Jing Bie

License Plate Recognition Algorithm for Passenger Cars in Chinese Residential Areas

This paper presents a solution for the license plate recognition problem in residential community administrations in China. License plate images are pre-processed through gradation, middle value filters and edge detection. In the license plate localization module the number of edge points, the length of license plate area and the number of each line of edge points are used for localization. In the recognition module, the paper applies a statistical character method combined with a structure character method to obtain the characters. In addition, more models and template library for the characters which have less difference between each other are built. A character classifier is designed and a fuzzy recognition method is proposed based on the fuzzy decision-making method. Experiments show that the recognition accuracy rate is up to 92%.

Assessment of safety levels and an innovative design for the Lane Change Assistant

In this paper we propose a novel design for the Lane Change Assistant (LCA). For drivers on the highway, LCA advises them on whether it is safe to change lanes under the current traffic conditions. We focus on how the LCA can provide a reliable advice in practice by considering the issues of changing circumstances and measurement uncertainties. Under some generic assumptions we develop a micro-simulation model for the lane change safety assessment. The model is in line with the car following models and lane change algorithms available in literature. It retains a probabilistic character to accurately represent realistic situations. Based on a sensitivity study we are able to develop a robust design for the LCA. In this design the system accounts for the practical uncertainties by including appropriate extra safety distances. The driver interface consists of a spectrum of five LED lights, each operating on a distinct color (varying from red to green) and guaranteeing a certain safety degree. Our results allow car developers to easily acquire reliable designs for the LCA.

Lane change and overtaking collisions: Causes and avoidance techniques

Lane change is the vehicle maneuver from one lane to another. Vehicles change lanes for various purposes and at various locations. Overtaking can be seen as two consecutive lane changes. Lane change and overtaking can result in several types of collisions, including rear-end and angle/sideswipe collisions.

Capacity of Multi-Lane Roundabout: Methodology Based on Lane Utilization

Traffic roundabout is a priority junction, whose capacity is typically captured by the entry capacities of individual approaches while considering the effects of conflicting flows. For a single-lane roundabout, entry capacity is traditionally analyzed based on gap acceptance where entering vehicles seek an acceptable gap among the circulating flow. An example of this approach can be found in HCM. This paper provides an extension to this approach for multi-lane roundabout. Through an analysis of lane utilization, entry capacity is estimated for each entry lane. Reserve capacity is then used as a measure to assess the overall roundabout performance. This paper also studies the sensitivity of drivers’ lane choices on the overall capacity of traffic roundabouts.