Elena Cardarelli

Toward automated driving in cities using close-to-market sensors: An overview of the V-Charge Project

Future requirements for drastic reduction of CO2 production and energy consumption will lead to significant changes in the way we see mobility in the years to come. However, the automotive industry has identified significant barriers to the adoption of electric vehicles, including reduced driving range and greatly increased refueling times. Automated cars have the potential to reduce the environmental impact of driving, and increase the safety of motor vehicle travel. The current state-of-the-art in vehicle automation requires a suite of expensive sensors. While the cost of these sensors is decreasing, integrating them into electric cars will increase the price and represent another barrier to adoption. The V-Charge Project, funded by the European Commission, seeks to address these problems simultaneously by developing an electric automated car, outfitted with close-to-market sensors, which is able to automate valet parking and recharging for integration into a future transportation system. The final goal is the demonstration of a fully operational system including automated navigation and parking. This paper presents an overview of the V-Charge system, from the platform setup to the mapping, perception, and planning sub-systems.

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.

Development of the control system for the Vislab Intercontinental Autonomous Challenge

This paper presents the control system of an autonomous vehicle capable of perceiving and describing the environment using different inputs, such as GPS waypoints, roadways borders and lines, leader vehicles, and obstacles to be avoided. The controller has been implemented and tested for the VisLab Intercontinental Autonomous Challenge, a long intercontinental trip that aims to demonstrate capabilities of modern autonomous vehicles. To fulfill this mission a general-purpose real-time motion planning system was designed and implemented. This pathplanner, based on the estimation of feasible trajectories on a cost map, is described and analyzed. System performance has been evaluated during tests: experimental results have demonstrated the capability of the system in vehicle following.

Real time road signs classification

This paper describes a method for classifying road signs based on a single color camera mounted on a moving vehicle. The main focus will be on the final neural network based classification stage of the candidates provided by an existing traffic sign detection algorithm. Great attention is paid to image preprocessing in order to provide a more simple and clear input to the network: candidate color images are cropped and converted to greyscale, then enhanced using a contrast stretching technique; a multi-layer perceptron neural network is then used to provide a matching score with different road sign models. Finally results are filtered using tracking. Benchmarks are presented, showing that the system is able to classify more then 200 different Italian road sign in real-time, with a recognition rate of 80% to 90%.

Terrain mapping for off-road Autonomous Ground Vehicles using rational B-Spline surfaces and stereo vision

Autonomous Ground Vehicles designed for extreme environments (e.g mining, constructions, defense, exploration applications) require a reliable estimation of terrain traversability, in terms of both terrain slope and obstacles presence. In this paper we present a new technique to build, in real time and only from a 3D points cloud, a dense terrain elevation map able to: 1) provide slope estimation; 2) provide a reference for segmenting points into terrains inliers and outliers, to be then used for obstacles detection. The points cloud is first smartly sampled into a 2.5 grid map, then samples are fitted into a rational B-Spline surface by means of re-weighted least square fitting and equalization. To meet an extensive range of extreme off-road scenarios, no assumptions on vehicle pose are made and no road infrastructure or a-priori knowledge about terrain appearance and shape is required. The algorithm runs in real time; it has been tested on one of VisLabs AGVs using a modified SGM-based stereo system as 3D data source.

Vehicle detection for autonomous parking using a Soft-Cascade AdaBoost classifier

This paper presents a monocular algorithm for front and rear vehicle detection, developed as part of the FP7 V-Charge projects perception system. The system is made of an AdaBoost classifier with Haar Features Decision Stump. It processes several virtual perspective images, obtained by un-warping 4 monocular fish-eye cameras mounted all-around an autonomous electric car. The target scenario is the automated valet parking, but the presented technique fits well in any general urban and highway environment. A great attention has been given to optimize the computational performance. The accuracy in the detection and a low computation costs are provided by combining a multiscale detection scheme with a Soft-Cascade classifier design. The algorithm runs in real time on the projects hardware platform. The system has been tested on a validation set, compared with several AdaBoost schemes, and the corresponding results and statistics are also reported.

An algorithm for Italian de-restriction signs detection

Color has proved to be an important feature to be exploited for road signs detection on images; however, not all road signs have distinctive color characteristics. This paper presents a shape-based approach for Italian de-restriction signs detection; the developed algorithm uses a black band extractor to highlight regions of interest, where a circle shape detection is performed. Tracking is used in order to increase reliability. The obtained detector is robust to different illumination conditions and shadows, and can manage different kinds of noise and perturbation. Despite its sensitiveness, the detector showed few false positives during performed tests.

GPU implementation of a road sign detector based on particle swarm optimization

Road Sign Detection is a major goal of the Advanced Driving Assistance Systems. Most published work on this problem share the same approach by which signs are first detected and then classified in video sequences, even if different techniques are used. While detection is usually performed using classical computer vision techniques based on color and/or shape matching, most often classification is performed by neural networks. In this work we present a novel modular and scalable approach to road sign detection based on Particle Swarm Optimization, which takes into account both shape and color to detect signs. In our approach, in particular, the optimization of a single fitness function allows both to detect a sign belonging to a certain category and, at the same time, to estimate its position with respect to the camera reference frame. To speed up processing, the algorithm implementation exploits the parallel computing capabilities offered by modern graphics cards and, in particular, by the Compute Unified Device Architecture by nVIDIA. The effectiveness of the approach has been assessed on both synthetic and real video sequences, which have been successfully processed at, or close to, full frame rate.

Road signs shapes detection based on Sobel phase analysis

This paper presents a method for triangular and rectangular shapes detection in a road sign recognition system based on a three step algorithm: color segmentation, shape detection and neural network classification. The shape detector is based on the evaluation of the Sobel edges and Hough images in a region of interest detected by the color-based stage. During the tests performed the shape detector shows its robustness to rotation, occlusion and deformation, despite a 10% increasing of total computational times compared with that requested by the pattern matching.

A validation tool for traffic signs recognition systems

During the last few years many Advanced Driver Assistant Systems have been developed and a larger number of new car models every year is going to be equipped with these systems. However the product/function scenario lacks of common evaluation methodologies and tools for testing and improving performances of these systems. In this paper a validation methodology and a tool for Traffic Sign Recognition Systems evaluation (TSRs) is described.