Timezone: »
Our demonstration shows a vision-based system that addresses a challenging and rarely addressed problem for self-driving cars: the detection of generic, small, and unexpected road hazards, such as lost cargo. To the best of our knowledge, our proposed approach to this unsolved problem is the first that leverages both, appearance and contextual cues via a deep convolutional neural network and geometric cues from a stereo-based approach, all combined in a Bayesian framework. Our visual detection framework achieves a very high detection performance with low false positive rates and proves to be robust to illumination changes, varying road appearance as well as 3D road profiles. Our system is able to reliably detect critical obstacles of very low heights (down to 5cm) even at large distances (up to 100m), operating at 22 Hz on our self-driving platform.
Author Information
Sebastian Ramos (Daimler AG R&D)
I am a fourth year computer science Ph.D. student at both the Image Understanding Group at Daimler AG R&D and the Computer Vision Lab at TU Dresden under the supervision of Dr. Uwe Franke and Prof. Carsten Rother, respectively. Before, I spent two years as a Ph.D. student at the Advanced Driver Assistance Systems Group (ADAS) at Computer Vision Center (CVC) in Barcelona under the supervision of Prof. Antonio M. López (Jan 2013 - Feb 2015). During my studies, I have also spent time as a research intern at the Image Understanding Group at Daimler AG R&D (Jul - Dic 2014), research assistant at the Automatic Control Group at National University of Colombia (May - Nov 2012), visiting student at the LSR Institute at TU Munich (Sept 2010 - Mar 2012) and research intern at the Robotics Group at Siemens AG R&D (Mar - Jul 2011). I obtained my Master's degree in computer vision from Autonomous University of Barcelona (UAB) and my Bachelor's degree in electronic engineering from National University of Colombia (UNAL). My research interests are in computer vision, machine learning and robotics with a special focus on visual scene understanding for autonomous driving.
Peter Pinggera (Daimler R&D)
stefan gehrig (daimler ag)
Daimler AG (Uwe Franke)
Carsten Rother (Microsoft Research Cambridge)
More from the Same Authors
-
2016 Demonstration: Detecting Unexpected Obstacles for Self-Driving Cars: Fusing Deep Learning and Geometric Modeling »
Sebastian Ramos · Peter Pinggera · stefan gehrig · Daimler AG · Carsten Rother -
2011 Poster: Recovering Intrinsic Images with a Global Sparsity Prior on Reflectance »
Peter Gehler · Carsten Rother · Martin Kiefel · Lumin Zhang · Bernhard Schölkopf -
2006 Poster: Clustering appearance and shape by learning jigsaws »
Anitha Kannan · John Winn · Carsten Rother -
2006 Talk: Clustering appearance and shape by learning jigsaws »
Anitha Kannan · John Winn · Carsten Rother