile robot environment with fast execution and rendering time. The main objective of the work, which was done as a part of ThermalMapper project, was to generate an accurate mesh of the indoor environment based on laser scans with added temperature scalars acquired by 6D SLAM method. This is useful for generating meshes of museums, buildings, tunnels, etc. which can be used for inspection and different analyses. A series of experiments demonstrate the usefulness and effectiveness of the proposed 3D surface reconstruction methods.

Burs of free C-space: A novel structure for path planning

This paper presents a new approach to C-space exploration and path planning for robotic manipulators using the structure named bur of free C-space. This structure builds upon the so-called bubble, which is a local volume of free C-space, easily computed using the distance information in the workspace. We show how the same distance information can be used to compute the bur that can reach substantially beyond the boundary of the bubble. It is shown how burs can be used to form a rapidly exploring bur tree (RBT): a space-filling tree that resembles RRT. Such a structure can easily be used within a suitably tailored path planning algorithm. Simulation study shows how the RBT-based algorithm outperforms the classical RRT-based method.

Performance and quality assessment of R-tree based nearest neighbour search in the scalar field mapping technique

Energy efficiency became more relevant recently. This also includes the construction of energy efficient buildings in terms of heat conservation and dissipation. For analysing the energy efficiency several mapping algorithms are proposed that map indoor environments with added thermal information. Also, several algorithms that generate virtual 3D models are recently presented. One of the main parts of these algoritms are nearest neighbour searching techniques. There are several algorithms that enables the use of nearest neighbour (NN) search. In this paper we present the assessment of R-tree based NN queries in the problem of scalar field mapping that maps a measured temperatures onto reconstructed 3D-mesh of indoor environment. The mesh is reconstructed from the point cloud recorded with 3D laser scanner and thermal imaging camera. We present the performance analysis of the R-tree based NN search with different R-tree types. Also, we present the quality of the scalar field mapping produced with employed R-tree based NN search techniques.

Detecting heat sources from 3D thermal model of indoor environment

Recent developments in environment sensing and virtual modelling enabled the construction of virtual models of indoor environments with added thermal information. In this paper we present the methods for heat sources extraction from the 3D thermal model of an indoor environment. They are based on known image segmentation techniques but adjusted to work with 3D models with added thermal information. All data are acquired using an autonomous mobile robot platform equipped with 3D laser scanner and thermal imaging camera.

Increasing the precision of reconstructed 3D model of indoor robot environment by elimination of problematic points1

Abstract In the process of reconstructing the 3D environment from the point cloud acquired from 3D laser the main objective is to obtain the model that is as precise as possible. Reconstruction algorithms greatly rely on the input data precision. Unfortunately, the point clouds regularly contains points that are problematic for the reconstruction. They are mostly associated with the reflection of laser beams off the semi–transparent surfaces, e.g. windows. This paper proposes the method for eliminating such points based on K–means clustering in order to increase the accuracy of the reconstructed 3D model.

Aerial image mosaicing approach based on feature matching

The paper treats a problem of building an image mosaic or a 2D map from the sequence of images taken by an Unmanned Aerial Vehicle (UAV). The proposed algorithm is composed of the following parts: feature detection and extraction using Speeded Up Robust Features (SURF) descriptor, feature matching using Fast Approximate Nearest Neighbor Search (FANN) with automatic algorithm configuration, estimation of the optimal transform between images using RANdom SAmple Consensus (RANSAC) and finally creating a mosaic by stitching images together using the obtained transformations. Summarizing results obtained in two different scenarios, it can be concluded that the proposed algorithm exhibits near real time performance for automated UAV 2D aerial mapping.

Rapidly exploring bur trees for optimal motion planning

This paper presents a new approach to C-space exploration and optimal path planning for robotic manipulators and planar scenarios using the structure named bur of free C-space. This structure builds upon the so-called bubble, which is a local volume of free C-space, easily computed using the distance information in the workspace. It is previously shown how burs can be used to form a rapidly exploring bur tree (RBT): a space-filling tree that resembles RRT. Now, we exploit the burs of free C-space approach to develop a new algorithm called RBT*, which is, like RRT* algorithm, provably asymptotically optimal, i.e., such that the cost of the returned solution converges almost surely to the optimum. Burs of free space offer better performance and faster convergence because it enables faster exploration of free space.