José-Joel González-Barbosa

Rover localization in natural environments by indexing panoramic images

In this paper, we present an approach to qualitative rover localization with panoramic images. The approach relies on the possibility to efficiently and robustly compute the resemblance between panoramic images, indexing them by histograms of local appearances. A database of image indexes is dynamically built during rover motions: when the rover re-perceives an already crossed area, it matches the current image with the stored ones (place recognition), and thus gets a qualitative estimate of its position. Experimental results on a 400 images database illustrates the effectiveness of the algorithms.

LIDAR Velodyne HDL-64E Calibration Using Pattern Planes

This work describes a method for calibration of the Velodyne HDL-64E scanning LIDAR system. The principal contribution was expressed by a pattern calibration signature, the mathematical model and the numerical algorithm for computing the calibration parameters of the LIDAR. In this calibration pattern the main objective is to minimize systematic errors due to geometric calibration factor. It describes an algorithm for solution of the intrinsic and extrinsic parameters. Finally, its uncertainty was calculated from the standard deviation of calibration result errors.

Optimal camera placement for total coverage

In this document, we study the problem of optimally placing a mixture of directional and omnidirectional cameras. In our solution, the workspace is represented by an occupancy grid map [1]. Then, using surface-projected workspace and camera perception models, we develop a binary integer programming algorithm. The results of the algorithm are applied successfully to a variety of simulated scenarios.

Fast Dense Panoramic Stereovision

The particular geometry of panoramic cameras defines complex epipolar lines equations. In this paper, we present a way to warp images from a panoramic stereovision bench, so that the epipolar lines become parallel straight lines, thus allowing the use of an optimized fast pixel correlation based stereovision algorithm. The paper first introduces the geometric characterization of panoramic camera composed of parabolic and spherical mirrors, that computes both the intrinsic parameters of the system (mirror surfaces and intrinsic camera parameters) and the errors alignment between the mirrors. Then, it presents the warping equations that allow to generate rectified images. Calibration and stereovision results are presented.

Detecting abnormal vehicular dynamics at intersections based on an unsupervised learning approach and a stochastic model.

This investigation demonstrates an unsupervised approach for modeling traffic flow and detecting abnormal vehicle behaviors at intersections. In the first stage, the approach reveals and records the different states of the system. These states are the result of coding and grouping the historical motion of vehicles as long binary strings. In the second stage, using sequences of the recorded states, a stochastic graph model based on a Markovian approach is built. A behavior is labeled abnormal when current motion pattern cannot be recognized as any state of the system or a particular sequence of states cannot be parsed with the stochastic model. The approach is tested with several sequences of images acquired from a vehicular intersection where the traffic flow and duration used in connection with the traffic lights are continuously changed throughout the day. Finally, the low complexity and the flexibility of the approach make it reliable for use in real time systems.

LIDAR and Panoramic Camera Extrinsic Calibration Approach Using a Pattern Plane

Mobile platforms typically combine several data acquisition systems such as lasers, cameras and inertial systems. However the geometrical combination of the different sensors requires their calibration, at least, through the definition of the extrinsic parameters, i.e., the transformation matrices that register all sensors in the same coordinate system. Our system generate an accurate association between platform sensors and the estimated parameters including rotation, translation, focal length, world and sensors reference frame. The extrinsic camera parameters are computed by Zhang’s method using a pattern composed of white rhombus and rhombus holes, and the LIDAR with the results of previous work. Points acquired by the LIDAR are projected into images acquired by the Ladybug cameras. A new calibration pattern, visible to both sensors is used. Correspondence is obtained between each laser point and its position in the image, the texture and color of each point of LIDAR can be know.

Error propagation and uncertainty analysis between 3D laser scanner and camera

In this work we present an in-situ method to compute the calibration of two sensors, a LIDAR (Light Detection and Ranging) and a spherical camera. Both sensors are used in urban environment reconstruction tasks. In this scenario the speed at which the various sensors acquire and merge the information is very important; however reconstruction accuracy, which depends on sensors calibration, is also of high relevance. Here, a new calibration pattern, visible to both sensors is proposed. By this means, the correspondence between each laser point and its position in the camera image is obtained so that the texture and color of each LIDAR point can be known. Experimental results for the calibration and uncertainty analysis are presented for data collected by the platform integrated with a LIDAR and a spherical camera. We calibrated two different kinds of sensors, LIDAR and camera.We calculated the uncertainty analysis between both sensors.The performance of the error propagation is computed.We develop a new algorithm to obtain the extrinsic parameters of the LIDAR sensor.A new calibration pattern is used.

A Panoramic 3D Reconstruction System Based on the Projection of Patterns

This work presents the implementation of a 3D reconstruction system capable of reconstructing a 360-degree scene with a single acquisition using a projection of patterns. The system is formed by two modules: the first module is a CCD camera with a parabolic mirror that allows the acquisition of catadioptric images. The second module consists of a light projector and a parabolic mirror that is used to generate the pattern projections over the object that will be reconstructed. The projection system has a 360-degree field of view and both modules were calibrated to obtain the extrinsic parameters. To validate the functionality of the system, we performed 3D reconstructions of three objects, and show the reconstruction error analysis.

Vision system for 3d reconstruction with telecentric lens

This paper addresses 3D object reconstruction from images acquired by camera-telecentric lense array. Firstly, we present a geometric model of an array camera-telecentric lens. Then we developed and implemented the calibration process using a planar checkerboard pattern. At the same time, we developed a three-dimensional reconstruction system based on contour extraction on objects with dimensions less than 50mm of diameter. Finally an analysis of the uncertainty model parameters and performance reconstruction of 3D objects are presented.

A double layer background model to detect unusual events

A double layer background representation to detect novelty in image sequences is shown. The model is capable of handling non-stationary scenarios, such as vehicle intersections. In the first layer, an adaptive pixel appearance background model is computed. Its subtraction with respect to the current image results in a blob description of moving objects. In the second layer, motion direction analysis is performed by a Mixture of Gaussians on the blobs. We have used both layers for representing the usual space of activities and for detecting unusual activity. Our experiments clearly showed that the proposed scheme is able to detect activities such as vehicles running on red light or making forbidden turns.