There is an increasing interest worldwide in animal detection systems to reduce animal-vehicle collisions. Traditional approaches include building animal crossings, introducing real or virtual fencing, video surveillance and break-the-beam systems. Unlike these approaches, the system described here Large Animal Warning and Detection System (LAWDS) employs a 360˚-scanning radar to monitor a stretch of highway. This provides year-round continuous highway monitoring, even in harsh weather conditions. Innovative analysis and classification techniques enable the system to track large animals (e.g. deer). Low false alarm rate and environmental impact make LAWDS attractive for operational use. LAWDS also distinguishes vehicles from large animals and analyzes highway traffic metrics such as traffic volume and vehicle speeds.

Collisions involving large animals are a serious safety, economic and ecological concern. Some North American jurisdictions have installed a roadside animal detection system (RADS) that can warn the possible presence of large animals on rural highway sections. This study provides a conceptual framework for developing a next generation (NG) RADS. This study focuses on developing a process that can estimate the varying levels of threat posed by animals on the roadway using real‐time data on animal and vehicle positions. To estimate the level of threat, the study used a fuzzy rule‐based algorithm that integrates four input indicators (e.g., physical distance between animal and vehicle). The methodology was tested using real‐world traffic and animal data collected from a conventional RADS in British Columbia, Canada. The NG RADS has significant advantages over the conventional RADS. In particular, the NG RADS can disseminate varying levels of warning according to the estimated level of the threat rather than the constant level of warning generated by a conventional RADS. The NG RADS can also use a Vehicle‐to‐Infrastructure communication technology to establish direct wireless communication with vehicles at risk, for instance, to automatically control a vehicle's speed to avoid a collision with a large animal.

First responders including firefighters, paramedics, and police officers are among the first to respond to vehicle collisions on roads and highways. Police officers conduct regular roadside Please check if the country name is correct traffic controls and checks on urban and rural roads, and highways. Once first responders begin such operations, they are vulnerable to motor vehicle collisions by oncoming traffic, a circumstance that calls for a better understanding of contributing factors and the extent to which they affect tragic outcomes. In light of factors identified in the literature, this paper applies machine learning methods including decision tree and random forest to a subset of the National Collision Database (NCDB) of Canada that includes information on collisions between two vehicles (one in parked position) and the severity of these collisions as measured by having or not having injuries. Findings reveal that key measurable, predictable, and sensible factors such as time, location, and weather conditions, as well as the interconnections among them, can explain the severity of collisions that may happen between motor vehicles and first responders who are working alongside the roads. Analysis from longitudinal data is rich and the use of automated methods can be used to predict and assess the risk and vulnerability of first responders while responding to or operating on different roads and conditions.

Police officers on duty on the road for traffic stops, vehicle collisions, traffic direction, and so forth, are exposed to the risk of being hit or even killed by a passing vehicle. Very few studies have tried to develop a system that can warn pedestrians or police officers on duty on the road to take proactive evasive action. This study proposes an Internet-of-Things protection system for police officers on duty on the road. The development of the system envisaged involves three essential phases: 1. detection, 2. risk analysis, and 3. warning and communication. This study focused on the risk analysis phase. We applied a fuzzy rule-based algorithm that integrates four input indicators (lateral distance from police officer to traveled lane, magnitude of speeding, stopping sight distance, and direct distance) into a single estimate of the risk of a collision. The study used data from a real-world situation on Highway 416 in Ontario, Canada to demonstrate the application of the proposed model. The results clearly demonstrated that the proposed model could generate risk estimates that could be used to give timely warning of a possible collision risk to police officers at work on a road.

No abstract