Vehicular ad-hoc networks (VANETs) are the most hopeful approach to provide safety information and other infotainment applications to both drivers and passengers. VANETs are formed by intelligent vehicles equipped with On Board Units and wireless communication devices. Hence, VANETs become a key component of the intelligent transport system. Even though VANETs are used in enormous number of applications, there are many security challenges and issues that need to be overcome to make VANETs usable in practice. A great deal of study has been done towards it, but security mechanisms in VANETs are not effective. This study provides a summary about the VANET, characteristics and security challenges. This study also provides a summary of some major security attacks on security services such as availability, confidentiality, authentication, integrity and non-repudiation and the corresponding countermeasures to make VANET communications more secure.

The detection and identification of license plates from captured images have been widely studied over the past two decades. The demand for this technology in security and commercial applications ranges from traffic control organisation to parking management and vehicle tracking. License plate recognition can be divided into two steps: detection and identification. Recent algorithms have focused on the detection step, with few researchers studying identification. In this study, an algorithm is developed to detect and identify license plates. The algorithm is based on the fact that license plates have a semi-symmetric distribution of corner points; it utilises morphological feature learning. The algorithm runs in real time, is highly robust, and can identify whether the candidate region contains a license plate.

Bandwidth progression optimisation is a widely used approach for traffic signal coordination along the arterial streets. In this study, a new mixed integer variable bandwidth optimisation model is proposed. In this way, arterial traffic signals are set based on fully acceptable and unacceptable thresholds for each arterial link-specific bandwidth and green split which are specified by traffic engineer. On the basis of these parameters, a fuzzy membership function is defined for each bandwidth as well as each green split. Then, the proposed bandwidth optimisation model is developed by Bellman–Zade principles of fuzzy decision making. In this model, green splits, junctions’ offsets, cycle length, and left turn phase sequences pattern are simultaneously optimised. By this method, the traffic engineer can balance the arterial green band and opposite movements green splits. The efficiency of the proposed method has been evaluated by several measures of effectiveness compared with classic variable bandwidth and TRANSYT13 software.

Intelligent transportation systems have received a lot of attention in the last decades. Vehicle detection is the key task in this area and vehicle counting and classification are two important applications. In this study, the authors proposed a vehicle detection method which selects vehicles using an active basis model and verifies them according to their reflection symmetry. Then, they count and classify them by extracting two features: vehicle length in the corresponding time-spatial image and the correlation computed from the grey-level co-occurrence matrix of the vehicle image within its bounding box. A random forest is trained to classify vehicles into three categories: small (e.g. car), medium (e.g. van) and large (e.g. bus and truck). The proposed method is evaluated using a dataset including seven video streams which contain common highway challenges such as different lighting conditions, various weather conditions, camera vibration and image blurring. Experimental results show the good performance of the proposed method and its efficiency for use in traffic monitoring systems during the day (in the presence of shadows), night and all seasons of the year.

Computing the positions of road signs from in-vehicle video log images is one of the most fundamental tasks for intelligent sign inventory. This study analysed vision-based positioning methods from video log images and proposed an analytic model of road sign positioning (AM-RSP) based on error propagation and first-order approximation. Both image noises and camera calibration errors were modelled as two error sources. The AM-RSP model can evaluate and quantify the positioning uncertainties for both single view and stereo vision-based methods. Moreover, it can quantitatively establish the relationship between the positioning uncertainties and the various parameters of the vehicle and the camera,such as camera focal length, view angle, baseline width, height, image acquisition interval, vehicle distance to the road edge etc. Hence, the proposed AM-RSP model can be applied to configure the parameters of the camera and the vehicle to meet some specific computation requirement such as RSP accuracy. The proposed AM-RSP model has been validated with real video log image data collected in the field. These results show that the AM-RSP model is accurate and reliable to compute sign positioning uncertainties.

The traditional roadway level of service (LOS) is based on the volume–capacity (V/C) ratio, which measures the volume of traffic. However, this approach does not follow the green transport trend, and it lacks the comprehensive concepts of time cost, environmental protection, and potential social cost of traffic safety. Given the international focus on the development of green economies and transport, this study examined freeways in Taiwan to establish three indicators: cost of travel delay, cost of incremental carbon emissions, and cost of potential accidents. Traffic data from the electronic toll collection system in Taiwan were collected and analysed according to three factors derived from different traffic volumes and travel speeds: time cost, pollution, and traffic safety. The results were integrated into a traffic green safety index to replace the overall evaluation standard for traditional freeway LOS. This index is intended for use in an online software application.

Non-recurrent traffic incidents (accidents, stalled vehicles and spilled loads) often bring about traffic congestion and even secondary accidents. Detecting and positioning them quickly and accurately has important significance for early warning, timely incident-disposal and speedy congestion-evacuation. This study proposes a video-based detecting and positioning method by analysing distribution characteristics of traffic states in a road segment. Each lane in the monitored segment is divided into a cluster of cells. Traffic parameters in each cell, including flow rate, average travel speed and average space occupancy, are obtained by detecting and tracking traffic objects (vehicles and spilled loads). On the basis of the parameters, traffic states in the cells are judged via a fuzzy-identification method. For each congested cell, a feature vector is constructed by taking its state together with states of its upstream and downstream neighbouring cells in the same lane. Then, a support vector machine classifier is trained to detect incident point. If a cell is judged to be corresponding to an incident point at least for two successive time periods, an incident is detected and its position is calculated based on the identity number of the cell. Experiments prove the efficiency and practicability of the proposed method.

Human detection is exploited as a key operation in many applications such as automotive safety, intelligent vehicles, assisted living, and video surveillance. Consequently, there is a significant advancement in this area of research in the past years and a vast literature. In this study, the authors propose a pedestrian detection system which relies on sliding covariance matrix feature descriptor combined with a support vector machine classifier. The proposed framework is implemented onto field programmable gate array prototyping boards. Experimental results using the standard Institut National de Recherche en Informatique et en Automatique (INRIA) pedestrian benchmark dataset show that the proposed architecture achieved outstanding processing performances with high detection accuracy when compared with state-of-the-art methods.

Aiming to efficiently resolve the problem that the subtraction background model is easily contaminated by slow-moving or temporarily stopped vehicles, the Gaussian mixture model with confidence measurement (GMMCM) is proposed for vehicle detection in complex urban traffic scenes. According to the current traffic state, each pixel of background model is set a CM. Whether to update the background model and the corresponding adaptive learning rate depends on if the current pixel point is in confidence period. Using the real-world urban traffic videos, the first experiments are conducted by GMMCM, compared with three commonly used models including GMM, self-adaptive GMM (SAGMM) and local parameter learning algorithm for the GMM (LPLGMM). The first experimental results show that GMMCM excels GMM, SAGMM and LPLGMM in keeping the background model being unpolluted from slow-moving or temporarily stopped vehicles. The second experiments are conducted by GMMCM, compared with visual background extractor, sigma-delta with CM, SAGMM, LPLGMM and GMM. The average recalls of six methods are 0.899, 0.753, 0.679, 0.420, 0.447 and 0.205, and the average F-measures of six methods are 0.636, 0.612, 0.592, 0.373, 0.330 and 0.179, respectively. All experimental results show the effectiveness of the proposed GMMCM in vehicles detection of complex urban traffic scenes.

With increasing market penetration, dedicated short-range communications (DSRC) probes are attracting more interest in the advanced traveller information system as a way to efficiently alleviate traffic congestion. Generally, DSRC probes, thanks to their ability to directly collect point-to-point travel time, are considered to be superior to conventional point detectors. However, outlying observations are inevitable in DSRC probe data, and can erroneously indicate abnormally long travel times. In this study, a practical algorithm to filter out outliers in DSRC probe data is proposed. The suggested algorithm is divided into two parts. In the case of small sample, it uses a previous interval value to determine a valid range for current interval values; otherwise, it uses a modified median filter that uses the median and absolute deviation of current interval observations to determine the valid range. The algorithm has been thoroughly verified using various types of DSRC probe data in interrupted and uninterrupted rural highways near Seoul, Korea. Consequently, it was proven to be sufficient to overcome the deficiencies of the previous techniques.