Multi-Camera Vessel-Speed Enforcement by Enhancing Detection and Re-Identification Techniques

This paper presents a camera-based vessel-speed enforcement system based on two cameras. The proposed system detects and tracks vessels per camera view and employs a re-identification (re-ID) function for linking vessels between the two cameras based on multiple bounding-box images per vessel. Newly detected vessels in one camera (query) are compared to the gallery set of all vessels detected by the other camera. To train and evaluate the proposed detection and re-ID system, a new Vessel-reID dataset is introduced. This extensive dataset has captured a total of 2474 different vessels covered in multiple images, resulting in a total of 136,888 vessel bounding-box images. Multiple CNN detector architectures are evaluated in-depth. The SSD512 detector performs best with respect to its speed (85.0% Recall@95Precision at 20.1 frames per second). For the re-ID of vessels, a large portion of the total trajectory can be covered by the successful detections of the SSD model. The re-ID experiments start with a baseline single-image evaluation obtaining a score of 55.9% Rank-1 (49.7% mAP) for the existing TriNet network, while the available MGN model obtains 68.9% Rank-1 (62.6% mAP). The performance significantly increases with 5.6% Rank-1 (5.7% mAP) for MGN by applying matching with multiple images from a single vessel. When emphasizing more fine details by selecting only the largest bounding-box images, another 2.0% Rank-1 (1.4% mAP) is added. Application-specific optimizations such as travel-time selection and applying a cross-camera matching constraint further enhance the results, leading to a final 88.9% Rank-1 and 83.5% mAP performance.

Impact of Average Speed Enforcement Systems on Traffic Safety: Evidence from the Roads of Lithuania

Average speed enforcement systems have been used on the roads of foreign countries for many years already, and give a positive effect on reducing accident number. The article presents good practices in the use of average speed enforcement systems in various countries and their impact on improving traffic safety. The article analyses the experience of system installation on the roads of Lithuania and the first results. The article also proposes methodologies for the selection of road sections to be enforced, the equipment used, and distribution of road sections in the road network of Lithuania. A detail analysis is given of the effect of average speed enforcement systems after their installation in three different periods on 25 road sections. The analysed data is differentiated between main and national roads. Conclusions and recommendations are given at the end of the paper for a future development of average speed enforcement systems.

Adopting Recommendations of a Road Safety Management Capacity Review: addressing a tragic decade of road safety in Romania

This article outlines a capacity review of Romania’s national road infrastructure and road safety in general. Romania’s road fatality rate per 100,000 population has improved overall from a 2008 high of around 15 to the current 2019 value of 9.6. However, the rate has flat-lined with no real improvement for the last decade, stalling at around 9.7 over the period 2011- 2019 and around double the EU rate. Moreover, Romania’s total annual number of road deaths has remained at an average of around 1900 fatalities per annum over this period. Romania has been the worst performing country in the European Union (EU) in recent years, and one of the worst performing countries compared to Organisation for Economic Co-operation and Development (OECD) nations in terms of road safety. The review performed in 2016 found inadequate political leadership and commitment to effective actions to reduce road fatalities, fragmented government road safety activities across a number of regulatory entities, speed limits set at levels that exceed internationally accepted survivable limits, weak traffic law enforcement including a lack of speed enforcement cameras resulting in a failure of drivers to comply with speed limits, and a lack of structured programs to implement human error tolerant road infrastructure constructed according to Safe System principles. A series of recommendations from the capacity review were adopted (as described here) since 2016, although much remains to improve road safety in Romania.

Field Testing Plan for Positive Train Control Enforcement in Passenger Terminals

In the United States, a train moving onto a terminating track at a passenger terminal relies on the train engineer’s operation. Currently, there are no mechanisms installed at the U.S. passenger terminals that are able to automatically stop a train before reaching the end of the track if an engineer fails to do so. The engineer’s actions determine whether the train will safely stop before the end of the terminating track. Thus, incapacitated or inattentive engineer operation would result in end-of-track collisions, such as the New Jersey Transit train accident at Hoboken Terminal in 2016. Currently, PTC enforcement is not required in passenger terminals. In an ongoing project tasked by the Federal Railroad Administration, we study the cost-effectiveness and operational impact of possible PTC enforcement to prevent end-of-track collisions. Specifically, a Concept of Operations (ConOps) was developed to outline the proposed plans to implement two of the most widely used PTC types, namely the Advanced Civil Speed Enforcement System (ACSES) and Interoperable Electronic Train Management System (I-ETMS). This paper describes in-field testing of the ConOps in ACSES-type terminal. In the planned field test, a train equipped with one locomotive and at least one passenger coach would be tested on platform tracks in a selected passenger terminal. These are three major testing components, which are test equipment, test track, and recorded information for each test sequence. Firstly, in terms of equipment, a traffic cone will be placed on the track to simulate a bumping post. In ACSES system, two sets of transponders are programmed to require a positive stop within a specified distance and mounted to the cross ties at specified positions. Secondly, a yard track will be used to test the feasibility of this exercise at the beginning. Upon successfully completing the test multiple times, a series of tests will also be made on the studied platform track. Thirdly, each test run should record the distance from the head end of the test train and the traffic cone for each test run. In addition, ACSES system should also record the information on the ACSES display as it passes the first and second transponder set, respectively. Overall, the field tests presented in this paper, along with previous work in benefit-cost analysis and operational impact assessment, can contribute to an assessment of the proposed PTC implementation at stub-end terminals in the United States in order to effectively and efficiently prevent end-of-track collisions.

Evaluation of Section Speed Enforcement System Using Empirical Bayes Approach and Turning Point Analysis

Speeding is a major risk factor for traffic-related injuries. As a countermeasure against speeding, automated speed enforcement systems (ASES) have been deployed in many countries. However, drivers’ awareness of enforcement locations allows themselves to adjust vehicle speeds in the vicinity of the enforcement locations. This enforcement avoidance behavior leads to a criticism of the effectiveness of ASES, in which the system promotes abrupt changes in vehicle speed near enforcement locations, increasing crash risk as a side effect. To address this issue, the section speed enforcement system (SSES), which enforces overspeeding vehicles by their average travel speed over a section, has been devised. In this study, we evaluate traffic speed and safety data that were collected from sections with SSES on Korean expressways. The speed analysis showed that the vehicles reduced their speeds inside the enforcement section, and this reduction in speed variations across vehicles was also noticeable, signifying that the risk of traffic crash should be lower. In view of this, we have performed before and after comparative analysis using the empirical Bayes method with the comparison group. The outcomes estimate 43% reduction in crash occurrence after installation of SSES. Furthermore, turning point analysis confirmed that the reduction in crash occurrence ensued immediately after installation of SSES.