53 research outputs found
The Driving School System: Learning Basic Driving Skills From a Teacher in a Real Car
No full textTo offer increased security and comfort, advanced driver-assistance systems (ADASs) should consider individual driving styles. Here, we present a system that learns a human's basic driving behavior and demonstrate its use as ADAS by issuing alerts when detecting inconsistent driving behavior. In contrast to much other work in this area, which is based on or obtained from simulation, our system is implemented as a multithreaded parallel central processing unit (CPU)/graphics processing unit (GPU) architecture in a real car and trained with real driving data to generate steering and acceleration control for road following. It also implements a method for detecting independently moving objects (IMOs) for spotting obstacles. Both learning and IMO detection algorithms are data driven and thus improve above the limitations of model-based approaches. The system's ability to imitate the teacher's behavior is analyzed on known and unknown streets, and results suggest its use for steering assistance but limit the use of the acceleration signal to curve negotiation. We propose that this ability to adapt to the driver can lead to better acceptance of ADAS, which is an important sales argument.sponsorship: Sponsored by: IEEE Intelligent Transportation Systems Society
This work was supported in part by the European Commission under Project FP6-IST-FET (DRIVSCO) and in part by the Bernstein Focus Neurotechnology (BFNT) Göttingen.
I. Markelic and F. Wörgötter are with Georg-August-University Göttingen, 37077 Göttingen, Germany (e-mail: [email protected]; [email protected]).
A. Kjær-Nielsen, L. Baunegaard With Jensen, and N. Krüger are with Maersk McKinney Moller Institute, University of Southern Denmark, 5230 Odense, Denmark (e-mail: [email protected]; [email protected]; [email protected]).
K. Pauwels, N. Chumerin, and M. Van Hulle are with Katholieke Universiteit, Leuven, 3000 Leuven, Belgium (e-mail: [email protected];
[email protected]; [email protected]).
A. Rotter is with Hella KGaA Hueck & Co, 59552 Lippstadt, Germany (e-mail: [email protected]).
A. Vidugiriene and M. Tamosiunaite are with Vytautas Magnus
University, 44248 Kaunas, Lithuania (e-mail: [email protected]; [email protected]).status: Publishe
Convolutional Network for Vergence Control
No full textWe present a biologically-inspired model for the one-shot vergence control of a robotic head, which has been used for an investigation of two vergence control networks. Both networks do not work with explicitly computed disparity, but extract the vergence control signal from the postprocessed response of a population of disparity tuned complex cells, the actual gaze direction and the actual vergence angle. Training and evaluation of the networks are also discussed.sponsorship: EU Project FP7-ICT-217077 EYESHOTSstatus: Publishe
Learning Eye Vergence Control from a Distributed Disparity Representation
No full textWe present two neural models for vergence angle control of a
robotic head, a simplified and a more complex one. Both models work in a closed-loop manner and do not rely on
explicitly computed disparity, but extract the desired vergence angle from the post-processed response of a population of disparity tuned complex cells, the actual gaze direction and the actual vergence angle. The first model assumes that the gaze direction of the robotic head is
orthogonal to its baseline and the stimulus is a frontoparallel plane, thus, also orthogonal to the gaze direction. The second model goes beyond these assumptions, and operates reliably in the general case where all restrictions on the orientation of the gaze,
as well as the stimulus position, type and orientation, are dropped.sponsorship: This work has been partially supported by the EU Project FP7-ICT-217077.status: Publishe
Van Multikanaals Visie Naar Actieve Exploratie
No full textThis thesis is a collection of three studies investigating the multi-channel processing of visual information in biologically-inspired computer vision systems. These three studies are interconnected and supported by an auxiliary work on object recognition.The first study (Chapter 2) is focused on a biologically-inspired multichannel vision approach to independent motion detection (IMD). The goal is to detect objects that move independently from the moving observer. For example, a video camera mounted in a car "sees" a constantly moving environment while the car is driving. In this case, the motion (perceived by the camera) is caused by the self-motion of the car and the independent motion of other objects (e.g., vehicles or pedestrians). The task then is to differentiate the independently moving object (IMOs) from the motion induced by the moving observer in the (static with respect to Earth) environment. In this chapter we propose an approach for IMD, which uses several channels extracted from the input visual stream to create a so-called independent motion (IM) map, which is a map where the intensity of each pixel encodes the likelihood of the pixel being a part of an IMO. Several extensions of the proposed IMD model are presented and described in this study. All these extended models involve an additional appearance-based object recognition channel, which is used to upgrade the representation of the detected independent motion from the pixel-based formto the object-based (set of IMO locations and descriptions) one.In the second study (Chapter 4) we move from the passive exploration of the surrounding world, addressed in the previous study, towards an active exploration. By the active exploration here we mean the ability of the system to move (or, more precisely, rotate) both cameras of the considered stereo setup. As a first step towards a complete active exploration scenario, we considered its simplified case of horizontal vergence control (VC). The goal of the latter is to verge both cameras on the target object. By vergence here we mean the horizontal (pan) rotation of both cameras in opposite directions, which brings the fixation point (intersection of the cameras' optical axes) onto the surface of the target object. The considered here vergence requires only horizontal rotation of both cameras, which can be easily modeled on the given (pan-tilt) robotic head by a symmetric pan-rotation of both cameras in opposite directions, while keeping the common tilt angle fixed. In Chapter 4 we propose and evaluate two neural models for vergence control. Both models use input stereo images to estimate the desired vergence angle (the angle between cameras' optical axes). The first model assumes that the gaze direction of the robotic head is orthogonal to the baseline and that the stimulus is a frontoparallel plane orthogonal to the gaze direction. The second model goes beyond these assumptions and operates reliably in the general case where all restrictions on the orientation of the gaze, as well as the target position, type and orientation, are dropped.In the third study (Chapter 5) we go to the next level of active exploration hierarchy by considering vergence and version eye movements. By the version eye movement we consider the rotational movements of both eyes in the same direction. In this chapter, we propose a novel model, called vergence-version control with attention effects (VVCA), where object recognition is used as a channel for controlling version/vergence eye movements in a biologically-plausible way. Besides purely theoretical (simulated) results, the proposed VVCA model has a real-world embodiment in the form of a robotic setup, working under real-time control of VVCA model, which was adapted specifically for this case (real-time performance).We have also extensively worked on object recognition, the results of which have been employed in all of the studies mentioned. For appearance-based object recognition (used in IMD and VC studies) we involve the well-known recognition paradigm - the convolutional neural network (CNN). In Chapter 3 we present and describe an extended version of CNN, called myCNN, which can be regarded as a fusion of a conventional CNN with hierarchical cortex-like mechanisms.status: Publishe
Steady State Visual Evoked Potential-based Computer Gaming on a Consumer-grade EEG Device
No full textWe introduce a game in which the player navigates an avatar through a maze by using a brain-computer interface (BCI) that analyzes the steady-state visual evoked potential (SSVEP) responses recorded with electroencephalography (EEG) on the players scalp. The four command control game, called The Maze was specifically designed around a SSVEP BCI and validated in several EEG set-ups when using a traditional electrode cap with relocatable electrodes and a consumer-grade headset with fixed electrodes (Emotiv EPOC). We experimentally derive the parameter values that provide an acceptable trade-off between accuracy of game control and interactivity, and evaluate the control provided by the BCI during gameplay. As a final step in the validation of the game, a population study on a broad audience was conducted with the EPOC headset in a real-world setting. The study revealed that the majority (85%) of the players enjoyed the game despite of its intricate control (mean accuracy 80.37%, mean mission time ratio 0.90). We also discuss what to take into account while designing BCI-based games.sponsorship: The work of N. Chumerin was supported by the Tetra project Spellbinder (Flemish Agency for Innovation by Science and Technology). The work of N. V. Manyakov was supported by the Research Grant GOA 10/019. The work of M. van Vliet was supported by IUAP P7/21. The work of A. Robben and A. Combaz was supported by IWT doctoral grants. The work of M. M. Van Hulle was supported by PFV/10/008, CREA/07/027, G.0588.09, IUAP P7/21, GOA 10/019, and the Tetra project Spellbinder. (Flemish Agency for Innovation by Science and Technology, IUAP|P7/21, IWT, Tetra project Spellbinder, GOA 10/019, PFV/10/008, CREA/07/027, G.0588.09, IUAP P7/21)status: Publishe
Cue and Sensor Fusion for Independent Moving Objects Detection and Description in Driving Scenes
No full textIn this study we present an approach to detecting, describing and tracking independently moving objects (IMOs) independently moving object, IMO in stereo video sequences acquired by on-board cameras on a moving vehicle.
In the proposed model only three sensors are used: stereovision,speedometer and LIDAR (Light Detection and Ranging) Light Detection and Ranging, LIDAR. The IMOs detected by vision are matched with obstacles provided by LIDAR. In the case of a successful matching, the descriptions of the IMOs (distance, relative speed and acceleration) are provided by ACC (Adaptive Cruise Control) Adaptive Cruise Control, ACC LIDAR sensor, or otherwise these descriptions are estimated based on vision. Absolute speed of the IMO is evaluated using its relative velocity and egospeed provided by the speedometer. Preliminary results indicate the generalization ability of the proposed system.sponsorship: The first author is supported by the European Commission
(NEST-2003-012963). The second author is supported by the Excellence Financing program (EF 2005) and the CREA Financing program (CREA/07/027) of the K.U.Leuven, the Belgian Fund for Scientific Research -- Flanders (G.0248.03,
G.0234.04), the Flemish Regional Ministry of Education (Belgium) (GOA 2000/11), the Belgian Science Policy (IUAP P5/04), and the European Commission (NEST-2003-012963, STREP-2002-016276, and IST-2004-027017.status: Publishe
Biologically-inspired model of vision-based independently moving objects detection system
No full textVision-based independent motion detection systems have attracted a lot of attention lately. Such sort of system could be used in on-board automotive assistance system to help driver prevent possible collisions with other independently moving objects (IMOs). In this paper we present a biologically inspired model of IMOs detection system. The proposed model, according to a widely accepted in neuroscience hypothesis, consists of two information-processing streams: "what" (crucial for objects recognition) and "where" (responsible for independent motion discrimination).status: Publishe
Comparison of Two Feature Extraction Methods Based on Maximization of Mutual Information
No full textComparison of two feature extraction methods based on maximization of mutual information
No full textWe perform a detailed comparison of two feature extraction methods that are based on mutual information maximization between the data points projected in the developed subspace and their class labels. For the simulations, we use synthetic as well as publicly available real-world data sets.status: Publishe
- …
