No abstract

No abstract

Abstract-Obstacle detection by means of stereo-vision is a fundamental task in computer vision, which has spurred a lot of research over the years, especially in the field of vehicular robotics. The information provided by this class of algorithms is used both in driving assistance systems and in autonomous vehicles, so the quality of the results and the processing times become critical, as detection failures or delays can have serious consequences. The obstacle detection system presented in this paper has been extensively tested during VIAC, the VisLab Intercontinental Autonomous Challenge [1], [2], which has offered a unique chance to face a number of different scenarios along the roads of two continents, in a variety of conditions; data collected during the expedition has also become a reference benchmark for further algorithm improvements.

No abstract

This paper describes a framework used to develop and run automotive applications both on board of vehicles and in laboratory. It includes the recording system designed and implemented in the GOLD framework. The system can record data from different sensors, such as cameras, laserscanners, radars, GPS, IMU, IO boards. The system can easily be expanded adding new device drivers. An in-RAM prerecording functionality is available to let the user record events started in the past. An index file collects essential information on each recorded event, such as timestamp, source identifier, and other sourcespecific data. Different file formats can be used to store data on disks; standard file formats are available for images and audio, small data such as CAN messages or GPS data are recorded directly into the index file. In order to have a faster lookup of a particular scene, the system is also equipped with a user interface that allows to insert tags during the recording. This system has been under development and successfully employed in the last 15 years to acquiring data for several VisLab projects. The description of two case studies is included in this paper. BRAiVE is an advanced prototype used as mobile laboratory to acquire data for different purposes. VIAC is a trip from Parma, Italy, to Shanghai, China, performed to test the robustness of VisLab driving assistance systems; the autonomous driving sessions have been recorded generating a unique database suitable to study and possibly improve the algorithm performance.