scispace - formally typeset
Search or ask a question

Showing papers by "Ivan Petrović published in 2015"


Proceedings ArticleDOI
01 Jan 2015
TL;DR: A novel algorithm for fast and robust stereo visual odometry based on feature selection and tracking (SOFT), which employs an IMU for outlier rejection and Kalman filter for rotation refinement and which outperforms all other validated methods.
Abstract: In this paper we present a novel algorithm for fast and robust stereo visual odometry based on feature selection and tracking (SOFT). The reduction of drift is based on careful selection of a subset of stable features and their tracking through the frames. Rotation and translation between two consecutive poses are estimated separately. The five point method is used for rotation estimation, whereas the three point method is used for estimating translation. Experimental results show that the proposed algorithm has an average pose error of 1.03% with processing speed above 10 Hz. According to publicly available KITTI leaderboard, SOFT outperforms all other validated methods. We also present a modified IMU-aided version of the algorithm, fast and suitable for embedded systems. This algorithm employs an IMU for outlier rejection and Kalman filter for rotation refinement. Experiments show that the IMU based system runs at 20 Hz on an ODROID U3 ARM-based embedded computer without any hardware acceleration. Integration of all components is described and experimental results are presented.

118 citations


Journal ArticleDOI
TL;DR: A place recognition method is presented that is based on matching sets of surface and line features extracted from depth images provided by a 3D camera to features of the same type contained in a previously created environment model.
Abstract: This paper considers the potential of using three-dimensional 3D planar surfaces and line segments detected in depth images for place recognition. A place recognition method is presented that is based on matching sets of surface and line features extracted from depth images provided by a 3D camera to features of the same type contained in a previously created environment model. The considered environment model consists of a set of local models representing particular locations in the modeled environment. Each local model consists of planar surface segments and line segments representing the edges of objects in the environment. The presented method is designed for indoor and urban environments. A computationally efficient pose hypothesis generation approach is proposed that ranks the features according to their potential contribution to the pose information, thereby reducing the time needed for obtaining accurate pose estimation. Furthermore, a robust probabilistic method for selecting the best pose hypothesis is proposed that allows matching of partially overlapping point clouds with gross outliers. The proposed approach is experimentally tested on a benchmark dataset containing depth images acquired in the indoor environment with changes in lighting conditions and the presence of moving objects. A comparison of the proposed method to FAB-MAP and DLoopDetector is reported.

24 citations


Journal ArticleDOI
TL;DR: This letter proposes a novel mixture approximation of the probability hypothesis density filter based on the von Mises distribution, thus constructing a method that globally captures the non-Euclidean nature of the state and the measurement space.
Abstract: This letter deals with the problem of tracking multiple targets on the unit circle, a problem that arises whenever the state and the sensor measurements are circular, i.e. angular-only, random variables. To tackle this problem, we propose a novel mixture approximation of the probability hypothesis density filter based on the von Mises distribution, thus constructing a method that globally captures the non-Euclidean nature of the state and the measurement space. We derive a closed-form recursion of the filter and apply principled approximations where necessary. We compared the performance of the proposed filter with the Gaussian mixture probability hypothesis density filter on a synthetic dataset of 100 randomly generated multitarget trajectory examples corrupted with noise and clutter, and on the PETS2009 dataset. We achieved respectively a decrease of 10.5% and 2.8% in the optimal subpattern assignement metric (notably 16.9% and 10.8% in the localization component).

24 citations


Journal ArticleDOI
TL;DR: Using single video camera and with no a priori knowledge of the environment it is shown that it is possible to constrain the inertial navigation position, velocity and attitude divergence while moving in vicinity of a map point.

22 citations


Proceedings ArticleDOI
01 Sep 2015
TL;DR: In this article, a novel algorithm for moving object detection in thermal images taken by a moving thermal camera is presented, which uses fusion of an inertial measurement unit (IMU) and a thermal camera.
Abstract: In this paper we present a novel algorithm for moving object detection in thermal images taken by a moving thermal camera. It allows a detection of moving objects in thermal images of low quality without imposing restrictions on the temperature and/or shape of the object. The main assumption required for good performance of the algorithm is that the transversal movement of the vehicle will not produce significant change in the optical flow of the static objects in the scene between two consecutive image frames. Our algorithm does not use any temperature thresholds and works well in urban environments detecting moving humans and other moving objects as well. To achieve this we use fusion of an inertial measurement unit (IMU) and a thermal camera. First we use IMU data to compensate for rotational movements of the thermal camera between two consecutive thermal images. Then we differentiate those images and filter the resulting image based on dense optical flow calculated using Farneback technique. After that moving objects are detected and further filtering is applied using random sampling consensus algorithm based on optical flow model.

7 citations


Proceedings ArticleDOI
13 Apr 2015
TL;DR: A model predictive control (MPC) strategy for energy efficient management of heating and cooling of a house that can cope with the nonlinearities in the system induced by the use of modern construction materials is proposed.
Abstract: The reduction of energy consumption in residential buildings and houses represents a major societal and environmental challenge. A huge portion of energy consumption in houses and buildings goes towards comfort control — heating, ventilation and air conditioning. Modern architecture tackles these problems by considering (i) passive exploitation of solar energy and (ii) use of special construction materials that often have quite complex characteristics. Therefore, a smart energy management control system should be able to take both of these considerations into account. This paper proposes a model predictive control (MPC) strategy for energy efficient management of heating and cooling of a house that can cope with the nonlinearities in the system induced by the use of modern construction materials. Furthermore, the proposed controller takes into account the weather forecast information, in particular the prediction of solar irradiance and air temperature. The nonlinear behavior of the system is approximated by a piecewise affine model and further incorporated into the mixed logical dynamical framework. The performance of the proposed nonlinear MPC is demonstrated in simulation experiments, which show applicability and usefulness of the MPC algorithm for energy management.

2 citations