Cristiano Premebida

Learn More
In this report some algorithms for 2D segmentation, feature detection and fitting are presented. The features discussed here consist of three geometric primitives: lines, circles and ellipses. The segmentation process, whose objective is grouping segments that belong to the same object, is analysed using several kinds of algorithms. Results are presented(More)
— This paper presents a sensorial-cooperative architecture to detect, track and classify entities in semi-structured outdoor scenarios for intelligent vehicles. In order to accomplish this task, information provided by in-vehicle Lidar and monocular vision is used. The detection and tracking phases are performed in the laser space, and the object(More)
A perception system for pedestrian detection in urban scenarios using information from a LIDAR and a single camera is presented. Two sensor fusion architectures are described, a centralized and a decentralized one. In the former, the fusion process occurs at the feature level, i.e., features from LIDAR and vision spaces are combined in a single vector for(More)
— A multi-module architecture to detect, track and classify objects in semi-structured outdoor scenarios for intelligent vehicles is proposed in this paper. In order to fulfill this task it was used the information provided by a laser range finder (LRF) and a monocular camera. The detection and tracking phases are performed in the LRF space, and the object(More)
— Why is pedestrian detection still very challenging in realistic scenes? How much would a successful solution to monocular depth inference aid pedestrian detection? In order to answer these questions we trained a state-of-the-art deformable parts detector using different configurations of optical images and their associated 3D point clouds, in conjunction(More)
— In this work, we propose an approach that relies on cues from depth perception from RGB-D images, where features related to human body motion (3D skeleton features) are used on multiple learning classifiers in order to recognize human activities on a benchmark dataset. A Dynamic Bayesian Mixture Model (DBMM) is designed to combine multiple classifier(More)
In this work, a context-based multisensor system, applied for pedestrian detection in urban environment, is presented. The proposed system comprises three main processing modules: (i) a LIDAR-based module acting as primary object detection, (ii) a module which supplies the system with contextual information obtained from a semantic map of the roads, and(More)
— In this paper we present a multistage method applied in pedestrian detection using information from a LIDAR and a monocular-camera mounted on an electric vehicle driving in urban scenarios. The proposed method is a cascade of classifiers trained in two subsets of features, one with laser-based features and the other with a set of image-based features. A(More)
— Many robotic systems combine cameras with Laser Rangefinders (LRF) for simultaneously achieving multipurpose visual sensing and accurate depth recovery. Employing a single sensor modality for accomplishing both goals is an appealing proposition because it enables substantial savings in equipment, and tends to decrease the overall complexity of the system.(More)