A5027145099- Robotics and Sensor-Based Localization
- Advanced Vision and Imaging
- Robotic Path Planning Algorithms
- Autonomous Vehicle Technology and Safety
- Video Surveillance and Tracking Methods
- Advanced Neural Network Applications
- Electrical Contact Performance and Analysis
- Image Processing Techniques and Applications
- Surface Roughness and Optical Measurements
- Railway Engineering and Dynamics
- Industrial Vision Systems and Defect Detection
University of Parma
2013-2014
One of the most important features for any intelligent ground vehicle is based on how reliable and complete perception environment capability to discriminate what an obstacle is. Obstacle Detection (OD) one widely discussed topics in literature. Many approaches have been presented different application fields scenarios; last years them revisited using stereo vision or 2D/3D sensor technologies. In this paper we present a brief survey about techniques vehicles, describing comparing...
Autonomous Ground Vehicles designed for dynamic environments require a reliable perception of the real world, in terms obstacle presence, position and speed. In this paper we present flexible technique to build, time, dense voxel-based map from 3D point cloud, able to: (1) discriminate between stationary moving obstacles; (2) provide an approximation detected obstacle's absolute speed using information vehicle's egomotion computed through visual odometry approach. The cloud is first sampled...
Autonomous Ground Vehicles designed for extreme environments (e.g mining, constructions, defense, exploration applications) require a reliable estimation of terrain traversability, in terms both slope and obstacles presence. In this paper we present new technique to build, real time only from 3D points cloud, dense elevation map able to: 1) provide estimation; 2) reference segmenting into terrain's inliers outliers, be then used detection. The cloud is first smartly sampled 2.5 grid map,...
This paper presents a monocular algorithm for front and rear vehicle detection, developed as part of the FP7 V-Charge project's perception system. The system is made an AdaBoost classifier with Haar Features Decision Stump. It processes several virtual perspective images, obtained by un-warping 4 fish-eye cameras mounted all-around autonomous electric car. target scenario automated valet parking, but presented technique fits well in any general urban highway environment. A great attention...
This paper describes Pantobot-3D, a vision-based monitoring system for rail pantograph inspection developed by Camlin Italy srl, part of Group. The is based on an automatic algorithm able to provide: fully three-dimensional representation the using stereo cameras, model classification, and integrity assessment main components, e.g. horns strips. provides details architecture, overview each functionality performance. Presently, two installations Pantobot-3D are mainline Italian High Speed...