Pietro Cerri

Vehicle and Guard Rail Detection Using Radar and Vision Data Fusion

This paper describes a vehicle detection system fusing radar and vision data. Radar data are used to locate areas of interest on images. Vehicle search in these areas is mainly based on vertical symmetry. All the vehicles found in different image areas are mixed together, and a series of filters is applied in order to delete false detections. In order to speed up and improve system performance, guard rail detection and a method to manage overlapping areas are also included. Both methods are explained and justified in this paper. The current algorithm analyzes images on a frame-by-frame basis without any temporal correlation. Two different statistics, namely: 1) frame based and 2) event based, are computed to evaluate vehicle detection efficiency, while guard rail detection efficiency is computed in terms of time savings and correct detection rates. Results and problems are discussed, and directions for future enhancements are provided

Real Time Road Signs Recognition

This paper presents a road signs detection and classification system based on a three-step algorithm composed of color segmentation, shape recognition, and a neural network. The final goal of this algorithm is to detect and classify almost all road signs present along Italian roads. Color segmentation was suggested by the aim to achieve real time execution, since color-based segmentation is faster than the one based on shape. In order to save computational time, only the RGB color space, directly supplied by the chosen camera, or color spaces that can be obtained with linear transformations, are considered. Two different methods are used for shape detection, one is based on pattern matching with simple models and the other one is based on edge detection and geometrical cues. The complete set of signs taken in account has been divided in several categories according to their shape and color. Finally for each road signs set a neural network is built and trained.

Multi-resolution vehicle detection using artificial vision

This paper describes a vehicle detection system using a single camera. It is based on the search for areas with a high vertical symmetry in multi-resolution images; symmetry is computed using different sized boxes centered on all the columns of the interest areas. All the columns with high symmetry are analyzed to get the width of detected objects. Horizontal edges are examined to find the base of the vehicle in the individuated area. The aim is to find horizontal lines located below an area with sufficient amount of edges. The algorithm deletes all the bounding boxes which are too large, too small, or too far from the camera in order to decrease the number of false positives. All the results found in different interest areas are mixed together and the overlapping bounding boxes are localized and managed in order to delete false positives. The algorithm analyzes images on a frame by frame basis, without any temporal correlation.

A New Approach to Urban Pedestrian Detection for Automatic Braking

This paper presents an application of a pedestrian-detection system aimed at localizing potentially dangerous situations under specific urban scenarios. The approach used in this paper differs from those implemented in traditional pedestrian-detection systems, which are designed to localize all pedestrians in the area in front of the vehicle. Conversely, this approach searches for pedestrians in critical areas only. The environment is reconstructed with a standard laser scanner, whereas the following check for the presence of pedestrians is performed due to the fusion with a vision system. The great advantages of such an approach are that pedestrian recognition is performed on limited image areas, therefore boosting its timewise performance, and no assessment on the danger level is finally required before providing the result to either the driver or an onboard computer for automatic maneuvers. A further advantage is the drastic reduction of false alarms, making this system robust enough to control nonreversible safety systems.

Suspended traffic lights detection and distance estimation using color features

Traffic Light Detection is a problem differently approached by many research groups around the world. Here we present a novel technique to detect suspended traffic lights, based on colors and features such as black area of traffic lights or area of lighting lamps. Additionally, the traffic light distance is estimated aiming at slowing down and stopping in the correct position, in case of red light. Some preliminary test results are presented to assess both the detection rate and the distance estimation.

Obstacle detection and classification fusing radar and vision

This paper presents a system whose aim is to detect and classify road obstacles, like pedestrians and vehicles, by fusing data coming from different sensors: a camera, a radar, and an inertial sensor. The camera is mainly used to refine the vehiclespsila boundaries detected by the radar and to discard those who might be false positives; at the same time, a symmetry based pedestrian detection algorithm is executed, and its results are merged with a set of regions of interest, provided by a Motion Stereo technique.

Environment-Detection-and-Mapping Algorithm for Autonomous Driving in Rural or Off-Road Environment

This paper presents an environment-detection-and-mapping algorithm for autonomous driving that is provided in real time and for both rural and off-road environments. Environment-detection-and-mapping algorithms have been designed to consist of two parts: (1) lane, pedestrian-crossing, and speed-bump detection algorithms using cameras and (2) obstacle detection algorithm using LIDARs. The lane detection algorithm returns lane positions using one camera and the vision module “VisLab Embedded Lane Detector (VELD),” and the pedestrian-crossing and speed-bump detection algorithms return the position of pedestrian crossings and speed bumps. The obstacle detection algorithm organizes data from LIDARs and generates a local obstacle position map. The designed algorithms have been implemented on a passenger car using six LIDARs, three cameras, and real-time devices, including personal computers (PCs). Vehicle tests have been conducted, and test results have shown that the vehicle can reach the desired goal with the proposed algorithm.

VIAC: An out of ordinary experiment

This paper presents the preliminary results of VIAC, the VisLab Intercontinental Autonomous Challenge, a test of autonomous driving along an unknown route from Italy to China. It took 3 months to run the entire test; all data have been logged, including all data generated by the sensors, vehicle data, and GPS info. This huge amount of information has been packed during the trip, compressed, and transferred back to Parma for further processing. This data is now ready for a deep analysis of the various systems performance, with the aim of virtually running the whole trip multiple times with improved versions of the software. This paper discusses some preliminary figures obtained by the analysis of the data collected during the test. More information will be generated by a deeper analysis, which will take additional time, being the data about 40 terabyte in size.

Data fusion for overtaking vehicle detection based on radar and optical flow

Trustworthiness is a key point when dealing with vehicle safety applications. In this paper an approach to a real application is presented, able to fulfill the requirements of such demanding applications. Most of commercial sensors available nowadays are usually designed to detect front vehicles but lack the ability to detect overtaking vehicles. The work presented here combines the information provided by two sensors, a Stop&Go radar and a camera. Fusion is done by using the unprocessed information from the radar, and computer vision based on optical flow. The basic capabilities of the commercial systems are upgraded giving the possibility to improve the front vehicles detection system, by detecting overtaking vehicles with a high positive rate.

Localization and analysis of critical areas in urban scenarios

This paper presents an application of a pedestrian detection system aimed at localizing potentially dangerous situations in specific urban scenarios. The approach used in this work differs from the one implemented in traditional pedestrian detection systems, which are designed to localize all pedestrians appearing in the area in front of the vehicle. This application first locates critical areas in the urban environment, and then it searches for pedestrians in these areas only. The environment is reconstructed with a standard laser scanner system, while the following check for the presence of pedestrians is performed thanks to the fusion with a vision system. The great advantages of such an approach are that pedestrian recognition is performed on a very limited image area -therefore boosting its timing performance- and no assessment on the danger level is finally required before providing the result to either the driver or an on-board computer for automatic manoeuvres.