Thanh-Binh To

Target classification based on near-distance radar sensors

Automotive radar systems offer the capability to measure very accurately target range, relative velocity, and azimuth angle of all objects inside the observation area. For future automotive applications like pedestrian safety systems, collision warning, turning-off and lane-changing assistance it will be necessary to have more detailed information about the target type. Therefore, a target classification technique, which is purely based on the range profile measured by a near-distance radar sensor, is presented in this paper.

A stereovision-based probabilistic lane tracker for difficult road scenarios

This paper presents a lane estimation technique based on the particle filter framework, which fuses several image-based cues (edges, lane markings and curbs), and 3D cues extracted from stereovision. A partition sampling-like approach is used to decouple pitch estimation from the rest of the parameter set, allowing the use of a significantly lower number of particles, and initialization samples are used for faster handling of discontinuous roads. We also introduce a measure for detection quality, for result validation. The resulted solution has proven to be a reliable and fast lane detector for difficult scenarios.

A Stereovision-Based Lane Detector for Marked and Non-Marked Urban Roads

This paper presents a lane detection system that combines stereovision-specific techniques with grayscale image processing for maximizing the robustness and applicability against the difficult conditions found on the urban roads, marked or non marked. The lane marking features are extracting using a fast and robust dark-light-dark transition detector thats aware of the perspective effect. The clothoid lane model is matched to the extracted features using line segment fitting for two distance intervals, under special constraints that ensure correctness. Freeform lane border detection, independent of the geometry constraints, driven by lane marking features only, is used to solve the situations not suited for clothoid representation. Intensive validation techniques are used for tracking initialization, and for monitoring of the noise level on the road, in order to avoid false positives. The results of each detection method are fused together in a Kalman filter based framework.

ENVIRONMENTAL PERCEPTION AND CONTROL STRATEGIES FOR AN ADVANCED HIGHWAY ASSISTANT

Abstract This paper is aimed to introduce a novel environmental perception method and control strategies for an advanced highway assistant. Using multi sensors systems the whole surrounding traffic scene can be well perceived and those data can be further provided for developing also comfortable and safety systems in the automotive area.