Michal Spanel

Continuous plane detection in point-cloud data based on 3D Hough Transform

We propose a 3D Hough Transform plane detector for depth sensors.Several significant optimizations are proposed to maximize its practical usability.Continuous flow of frames is used to accumulate and iteratively refine detected planes.Comparison with another widely used plane extraction, RANSAC, is provided. This paper deals with shape extraction from depth images (point clouds) in the context of modern robotic vision systems. It presents various optimizations of the 3D Hough Transform used for plane extraction from point cloud data. Presented enhancements of standard methods address problems related to noisy data, high memory requirements for the parameter space and computational complexity of point accumulations. The realised robust plane detector benefits from a continuous point cloud stream generated by a depth sensor over time. It is used for iterative refinements of the results. The system is compared to a state-of-the-art RANSAC-based plane detector from the Point Cloud Library (PCL). Experimental results show that it overcomes the PCL alternative in the stability of plane detection and in the number of negative detections. This advantage is crucial for robotic applications, e.g., when a robot approaches a wall, it can be consistently recognized. The paper concludes with a discussion of further promising optimisation that will be implemented as a future step.

Fast and accurate plane segmentation in depth maps for indoor scenes

This paper deals with a scene pre-processing task - depth image segmentation. Efficiency and accuracy of several methods for depth map segmentation are explored. To meet real-time capable constraints, state-of-the-art techniques needed to be modified. Along with these modifications, new segmentation approaches are presented which aim at optimizing performance characteristics. They benefit from an assumption of human-made indoor environments by focusing on detection of planar regions. All methods were evaluated on datasets with manually annotated real environments. A comparison with alternative solutions is also presented.

Teeth And Jaw 3D Reconstrucion In Stomatology

The article deals with problematic of 3D tissues reconstruction in area of stomatology. 3D geometry models of teeth and jaw bones we have created based on input CT image data. The input discrete CT data have to be segmented by nearly automatic procedure with correction and verification. Creation of segmented tissue 3D geometry models is based on vectorization of input discrete data extended by smoothing and decimation. We have actually processed data for almost 40 patients (60 models). Created 3D models are all applied in clinical practice for planning, simulations and navigation in orthodontic and stomatology surgery treatments.

Collar Line Segments for fast odometry estimation from Velodyne point clouds

We present a novel way of odometry estimation from Velodyne LiDAR point cloud scans. The aim of our work is to overcome the most painful issues of Velodyne data - the sparsity and the quantity of data points - in an efficient way, enabling more precise registration. Alignment of the point clouds which yields the final odometry is based on random sampling of the clouds using Collar Line Segments (CLS). The closest line segment pairs are identified in two sets of line segments obtained from two consequent Velodyne scans. From each pair of correspondences, a transformation aligning the matched line segments into a 3D plane is estimated. By this, significant planes (ground, walls, ...) are preserved among aligned point clouds. Evaluation using the KITTI dataset shows that our method outperforms publicly available and commonly used state-of-the-art method GICP for point cloud registration in both accuracy and speed, especially in cases where the scene lacks significant landmarks or in typical urban elements. For such environments, the registration error of our method is reduced by 75% compared to the original GICP error.

Intensity-based femoral atlas 2D/3D registration using Levenberg-Marquardt optimisation

The reconstruction of a patient-specific 3D anatomy is the crucial step in the computer-aided preoperative planning based on plain X-ray images. In this paper, we propose a robust and fast reconstruction methods based on fitting the statistical shape and intensity model of a femoral bone onto a pair of calibrated X-ray images. We formulate the registration as a non-linear least squares problem, allowing for the involvement of Levenberg-Marquardt optimisation. The proposed methods have been tested on a set of 96 virtual X-ray images. The reconstruction accuracy was evaluated using the symmetric Hausdorff distance between reconstructed and ground-truth bones. The accuracy of the intensity-based method reached 1.18 ± 1.57mm on average, the registration took 8.76 seconds on average.

Simplified industrial robot programming: Effects of errors on multimodal interaction in WoZ experiment

This paper presents results of an exploratory study comparing various modalities employed in an industrial-like robot-human shared workplace. Experiments involved 39 participants who used a touch table, a touch display, hand gestures, a 6D pointing device, and a robot arm to show the robot how to assemble a simple product. To rule out a potential dependence of results on the number of misrecognized actions (resulting, e.g., from unreliable gesture recognition), a controlled amount of interaction errors was introduced. A Wizard-of-Oz setting with three user groups differing in the amount of simulated recognition errors helped us to show that hand gestures and 6D pointing are the fastest modalities that are also generally preferred by users for setting parameters of certain robot operations.

Consultation virtual collaborative environment for 3D medicine

This article focuses on the problems of consultation virtual collaborative environment, which is designed to support 3D medical applications. This system allows loading CT/MR data from PACS system, segmentation and 3D models of tissues. It allows distant 3D consultations of the data between technicians and surgeons. System is designed as three-layer client-server architecture. Communication between clients and server is done via HTTP/HTTPS protocol. Results and tests have confirmed, that todays standard network latency and dataflow do not affect the usability of our system.

Network collaborative environment supporting 3D medicine

This paper is focused on the virtual collaborative consultation system which is intended for support of 3D geometrical modelling applications in the field of clinical human medicine. The system allows uploading the CT/MR data and 3D tissue geometry models (prepared in advance). The data define a 3D scene, which allows for viewing of the data and consulting them between technicians and physicians over the medium of computer network. The system is conceived as a three layer client-server architecture. For communication between the server and a client, the HTTPS protocol is used. Test results in Czech republic and the world-wide tests as well confirm, that the system is practically applicable and beneficial.

Network collaborative environment for human tissues 3D modeling

This paper deals with the new concept of network based virtual collaborative environment to support clinical applications of 3D models of human tissues, created from CT/MR data. It is a topic lying between 3D tissue modeling and PACS systems. Designed system allows clinical realizations of 3D applications as a service to clinical workplaces, provided by specialized 3D laboratory, even over great distances. Problem lies within the need of doing necessary consultations, corrections and verifications distantly. This is solved by our system in the form of virtual collaborative environment. This system is built upon three-layer client-server architecture. Our application is focused on 3D tissue modeling. Generally it can be used as a basis for other similar applications.

Intensity-Based Nonoverlapping Area Registration Supporting “Drop-Outs” in Terms of Model-Based Radiostereometric Analysis

A model-based radiostereometric analysis (MBRSA) is a method for precise measurement of prosthesis migration, which does not require marking the implant with tantalum beads. Instead, the prosthesis pose is typically recovered using a feature-based 2D-3D registration of its virtual model into a stereo pair of radiographs. In this study, we evaluate a novel intensity-based formulation of previously published nonoverlapping area (NOA) approach. The registration is capable of performing with both binary radiographic segmentations and nonsegmented X-ray images. In contrast with the feature-based version, it is capable of dealing with unreliable parts of prosthesis. As the straightforward formulation allows efficient acceleration using modern graphics adapters, it is possible to involve precise high-poly virtual models. Moreover, in case of binary segmentations, the nonoverlapping area is simply interpretable and useful for indicating the accuracy of the registration outcome. In silico and phantom evaluations were performed using a cementless Zweymüller femoral stem and its reverse engineered (RE) model. For initial pose estimates with difference from the ground-truth limited to ±4 mm and ±4°, respectively, the mean absolute translational error was not higher than 0.042 ± 0.035 mm. The error in rotation around the proximodistal axis was 0.181 ± 0.265°, and the error for the remaining axes was not higher than 0.035 ± 0.037°.