Pavel Smrz

A New Czech Morphological Analyser ajka

This paper deals with the effective implementation of the new Czech morphological analyser ajka which is based on the algorithmic description of the Czech formal morphology. First, we present two most important word-forming processes in Czech - inflection and derivation. A brief description of the data structures used for storing morphological information as well as a discussion of the efficient storage of lexical items (stem bases of Czech words) is included too. Finally, we bring some interesting features of the designed and implemented system ajka together with current statistic data.

DESAM - Annotated Corpus for Czech

This paper deals with Czech disambiguated corpus DESAM. It is a tagged corpus which has been manually disambiguated and can be used in various applications. We discuss the structure of the corpus, tools used for its managing, linguistic applications, and also possible use of machine learning techniques relying on the disambiguated data. Possible ways of developing the procedures for complete automatic disambiguation are considered.

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.

Incremental Block Cholesky Factorization for Nonlinear Least Squares in Robotics

Efficiently solving nonlinear least squares (NLS) problems is crucial for many applications in robotics. In online applications, solving the associated nolinear systems every step may become very expensive. This paper introduces online, incremental solutions, which take full advantage of the sparseblock structure of the problems in robotics. In general, the solution of the nonlinear system is approximated by incrementally solving a series of linearized problems. The most computationally demanding part is to assemble and solve the linearized system at each iteration. In our solution, this is mitigated by incrementally updating the factorized form of the linear system and changing the linearization point only if needed. The incremental updates are done using a resumed factorization only on the parts affected by the new information added to the system at every step. The sparsity of the factorized form directly affects the efficiency. In order to obtain an incremental factorization with persistent reduced fill-in, a new incremental ordering scheme is proposed. Furthermore, the implementation exploits the block structure of the problems and offers efficient solutions to manipulate block matrices, including a highly efficient Cholesky factorization on sparse block matrices. In this work, we focus our efforts on testing the method on SLAM applications, but the applicability of the technique remains general. The experimental results show that our implementation outperforms the state of the art SLAM implementations on all the tested datasets.

Towards robust personal assistant robots: Experience gained in the SRS project

SRS is a European research project for building robust personal assistant robots using ROS (Robotic Operating System) and Care-O-bot (COB) 3 as the initial demonstration platform. In this paper, experience gained while building the SRS system is presented. A main contribution of the paper is the SRS autonomous control framework. The framework is divided into two parts. First, it has an automatic task planner, which initialises actions on the symbolic level. The planner produces proactive robotic behaviours based on updated semantic knowledge. Second, it has an action executive for coordination actions at the level of sensing and actuation. The executive produces reactive behaviours in well-defined domains. The two parts are integrated by fuzzy logic based symbolic grounding. As a whole, they represent the framework for autonomous control. Based on the framework, several new components and user interfaces are integrated on top of COBs existing capabilities to enable robust fetch and carry in unstructured environments. The implementation strategy and results are discussed at the end of the paper.

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.

Efficient implementation for block matrix operations for nonlinear least squares problems in robotic applications

A large number of robotic, computer vision and computer graphics applications rely on efficiently solving the associated sparse linear systems. Simultaneous localization and mapping (SLAM), structure from motion (SfM), non-rigid shape recovery, and elastodynamic simulations are only few examples in this direction. In general, these problems are nonlinear and the solution can be approximated by incrementally solving a series of linearized problems. In some applications, the size of the system considerably affects the performance, especially when the sparsity is low. This paper exploits the block structure of such problems and offers very efficient solutions to manipulate block matrices within iterative nonlinear solvers. The resulting method considerably speeds-up the execution of the implementation of the nonlinear optimization problem. In this work, in particular, we focus our effort on testing the method on SLAM applications, but the applicability of the technique remains general. Our implementation outperforms the state of the art SLAM implementations on all tested datasets. In incremental mode, where a larger portion of time is spent in updating the system, our implementation is on average two times faster than the others.

Fast covariance recovery in incremental nonlinear least square solvers

Many estimation problems in robotics rely on efficiently solving nonlinear least squares (NLS). For example, it is well known that the simultaneous localisation and mapping (SLAM) problem can be formulated as a maximum likelihood estimation (MLE) and solved using NLS, yielding a mean state vector. However, for many applications recovering only the mean vector is not enough. Data association, active decisions, next best view, are only few of the applications that require fast state covariance recovery. The problem is not simple since, in general, the covariance is obtained by inverting the system matrix and the result is dense. The main contribution of this paper is a novel algorithm for fast incremental covariance update, complemented by a highly efficient implementation of the covariance recovery. This combination yields to two orders of magnitude reduction in computation time, compared to the other state of the art solutions. The proposed algorithm is applicable to any NLS solver implementation, and does not depend on incremental strategies described in our previous papers, which are not a subject of this paper.

Multimodal Emotion Recognition for AVEC 2016 Challenge

This paper describes a systems for emotion recognition and its application on the dataset from the AV+EC 2016 Emotion Recognition Challenge. The realized system was produced and submitted to the AV+EC 2016 evaluation, making use of all three modalities (audio, video, and physiological data). Our work primarily focused on features derived from audio. The original audio features were complement with bottleneck features and also text-based emotion recognition which is based on transcribing audio by an automatic speech recognition system and applying resources such as word embedding models and sentiment lexicons. Our multimodal fusion reached CCC=0.855 on dev set for arousal and 0.713 for valence. CCC on test set is 0.719 and 0.596 for arousal and valence respectively.

Collective Intelligence Generation from User Contributed Content

In this paper we provide a foundation for a new generation of services and tools. We define new ways of capturing, sharing and reusing information and intelligence provided by single users and communities, as well as organizations by enabling the extraction, generation, interpretation and management of Collec- tive Intelligence from user generated digital multimedia content. Different layers of intelligence are generated, which together constitute the notion of Collective Intel- ligence. The automatic generation of Collective Intelligence constitutes a departure from traditional methods for information sharing, since information from both the multimedia content and social aspects will be merged, while at the same time the social dynamics will be taken into account. In the context of this work, we present two case studies: an Emergency Response and a Consumers Social Group case study.