The varied road conditions, chaotic and unstructured traffic, lack of lane discipline and wide variety of vehicles in countries like India, Pakistan and so on pose a need for a novel traffic monitoring system. In this study, the authors propose a novel camera-based traffic monitoring and prediction scheme without identifying or tracking vehicles. Spatial interest points (SIPs) and spatio-temporal interest points (STIPs) are extracted from the video stream of road traffic. SIP represents the number of vehicles and STIP represents the number of moving vehicles. The distributions of these features are then classified using Gaussian mixture model. In the proposed method, they learn the road state pattern using dynamic Bayesian network and predict the future road traffic state within a specific time delay. The predicted road state information can be used for traffic planning. The proposed method is computationally light, yet very powerful and efficient. The algorithm is tested for different weather conditions as well. They have validated their algorithm using Synchro Studio simulator and got 95.7% as average accuracy and on real-time video we got an accuracy of 84%.

The numerous applications of urban traffic detection technology in road traffic data acquisition bring new challenges for transportation and storage of road traffic big data. The travel demand and travel time of travel participants present certain specific regularity; thus, a compression algorithm for road traffic data in time series based on temporal correlation was proposed in this study. First, the temporal correlation of the road traffic data in time series was analysed. Second, the reference sequences of road traffic characteristics were constructed to acquire the base data under different modes. Third, the training data under the same mode were extracted to acquire the difference data between training and base data. Then the optimal threshold of the difference data was trained. Fourth, the optimal threshold was introduced into the difference data between real-time and base data in time series, combining with Lempel-Ziv-Welch (LZW) encoding to achieve the compression of difference data. Finally, the reconstruction of real-time road traffic data in time series was accomplished based on LZW decoding technology. Six typical road segments in Beijing were adopted for case studies. The final results prove the feasibility of the algorithm, and that the reconstructed data can achieve high accuracy.

As a classical machine learning method, multi-task learning (MTL) has been widely applied in computer vision technology. Due to deep convolutional neural network (D-CNN) having strong ability of feature representation, the combination of MTL and D-CNN has attracted much attention from researchers recently. However, this kind of combination has rarely been explored in the field of vehicle analysis. The authors propose a D-CNN enhanced with weighted multi-attribute strategy for extensive exploration of comprehensive vehicle attributes over surveillance images. Specifically, regarding to recognising vehicle model and make/manufacturer, several related attributes as auxiliary tasks are incorporated in the training process of D-CNN structure. The proposed strategy focuses more on the main task compared with traditional MTL methods, which has assigned different weights for the main task and auxiliary tasks rather than treating all involved tasks equally. To the extent of their knowledge, this is the first report relating to the combination of D-CNN and weighted MTL for exploration of comprehensive vehicle attributes. The following experiments will show that the proposed approach outperforms the state-of-the-art method for the vehicle recognition and improves the accuracy rate by about 10% for the analysis of other vehicle attributes on the recently public CompCars dataset.

Real-time passenger information (RTPI) systems have been identified as having benefits in terms of passenger willingness to travel by public transport and their satisfaction levels with services provided. The lack of this amenity in rural areas, however, may hamper public transport use, thus reinforcing patterns of over-reliance on personal vehicles. To explore the potential impacts of providing RTPI in rural areas, a smartphone application (GetThereBus) was developed to allow rural bus passengers to share real-time public transport data, and access real-time and timetable information. Through user testing of GetThereBus, this work aimed to address questions related to the impact of the limited availability of rural digital infrastructure on the provision of RTPI; the potential for crowdsourced information to supplement published timetable information given digital limitations; and the potential impacts of such a system on the traveller experience. This study describes the GetThereBus development and evaluation phases. The authors found it was possible to design and develop a system that overcame many of the technological limitations experienced in rural areas, and users reported a positive response to the system. However, despite a campaign of user engagement, it proved difficult to recruit and motivate sufficient users to provide the data needed to achieve area-wide coverage.

An electric vehicle-routing problem (EVRP) is developed to settle some operation distribution troubles such as battery energy limitations and difficulties in finding charging stations for electric vehicles (EVs). Meanwhile, in view of realistic traffic conditions and features of EVs, energy consumption with travel speed and cargo load is considered in the EVRP model. Moreover, to avoid the depletion of all battery power and ensure safe operation, EVs with insufficient battery power can be recharged at charging stations many times in transit. In conclusion, a large, realistic case study with the road network of Beijing urban, 100 customers and 30 charging stations is conducted to test the performance of the model and obtain an optimal operation scheme consisted of the routes, charging plan and driving paths. The EVRP model is solved based on the hybrid genetic algorithm to get the routes and charging plan. The dynamic Dijkstra algorithm with some improvements over the classical Dijkstra algorithm is applied to find the driving paths called the most energy efficient paths between any two adjacent visited nodes in the routes.

License plate recognition (LPR) is an important component of intelligent transportation systems. Compared with letters and numbers, Chinese characters contain more information, making automatic recognition more difficult. Accurate Chinese LPR (CLPR) is determined by three factors: training dataset, feature extractor, and classifier. Most license plates with benchmark dataset contain only letters and numbers; thus, the authors build a large dataset for CLPR. Convolutional neural networks (CNNs) can be used to extract inherent image features, on all levels of abstraction. CNNs can be used for classification if they have a sufficient number of fully connected layers. This implies that CNNs must be trained using gradient descent-based methods, which often yields sub-optimal results. Extreme learning machines (ELMs) demonstrate impressive performance on classification, with good generalisation. Therefore, the authors propose a novel deep architecture for CLPR which combines a CNN and an ELM. Firstly, a CNN without fully connected layers, working as a feature extractor, learns deep features associated with characters in written Chinese. Then, a kernel-based ELM (KELM) classifier, which accepts CNN features as input, is utilised for classification. Compared with CNNs that use Softmax, support vector machines and ELMs, the CNN that uses KELM yields competitive results in a shorter training time.

Drowsiness as one of the impaired driving behaviour is an important area of concern in ground transportation safety. It can coincide with skill-demanding situations that may lead to vehicle control loss and possibly traffic accidents. Although drowsiness effects on driving performances have been widely investigated, there are few studies that propose a description of its effect on human neuromuscular state. To address this issue, this study aims to investigate the effects of drowsiness on driver neuromuscular state via the estimation of mechanical arm admittance. Mechanical arm admittance is a car dedicated parameter that gives information about arm stiffness of driver and its corresponding response in the frequency domain. Ten participants performed an experiment on a driving simulator, where they experienced steering disturbances, which aims to estimate variations of mechanical arm admittance as well as variations of driving performances between alert and drowsy states. Moreover, variation in driving performances were assessed by the variation of steering reversal rate and standard deviation of lane position. Results indicate that drowsiness increases the gain of mechanical arm admittance for arm movements <2.5 Hz and also deteriorates car steering control, increasing the steering operations amplitude and leading to larger vehicle lateral deviations.

Variable speed limits (VSL) are used to balance traffic safety and transportation efficiency on the highway. However, driver satisfaction usually affects both aspects because human behaviour is an important factor in the traffic system. Therefore, this study aims to propose a VSL rule that combines traffic flow, risk level and driver satisfaction. First, the authors present a physical model of the lane-changing process, and the psychology of drivers when judging whether to change lanes is measured by mathematical expectation and membership functions. Considering the above three factors as target functions, a new VSL rule for two-lane highways and a periodic VSL rule for three-lane highways are formulated. Simulation results indicate that the rule for two-lane highways has good performance in the three aspects, but when it is extended to the three-lane situation, the driver satisfaction does not improve significantly. However, the periodic speed limit rule can help increase driver satisfaction. Therefore, the VSL rules that are proposed reveal a potentially highly effective way to improve the vehicle speed on the highway and advance rule making.

This study investigated the effects of supervision on autonomous wheelchairs, which are considered to be a means of future transportation. A rider using an automated wheelchair needs to be vigilant about the failure modes of the system. This study focused on the effects of human factors on an automated system. Several experiments were conducted in public areas to investigate the influence of human factors including acceptability, capability, and usability on the supervision of an automated system by using questionnaires. The average reaction time from the occurrence of system failure until the emergency switch is activated was found to be similar in all the experiments for all test tracks. Regarding the positions of the subject's hand, several patterns for pushing the emergency switch were observed. The method of supervision for pushing the emergency switch was the same among all subjects, even though they had different attitudes. Most subjects had favourable opinions on the automated wheelchair, whereas some found the supervision bothersome. The results reveal the conditions under which future users would prefer to use the automated wheelchair, given the expected cost and functions. The real-world experimental data are valuable for developing automated wheelchairs and effective human–machine interfaces on automated systems.

Vehicular ad hoc network (VANET) is an emerging trend where vehicles communicate with each other and possibly with a roadside unit. Collaboration among vehicles is significant in VANET. Resource constraint is one of the great challenges of VANETs. Owing to the absence of centralised management, there is pitfall in optimal resource allocation that leads ineffective routing. Effective reliable routing is quite essential to achieve intelligent transportation. Stochastic dynamic programming (SDP) is currently employed as a tool to analyse and solve network resource constraint and allocation issues of resources in VANET. The authors have considered this work as a geographic angular zone-based two-phase dynamic resource allocation problem with homogeneous and heterogeneous resource class. This work uses relaxed approximation-based SDP algorithm to generate optimal resource allocation strategies over time in response to past task completion status history. The second-phase resource allocation uses the observed outcome of the first-phase task completion to provide optimal viability decisions. They have also suggested an alternative solution called model predictive control algorithm (MPCA) that used approximation as a part to allocate resource over time in response to information on data transmission completion status. Simulation results show that the proposed schemes works significantly well for homogeneous resources.