Javier Gonzalez-Jimenez

The Málaga urban dataset: High-rate stereo and LiDAR in a realistic urban scenario

This paper introduces a dataset gathered entirely in urban scenarios with a car equipped with one stereo camera and five laser scanners, among other sensors. One distinctive feature of the present dataset is the existence of high-resolution stereo images grabbed at a high rate (20 fps) during a 36.8 km trajectory, which allows the benchmarking of a variety of computer vision techniques. We describe the sensors employed and highlight some applications which could be benchmarked using the present work. Both plain text and binary files are provided, as well as open-source tools for working with the binary versions. The dataset is available for download at http://www.mrpt.org/MalagaUrbanDataset.

The Multi-Chamber Electronic Nose--an improved olfaction sensor for mobile robotics.

One of the major disadvantages of the use of Metal Oxide Semiconductor (MOS) technology as a transducer for electronic gas sensing devices (e-noses) is the long recovery period needed after each gas exposure. This severely restricts its usage in applications where the gas concentrations may change rapidly, as in mobile robotic olfaction, where allowing for sensor recovery forces the robot to move at a very low speed, almost incompatible with any practical robot operation. This paper describes the design of a new e-nose which overcomes, to a great extent, such a limitation. The proposed e-nose, called Multi-Chamber Electronic Nose (MCE-nose), comprises several identical sets of MOS sensors accommodated in separate chambers (four in our current prototype), which alternate between sensing and recovery states, providing, as a whole, a device capable of sensing changes in chemical concentrations faster. The utility and performance of the MCE-nose in mobile robotic olfaction is shown through several experiments involving rapid sensing of gas concentration and mobile robot gas mapping.

Fast place recognition with plane-based maps

This paper presents a new method for recognizing places in indoor environments based on the extraction of planar regions from range data provided by a hand-held RGB-D sensor. We propose to build a plane-based map (PbMap) consisting of a set of 3D planar patches described by simple geometric features (normal vector, centroid, area, etc.). This world representation is organized as a graph where the nodes represent the planar patches and the edges connect planes that are close by. This map structure permits to efficiently select subgraphs representing the local neighborhood of observed planes, that will be compared with other subgraphs corresponding to local neighborhoods of planes acquired previously. To find a candidate match between two subgraphs we employ an interpretation tree that permits working with partially observed and missing planes. The candidates from the interpretation tree are further checked out by a rigid registration test, which also gives us the relative pose between the matched places. The experimental results indicate that the proposed approach is an efficient way to solve this problem, working satisfactorily even when there are substantial changes in the scene (lifelong maps).

Overcoming the Slow Recovery of MOX Gas Sensors through a System Modeling Approach

Metal Oxide Semiconductor (MOX) gas transducers are one of the preferable technologies to build electronic noses because of their high sensitivity and low price. In this paper we present an approach to overcome to a certain extent one of their major disadvantages: their slow recovery time (tens of seconds), which limits their suitability to applications where the sensor is exposed to rapid changes of the gas concentration. Our proposal consists of exploiting a double first-order model of the MOX-based sensor from which a steady-state output is anticipated in real time given measurements of the transient state signal. This approach assumes that the nature of the volatile is known and requires a precalibration of the system time constants for each substance, an issue that is also described in the paper. The applicability of the proposed approach is validated with several experiments in real, uncontrolled scenarios with a mobile robot bearing an e-nose.

Time-variant gas distribution mapping with obstacle information

This paper addresses the problem of estimating the spatial distribution of volatile substances using a mobile robot equipped with an electronic nose. Our work contributes an effective solution to two important problems that have been disregarded so far: First, obstacles in the environment (walls, furniture,...) do affect the gas spatial distribution. Second, when combining odor measurements taken at different instants of time, their ‘ages’ must be taken into account to model the ephemeral nature of gas distributions. In order to incorporate these two characteristics into the mapping process we propose modeling the spatial distribution of gases as a Gaussian Markov random field. This mathematical framework allows us to consider both: (i) the vanishing information of gas readings by means of a time-increasing uncertainty in sensor measurements, and (ii) the influence of objects in the environment by means of correlations among the different areas. Experimental validation is provided with both, simulated and real-world datasets, demonstrating the out-performance of our method when compared to previous standard techniques in gas mapping.

A primal-dual framework for real-time dense RGB-D scene flow

This paper presents the first method to compute dense scene flow in real-time for RGB-D cameras. It is based on a variational formulation where brightness constancy and geometric consistency are imposed. Accounting for the depth data provided by RGB-D cameras, regularization of the flow field is imposed on the 3D surface (or set of surfaces) of the observed scene instead of on the image plane, leading to more geometrically consistent results. The minimization problem is efficiently solved by a primal-dual algorithm which is implemented on a GPU, achieving a previously unseen temporal performance. Several tests have been conducted to compare our approach with a state-of-the-art work (RGB-D flow) where quantitative and qualitative results are evaluated. Moreover, an additional set of experiments have been carried out to show the applicability of our work to estimate motion in real-time. Results demonstrate the accuracy of our approach, which outperforms the RGB-D flow, and which is able to estimate heterogeneous and non-rigid motions at a high frame rate.

Extrinsic calibration of a set of range cameras in 5 seconds without pattern

The integration of several range cameras in a mobile platform is useful for applications in mobile robotics and autonomous vehicles that require a large field of view. This situation is increasingly interesting with the advent of low cost range cameras like those developed by Primesense. Calibrating such combination of sensors for any geometric configuration is a problem that has been recently solved through visual odometry (VO) and SLAM. However, this kind of solution is laborious to apply, requiring robust SLAM or VO in controlled environments. In this paper we propose a new uncomplicated technique for extrinsic calibration of range cameras that relies on finding and matching planes. The method that we present serves to calibrate two or more range cameras in an arbitrary configuration, requiring only to observe one plane from different viewpoints. The conditions to solve the problem are studied, and several practical examples are presented covering different geometric configurations, including an omnidirectional RGB-D sensor composed of 8 range cameras. The quality of this calibration is evaluated with several experiments that demonstrate an improvement of accuracy over design parameters, while providing a versatile solution that is extremely fast and easy to apply.

An Instrumented Vehicle for Efficient and Accurate 3D Mapping of Roads

An electric vehicle equipped with a laser scanner and a highly accurate absolute positioning system aimed at surveying the geometry of roads is described in this article. The main advantages of the proposed system with respect to conventional topographic procedures are the possibility of achieving a much higher density of surveyed points and its efficiency while keeping almost the same accuracy—a standard deviation of 12 mm of absolute error. The data acquisition process is managed by an on-board computer which, in a synchronized way, deals with laser scanning and readings from three real-time-kinematics-enabled millimeter global positioning system (GPS) receivers. The three-dimensional position and orientation of the vehicle (6 degrees of freedom) all along its trajectory is calculated off-line by a custom software. The system also obtains the absolute coordinates of the road scanned points with that information that was obtained from the software. A rigorous description regarding the theory behind the 3D reconstruction and the calibration process is also presented in the article.

Fast Visual Odometry for 3-D Range Sensors

This paper presents a new dense method to compute the odometry of a free-flying range sensor in real time. The method applies the range flow constraint equation to sensed points in the temporal flow to derive the linear and angular velocity of the sensor in a rigid environment. Although this approach is applicable to any range sensor, we particularize its formulation to estimate the 3-D motion of a range camera. The proposed algorithm is tested with different image resolutions and compared with two state-of-the-art methods: generalized iterative closest point (GICP) [1] and robust dense visual odometry (RDVO) [2]. Experiments show that our approach clearly overperforms GICP which uses the same geometric input data, whereas it achieves results similar to RDVO, which requires both geometric and photometric data to work. Furthermore, experiments are carried out to demonstrate that our approach is able to estimate fast motions at 60 Hz running on a single CPU core, a performance that has never been reported in the literature. The algorithm is available online under an open source license so that the robotic community can benefit from it.

An Alternative to the Mahalanobis Distance for Determining Optimal Correspondences in Data Association

The most common criteria to determine data association rely on minimizing the squared Mahalanobis distance (SMD) between observations and predictions. We hold that the SMD is just a heuristic, while the alternative matching likelihood is the optimal statistic to be maximized. Thorough experiments undoubtedly confirm this idea, with false positive reductions of up to 16%.