Abstract — This paper is concerned with the, by now rather well studied, problem of integrated road geometry estimation and vehicle tracking. The main differences to the existing approaches are that we make use of an improved host vehicle model and a new dynamic model for the road. The problem is posed within a standard sensor fusion framework, allowing us to make good use of the available sensor information. The performance of the solution is evaluated using measurements from real and relevant traffic environments from public roads in Sweden. The experiments indicates that the gain in using the extended host vehicle model is most prominent when driving on country roads without any vehicles in front. I.

The Selective Tuning Model is a proposal for modelling visual attention in primates and humans. Although supported by significant biological evidence, it is not without its weaknesses. The main one addressed by this paper is that the levels of representation on which it was previously demonstrated (spatial Gaussian pyramids) were not biologically plausible. The motion domain was chosen because enough is known about motion processing to enable a reasonable attempt at defining the feedforward pyramid. The effort is unique because it seems that no past model presents a motion hierarchy plus attention to motion. We propose a neurally-inspired model of the primate visual motion system attempting to explain how a hierarchical feedforward network consisting of layers representing cortical areas V1, MT, MST, and 7a detects and classifies different kinds of motion patterns. The STM model is then integrated into this hierarchy demonstrating that successfully attending to motion patterns, results in localization and labelling of those patterns.

Abstract: Efficient real-time visual perception in civilized natural environments (e.g. road networks) has to take advantage of foveal – peripheral differentiation for data economy and of active gaze control for a number of benefits. 1. Inertial gaze stabilization considerably alleviates the evaluation of image sequences taken by cameras with stronger tele-lenses; it allows a reduction in angular disturbances from rough ground by at least an order of magnitude with simple negative angular rate data feedback. 2. Visual tracking of fast moving objects reduces motion blur for these objects. – 3. In the near range, a large field of view is mandatory, however, only coarse angular resolution is sufficient; with a field of view (f.o.v.)> ~ 100°, both the region in front of and to the side of the vehicle may be viewed simultaneously. For own behavior decision, motion behaviors of objects both in the wide f.o.v. nearby and in several regions of special interest further away have to be understood in conjunction. In order to achieve this efficiently, three distinct visual processes with specific knowledge bases have to be employed in a consecutive way. In the wide f.o.v., bottom-up feature extraction has to answer the question: ‘Is there anything of special interest? ’ The corresponding feature extraction operators are domain-specific. On initialization, they have to give indications of objects of interest all over the image. Stable feature aggregations over several cycles have to trigger object hypotheses for the second stage; these regions may then be discarded for stage 1. Stage 2 works on single objects, however, on multiple of these in parallel. When looking almost parallel to

Abstract. The newly established cluster of excellence COTESYS 1 investigates the realization of cognitive capabilities such as perception, learning, reasoning, planning, and execution for technical systems including humanoid robots, flexible manufacturing systems, and autonomous vehicles. In this paper we describe cognitive technical systems using a sensor-equipped kitchen with a robotic assistant as an example. We will particularly consider the role of Artificial Intelligence in the research enterprise. Key research foci of Artificial Intelligence research in COTESYS include (◦) symbolic representations grounded in perception and action, (◦) first-order probabilistic representations of actions, objects, and situations, (◦) reasoning about objects and situations in the context of everyday manipulation tasks, and (◦) the representation and revision of robot plans for everyday activity. 1

There are more and more systems emerging making use of measurements from a forward looking radar and a forward looking camera. It is by now well known how to exploit this data in order to compute estimates of the road geometry, tracking leading vehicles, etc. However, there is valuable information present in the radar concerning stationary objects, that is typically not used. The present work shows how radar measurements of stationary objects can be used to obtain a reliable estimate of the free space in front of a moving vehicle. The approach has been evaluated on real data from highways and rural roads in Sweden.

Abstract—The sensors present in modern premium cars deliver a wealth of information. We will in this work illustrate one way of making better use of the sensor information already present in modern premium cars. More specifically, we will show how a far infrared (FIR) camera can be used to enhance the estimates of the vehicle ego-motion and indirectly the road geometry in 3D. The FIR camera is primarily intended for pedestrian detection. The solution is obtained by solving a suitable sensor fusion problem, where we merge information from proprioceptive sensors with the FIR camera images. In order to illustrate the performance of the proposed method we have made use of measurement sequences recorded during night-time driving on rural roads in Sweden. The results illustrate that the FIR images can be used to improve the ego-motion estimation, especially during night time driving. I.

Abstract Position and orientation tracking is a major challenge for Mixed / Augmented Reality applications, especially in heterogeneous and wide-area sensor setups. In this article, we describe trackman, a planning and analysis tool which supports the AR-engineer in setup and maintenance of the tracking infrastructure. A new graphical modeling approach based on spatial relationship graphs (SRGs) eases the specification of known as well as the deduction of new relationships between entities in the scene. Modeling is based on reusable patterns representing the underlying sensor drivers or algorithms. Recurring constellations in the scene can be condensed into reusable meta-patterns. The process is further simplified by semiautomatic modeling techniques which automize trivial steps. Dataflow networks can be generated automatically from the SRG and are guaranteed to be semantically correct. Furthermore, generic tools are described that allow for the calibration/registration of static spatial transformations as well as for the live surveillance of tracking accuracy. In summary, this approach reduces tremendously the amount of expert knowledge needed for the administration of tracking setups. Keywords: Mixed/Augmented Reality, spatial relationship graph, tracking, sensor fusion, authoring, calibration, registration, error analysis. 1

We provide a sensor fusion framework for solving the problem of joint ego-motion and road geometry estimation. More specifically we employ a sensor fusion framework to make systematic use of the measurements from a forward looking radar and camera, steering wheel angle sensor, wheel speed sensors and inertial sensors to compute good estimates of the road geometry and the motion of the ego vehicle on this road. In order to solve this problem we derive dynamical models for the ego vehicle, the road and the leading vehicles. The main difference to existing approaches is that we make use of a new dynamic model for the road. An extended Kalman filter is used to fuse data and to filter measurements from the camera in order to improve the road geometry estimate. The proposed solution has been tested and compared to existing algorithms for this problem, using measurements from authentic traffic environments on public roads in Sweden. The results clearly indicate that the proposed method provides better estimates.

Abstract: This paper is concerned with vehicle motion estimation. The problem is formulated as a sensor fusion problem, where the vehicle motion is estimated based on the information from a far infrared camera, inertial sensors and the vehicle speed. This information is already present in premium cars. This work is concerned with the off-line situation and the approach taken is to formulate the problem as a nonlinear least squares problem. In order to illustrate the performance of the proposed method experiments on rural roads in Sweden during night time driving have been performed. The results clearly indicates the efficacy of the approach.

awareness and road prediction for trajectory control applications