IVVI 2.0: An intelligent vehicle based on computational perception

Abstract

This is a postprint version of the following published document: Martín, D., et al. (2014) a b s t r a c tThis paper presents the IVVI 2.0 a smart research platform to foster intelligent systems in vehicles. Com putational perception in intelligent transportation systems applications has advantages, such as huge data from vehicle environment, among others, so computer vision systems and laser scanners are the main devices that accomplish this task. Both have been integrated in our intelligent vehicle to develop cutting edge applications to cope with perception difficulties, data processing algorithms, expert knowl edge, and decision making. The long term in vehicle applications, that are presented in this paper, out perform the most significant and fundamental technical limitations, such as, robustness in the face of changing environmental conditions. Our intelligent vehicle operates outdoors with pedestrians and oth ers vehicles, and outperforms illumination variation, i.e.: shadows, low lighting conditions, night vision, among others. So, our applications ensure the suitable robustness and safety in case of a large variety of lighting conditions and complex perception tasks. Some of these complex tasks are overcome by the improvement of other devices, such as, inertial measurement units or differential global positioning sys tems, or perception architectures that accomplish sensor fusion processes in an efficient and safe manner. Both extra devices and architectures enhance the accuracy of computational perception and outreach the properties of each device separately.

Stereo visual odometry in urban environments based on detecting ground features

“…That is why another sensor is needed and here is where digital cameras can play an important role. On one hand because, as it will be shown, they are useful for obtaining the vehicle's ego motion and, on the other hand, because nowadays they are already used for other tasks such as pedestrian, traffic sign or road lane detection [1], accordingly it is a sensor that can be applied for multiple assignments. Visual Odometry (VO) estimates the ego motion of a camera or a set of cameras mounted on a vehicle using only the visual information provided by it or them.…”

Computer Vision Applied to Road Lines Recognition Using Machine Learning

“…This paper presents the Road Lane Classification module of the IvvI 2.0 project (Intelligent Vehicle based on Visual Information) [12]. Its goal is to automatically detect the position, type, and number of the road lanes with a stereo onboard camera inside of the Intelligent System Lab at Carlos III University experimental vehicle.…”

Motorcycle detection for ADAS through camera and V2V Communication, a comparative analysis of two modern technologies

“…The different technologies developed are later tested and compared, and the results are shown in this paper. All the tests are performed under real road conditions in the platform Intelligent Vehicle based on Visual Information 2.0 (IWI 2.0) (Carmona, García, Martín, Escalera Ade, & Armingol, 2015;Martín et al, 2014), and the test motorcycle shown in Fig. 1.…”