Eric Wahl

Parking assistance using dense motion-stereo

The ability of generating and interpreting a three-dimensional representation of the environment in real-time is one of the key technologies for autonomous vehicles. While active sensors like ultrasounds have been commercially used, their cost and precision is not favorable. On the other hand, integrating passive sensors, like video cameras, in modern vehicles is quite appealing especially because of their low cost. However, image processing requires reliable real-time algorithms to retrieve depth from visual information. In addition, the limited processing power in automobiles and other mobile platforms makes this problem even more challenging. In this paper we introduce a parking assistance system which relies on dense motion-stereo to compute depth maps of the observed environment in real-time. The flexibility and robustness of our method is showcased with different applications: automatic parking slot detection, a collision warning for the pivoting ranges of the doors and an image-based rendering technique to visualize the environment around the host vehicle. We evaluate the accuracy and reliability of our system and provide quantitative and qualitative results. A comparison to ultrasound and feature-based motion-stereo solutions shows that our approach is more reliable.

Efficient Disparity Computation without Maximum Disparity for Real-Time Stereo Vision

In order to improve the performance of correlation-based disparity computation of stereo vision algorithms, standard methods need to choose in advance the value of the maximum disparity (MD). This value corresponds to the maximum displacement of the projection of a physical point expected between the two images. It generally depends on the motion model, the camera intrinsic parameters and on the depths of the observed scene. In this paper, we show that there is no optimal MD value that minimizes the matching errors in all image regions simultaneously and we propose a novel approach of the disparity computation that does not rely on any a priori MD. Two variants of this approach will be presented. When compared to traditional correlation-based methods, we show that our approach improves not only the accuracy of the results but also the efficiency of the algorithm. A local energy minimization is also proposed for fast refinement of the results. An extensive comparative study with ground truth is carried out on classical stereo images and the results show that the proposed method clearly gives more accurate results and it is two times faster than the fastest possible implementation of traditional correlation-based methods.

Efficient stereo and optical flow with robust similarity measures

In this paper we address the problem of dense stereo matching and computation of optical flow. We propose a generalized dense correspondence computation algorithm, so that stereo matching and optical flow can be performed robustly and efficiently at the same time. We particularly target automotive applications and tested our method on real sequences from cameras mounted on vehicles. We performed an extensive evaluation of our method using different similarity measures and focused mainly on difficult real-world sequences with abrupt exposure changes. We did also evaluations on Middlebury data sets and provide many qualitative results on real images, some of which are provided by the adverse vision conditions challenge of the conference.

Stereo Fusion from Multiple Viewpoints

Advanced driver assistance using cameras is a first important step towards autonomous driving tasks. However, the computational power in automobiles is highly limited and hardware platforms with enormous processing resources such as GPUs are not available in serial production vehicles. In our paper we address the need for a highly efficient fusion method that is well suited for standard CPUs.

3D-environment modeling as an enabler for autonomous vehicles

The ability of generating and interpreting a three-dimensional model of the real world is a key technology for autonomous vehicle movements. This article discusses a powerful approach invented in the BMW Group which provides dense and accurate point clouds of a vehicles environment generated with a motion stereo algorithm. The potential of the approach will be showcased using a parking assistance system.

3D-Umwelterfassung als Schluessel fuer autonome Fahrzeuge

Die Fahigkeit, online dreidimensionale Umweltmodelle zu erzeugen und diese auch zu interpretieren, ist eine Schlusseltechnologie fur vollautonome Fahrerassistenzsysteme. Dieser Artikel diskutiert ein in der BMW Group entwickeltes Verfahren, das in der Lage ist, dichte und zugleich genaue Punktwolken aus der Fahrzeugumgebung mittels Motion-Stereo abzuleiten. Die Ergebnisse werden anhand eines Parksystems beispielhaft prasentiert.