Detecting anomalous events at railway level crossings

Collisions between pedestrians and vehicles continue to be a major problem throughout the world. Pedestrians trying to cross roads and railway tracks without any caution are often highly susceptible to collisions with vehicles and trains. Continuous financial, human and other losses have prompted transport related organizations to come up with various solutions addressing this issue. However, the quest for new and significant improvements in this area is still ongoing. This work addresses this issue by building a general framework using computer vision techniques to automatically monitor pedestrian movements in such high-risk areas to enable better analysis of activity, and the creation of future alerting strategies. As a result of rapid development in the electronics and semi-conductor industry there is extensive deployment of CCTV cameras in public places to capture video footage. This footage can then be used to analyse crowd activities in those particular places. This work seeks to identify the abnormal behaviour of individuals in video footage. In this work we propose using a Semi-2D Hidden Markov Model (HMM), Full-2D HMM and Spatial HMM to model the normal activities of people. The outliers of the model (i.e. those observations with insufficient likelihood) are identified as abnormal activities. Location features, flow features and optical flow textures are used as the features for the model. The proposed approaches are evaluated using the publicly available UCSD datasets, and we demonstrate improved performance using a Semi-2D Hidden Markov Model compared to other state of the art methods. Further we illustrate how our proposed methods can be applied to detect anomalous events at rail level crossings.

Evaluating ITS interventions at railway level crossings using a driving simulator

This paper assesses Intelligent Transportation Systems (ITS) to identify safety systems that are most likely to reduce driver errors at railway crossings. ITS technologies have been integrated in order to develop improved evaluation tools to reduce crashes at railway crossings. Although emerging technologies, knowledge, innovative interventions have been introduced to change driver behaviour, there is a lack of research on the impact of integrating ITS technologies and transportation simulation on drivers. The outcomes of ITS technologies for complementing traditional signage were compared with those of current safety systems (passive and active) at railway crossings. Three ITS technologies are compared with current treatments, in terms of compliance rate and vehicle speed profiles. It is found that ITS technologies improve compliance rate by 17~30% and also encourage drivers to slow down earlier compared to current passive and active crossings when there is a train approaching the railway crossings.

On-road driving studies to understand why drivers behave as they do at regional rail level crossings

Improving safety at rail level crossings is an important part of both road and rail safety strategies. While low in number, crashes between vehicles and trains at level crossings are catastrophic events typically involving multiple fatalities and serious injuries. Advances in driving assessment methods, such as the provision of on-road instrumented test vehicles with eye and head tracking, provide researchers with the opportunity to further understand driver behaviour at such crossings in ways not previously possible. This paper describes a study conducted to further understand the factors that shape driver behaviour at rail level crossings using instrumented vehicles. Twenty-two participants drove an On-Road Test Vehicle (ORTeV) on a predefined route in regional Victoria with a mix of both active (flashing lights with/without boom barriers) and passively controlled (stop, give way) crossings. Data collected included driving performance data, head checks, and interview data to capture driver strategies. The data from an integrated suite of methods demonstrated clearly how behaviour differs at active and passive level crossings, particularly for inexperienced drivers. For example, the head check data clearly show the reliance and expectancies of inexperienced drivers for active warnings even when approaching passively controlled crossings. These studies provide very novel and unique insights into how level crossing design and warnings shape driver behaviour.

Understanding pedestrian behaviour at railway level crossings : is there a need for more research?

Aim Collisions between trains and pedestrians are the most likely to result in severe injuries and fatalities when compared to other types of rail crossing accidents. Currently, there is a growing emphasis towards developing effective interventions designed to reduce the prevalence of train–pedestrian collisions. This paper reviews what is currently known regarding the personal and environmental factors that contribute to train–pedestrian collisions, particularly among high-risk groups. Method Studies that reported on the prevalence and characteristics of pedestrian accidents at railway crossings up until June 2012 were searched in electronic databases. Results Males, school children and older pedestrians (and those with disabilities) are disproportionately represented in fatality databases. However, a main theme to emerge is that little is known about the origins of train–pedestrian collisions (especially compared to train–vehicle collisions). In particular, whether collisions result from engaging in deliberate violations versus making decisional errors. This subsequently limits the corresponding development of effective and targeted interventions for high-risk groups as well as crossing locations. Finally, it remains unclear what combination of surveillance and deterrence-based and education-focused campaigns are required to produce lasting reductions in train–pedestrian fatality rates. This paper provides direction for future research into the personal and environmental origins of collisions as well as the development of interventions that aim to attract pedestrians’ attention and ensure crossing rules are respected.

Waiting for warning: Driver Situation awareness at rural rail level crossings

Driver behaviour at rail level crossings represents a key area for further research. This paper describes an on-road study comparing novice and experienced driver situation awareness at rural rail level crossings. Participants provided verbal protocols while driving a pre-determined rural route incorporating ten rail level crossings. Driver situation awareness was assessed using a network analysis approach. The analysis revealed key differences between novice and experienced drivers' situation awareness. In particular, the novice drivers seemed to be more reliant on rail level crossing warnings and their situation awareness was less focussed on the environment outside of the rail level crossing. In closing, the implications for rail level crossing safety are discussed.

Study of a geo-multicast framework for efficient message dissemination at unmanned level crossings

Collisions among trains and cars at road/rail level crossings (LXs) can have severe consequences such as high level of fatalities, injuries and significant financial losses. As communication and positioning technologies have significantly advanced, implementing vehicular ad hoc networks (VANETs) in the vicinity of unmanned LXs, generally LXs without barriers, is seen as an efficient and effective approach to mitigate or even eliminate collisions without imposing huge infrastructure costs. VANETs necessitate unique communication strategies, in which routing protocols take a prominent part in their scalability and overall performance, through finding optimised routes quickly and with low bandwidth overheads. This article studies a novel geo-multicast framework that incorporates a set of models for communication, message flow and geo-determination of endangered vehicles with a reliable receiver-based geo-multicast protocol to support cooperative level crossings (CLXs), which provide collision warnings to the endangered motorists facing road/rail LXs without barriers. This framework is designed and studied as part of a $5.5 m Government and industry funded project, entitled 'Intelligent-Transport-Systems to improve safety at road/rail crossings'. Combined simulation and experimental studies of the proposed geo-multicast framework have demonstrated promising outcomes as cooperative awareness messages provide actionable critical information to endangered drivers who are identified by CLXs.

Safety at railway level crossings : driver acceptance of potential ITS interventions

There is a continuing need to improve safety at Railway Level Crossings (RLX) particularly those that do not have gates and lights regulating traffic flow. A number of Intelligent Transport System (ITS) interventions have been proposed to improve drivers’ awareness and reduce errors in detecting and responding appropriately at level crossings. However, as with other technologies, successful implementation and ultimately effectiveness rests with the acceptance of the technology by the end user. In the current research, four focus groups were held (n=38) with drivers in metropolitan and regional locations in Queensland to examine their perceptions of potential in-vehicle and road-based ITS interventions to improve safety at RLX. The findings imply that further development of the ITS interventions, in particular the design and related promotion of the final product, must consider ease of use, usefulness and relative cost.

Pedestrian safety at level crossings : how the issue should be addressed?

• crashes at level crossings : pedestrians at higher risk • why pedestrian risky crossing lacks in understandng ? • systems approach – what benefits ? • what are the risk factors at play ? • focus group study: results and future implications

Video analytics for the detection of near-miss incidents on approach to railway level crossings

Recent modelling of socio-economic costs by the Australian railway industry in 2010 has estimated the cost of level crossing accidents to exceed AU$116 million annually. To better understand causal factors that contribute to these accidents, the Cooperative Research Centre for Rail Innovation is running a project entitled Baseline Level Crossing Video. The project aims to improve the recording of level crossing safety data by developing an intelligent system capable of detecting near-miss incidents and capturing quantitative data around these incidents. To detect near-miss events at railway level crossings a video analytics module is being developed to analyse video footage obtained from forward-facing cameras installed on trains. This paper presents a vision base approach for the detection of these near-miss events. The video analytics module is comprised of object detectors and a rail detection algorithm, allowing the distance between a detected object and the rail to be determined. An existing publicly available Histograms of Oriented Gradients (HOG) based object detector algorithm is used to detect various types of vehicles in each video frame. As vehicles are usually seen from a sideway view from the cabin’s perspective, the results of the vehicle detector are verified using an algorithm that can detect the wheels of each detected vehicle. Rail detection is facilitated using a projective transformation of the video, such that the forward-facing view becomes a bird’s eye view. Line Segment Detector is employed as the feature extractor and a sliding window approach is developed to track a pair of rails. Localisation of the vehicles is done by projecting the results of the vehicle and rail detectors on the ground plane allowing the distance between the vehicle and rail to be calculated. The resultant vehicle positions and distance are logged to a database for further analysis. We present preliminary results regarding the performance of a prototype video analytics module on a data set of videos containing more than 30 different railway level crossings. The video data is captured from a journey of a train that has passed through these level crossings.

Specification & design of safety technologies for complex socio-technical systems : low-cost level crossings case study

The introduction of safety technologies into complex socio-technical systems requires an integrated and holistic approach to HF and engineering, considering the effects of failures not only within system boundaries, but also at the interfaces with other systems and humans. Level crossing warning devices are examples of such systems where technically safe states within the system boundary can influence road user performance, giving rise to other hazards that degrade safety of the system. Chris will discuss the challenges that have been encountered to date in developing a safety argument in support of low-cost level crossing warning devices. The design and failure modes of level crossing warning devices are known to have a significant influence on road user performance; however, quantifying this effect is one of the ongoing challenges in determining appropriate reliability and availability targets for low-cost level crossing warning devices.

Driver’s over-trust on Advanced Driver Assistance Systems on passively protected railway crossings

Passively protected railway crossings are a major rail safety issue in Australia. Such crossings cannot be upgraded as such crossings are too numerous and the cost involved is prohibitive. Advanced Driver Assistance Systems (ADAS) have been shown to improve road safety and are widely used. These systems could be a solution to improve safety of passively protected crossings at a lower cost. Such complementary ADAS could result in driver’s over-trust due to the absence of Humane Machine Interface reflecting the quality of the information or the state of the ADAS (failure status). This paper demonstrates that driver’s exposure to crossing exhibiting fail-safe and non-fail safe properties could result in improperly allocating trust between technologies. We conducted a driving simulator study where participants (N=58) were exposed to three types of level crossing warning system on passive and active crossings. The results show that a significant proportion of participants over-trust the ADAS. Such drivers exhibit the same driving performance with the ADAS as when exposed to infrastructure based active crossing protection. They do not take the necessary safety precautions as they have a faster speed approach, reduced number of gaze toward the rail tracks and fail to stop at the crossing.

Evaluation of emerging intelligent transport systems to improve safety on level crossings : an overview

Safety at railway level crossings (RLX) is one part of a wider picture of safety within the whole transport system. Governments, the rail industry and road organisations have used a variety of countermeasures for many years to improve RLX safety. New types of interventions are required in order to reduce the number of crashes and associated social costs at railway crossings. This paper presents the results of a large research program which aimed to assess the effectiveness of emerging Intelligent Transport Systems (ITS) interventions, both on-road and in-vehicle based, to improve the safety of car drivers at RLXs in Australia. The three most promising technologies selected from the literature review and focus groups were tested in an advanced driving simulator to provide a detailed assessment of their effects on driver behaviour. The three interventions were: (i) in-vehicle visual warning using a GPS/smartphone navigation-like system, (ii) in-vehicle audio warning and; (iii) on-road intervention known as valet system (warning lights on the road surface activated as a train approaches). The effects of these technologies on 57 participants were assessed in a systematic approach focusing on the safety of the intervention, effects on the road traffic around the crossings and driver’s acceptance of the technology. Given that the ITS interventions were likely to provide a benefit by improving the driver’s awareness of the crossing status in low visibility conditions, such conditions were investigated through curves in the track before arriving at the crossing. ITS interventions were also expected to improve driver behaviour at crossings with high traffic (blocking back issue), which were also investigated at active crossings. The key findings are: (i) interventions at passive crossings are likely to provide safety benefits; (ii) the benefits of ITS interventions on driver behaviour at active crossings are limited; (iii) the trialled ITS interventions did not show any issues in terms of driver distraction, driver acceptance or traffic delays; (iv) these interventions are easy to use, do not increase driver workload substantially; (v) participants’ intention to use the technology is high and; (vi) participants saw most value in succinct messages about approaching trains as opposed to knowing the RLX locations or the imminence of a collision with a train.

Near-miss event detection at railway level crossings

Recent modelling of socio-economic costs by the Australian railway industry in 2010 has estimated the cost of level crossing accidents to exceed AU$116 million annually. To better understand the causal factors of these accidents, a video analytics application is being developed to automatically detect near-miss incidents using forward facing videos from trains. As near-miss events occur more frequently than collisions, by detecting these occurrences there will be more safety data available for analysis. The application that is being developed will improve the objectivity of near-miss reporting by providing quantitative data about the position of vehicles at level crossings through the automatic analysis of video footage. In this paper we present a novel method for detecting near-miss occurrences at railway level crossings from video data of trains. Our system detects and localizes vehicles at railway level crossings. It also detects the position of railways to calculate the distance of the detected vehicles to the railway centerline. The system logs the information about the position of the vehicles and railway centerline into a database for further analysis by the safety data recording and analysis system, to determine whether or not the event is a near-miss. We present preliminary results of our system on a dataset of videos taken from a train that passed through 14 railway level crossings. We demonstrate the robustness of our system by showing the results of our system on day and night videos.

Traffic safety at road-rail level crossings using a driving simulator and traffic simulation

A number of Intelligent Transportation Systems (ITS) were used with an advanced driving simulator to assess its influence on driving behavior. Three types of ITS interventions namely, Video in-vehicle (ITS1), Audio in-vehicle (ITS2), and On-road flashing marker (ITS3) were tested. Then, the results from the driving simulator were used as inputs for a developed model using a traffic micro-simulation (Vissim 5.4) in order to assess the safety interventions. Using a driving simulator, 58 participants were required to drive through a number of active and passive crossings with and without an ITS device and in the presence or absence of an approaching train. The effect of driver behavior changing in terms of speed and compliance rate was greater at passive crossings than at active crossings. The difference in speed of drivers approaching ITS devices was very small which indicates that ITS helps drivers encounter the crossings in a safer way. Since the current traffic simulation was not able to replicate a dynamic speed change or a probability of stopping that varies based on different ITS safety devices, some modifications of the current traffic simulation were conducted. The results showed that exposure to ITS devices at active crossings did not influence the drivers’ behavior significantly according to the traffic performance indicators used, such as delay time, number of stops, speed, and stopped delay. On the other hand, the results of traffic simulation for passive crossings, where low traffic volumes and low train headway normally occur, showed that ITS devices improved overall traffic performance.