Yosef Dalbah

A method for reducing false warnings in collision warning system (CWS) during turning maneuvers at road intersection

This paper proposes a method for reducing false warnings at road intersections, which uses a novel multi model rule based approach for long term trajectory predictions (1s-3s) and incorporates road crossing angle as additional input from the environment. Two major contributions to the field of collision warning have resulted from this research. First, an 8-state variable vehicle motion model is expanded from CTRA model and incorporates yaw-acceleration and acceleration-gradient as additional input variables. Second, a set of motion models are selected based on vehicle maneuver mode and turning phases. The crucial component is the incorporating road crossing angle in the switching logic. The system is tested using simulated and real world data and is shown to reduce false warnings by reducing long term trajectory prediction errors.

Visual odometry with high resolution time-of-flight cameras

We present a method that estimates the ego motion of a vehicle based on camera data of high resolution (207x204 pixels) Time-of-Flight cameras using visual odometry techniques. Translation and rotation of camera motion in six degrees of freedom are calculated. Point correspondences in consecutive amplitude image pairs are built. By consideration of the depth image of the camera 3D point correspondences are derived from the two dimensional point correspondences. Camera motion between the two images is then computed by registration of the two resulting point clouds. The process is optimized by incorporation of outlier removal and a multi sensor setup. The presented optimizations raise the precision and robustness of the method and enable visual odometry by Time-of-Flight camera data as an alternative to common odometry systems in low speed scenarios.

Detection of dynamic objects for environment mapping by time-of-flight cameras

We present a method for the detection of dynamic objects in the data of wide angle time-of-flight cameras. A vehicle is equipped with four cameras to incorporate a 360° vision by depth cameras. Depth measurements can be used for environment mapping. Dynamic objects however, lead to errors in the reconstruction of static scenes. Our method detects objects in the surrounding of the vehicle and discriminates between static and dynamic objects. Segments and keypoints are extracted from combinations of depth and amplitude images. After the generation and description of objects the vehicle odometry is incorporated for optimal object matching between consecutive images. Based on the computed movements of the objects a classification into static or dynamic is done. We evaluated our method based on different scenarios and under real world conditions including low lighting conditions and influence of external infrared light.

Robust real time extraction of plane segments from time-of-flight camera images

We present a method that extracts plane segments from images of a time-of-flight camera. Future driver assistance systems rely on an accurate description of the vehicle’s environment. Time-of-flight cameras can be used for environment perception and for the reconstruction of the environment. Since most structures in urban environments are planar, extracted plane segments from single camera images can be used for the creation of a global map. We present a method for real time detection of planar surface structures from time-of-flight camera data. The concept is based on a planar surface segmentation that serves as the fundament for a subsequent global planar surface extraction. The evaluation demonstrates the ability of the described algorithm to detect planar surfaces form depth data of complex scenarios in real time. We compare our methods to state of the art planar surface extraction algorithms.