Wildlife Detection System
Author(s): Steele
Slidedeck Presentation Only:
Abstract:
Background/Context: Each year, thousands of collisions with wildlife are reported on British Columbia highways. Wildlife Vehicle Collisions (WVCs) often result in serious personal injuries, endanger various wildlife species, and cost millions of dollars annually. Through an analysis of historical collision information, the BC Ministry of Transportation and Infrastructure (MoTI) identified two corridors along Highway 3 in Southeastern BC as having the highest densities of large WVCs in the province. To protect the surrounding natural wildlife habitat and improve safety for travelers, MoTI sought to reduce the number of WVCs in the area through the application of an appropriate technology solution.
Aims/Objectives: To protect the surrounding natural wildlife habitat and improve safety for travelers, the Ministry sought to reduce the number of WVCs in the area through the application of an appropriate technology solution. This solution was deemed to be the design, implementation, and commissioning of an effective Wildlife Detection System (WDS) to reduce the number of animal-vehicle incidents. The long term goal is to expand the WDS to other areas of the province. In order to do so, it was necessary to ensure that the system performed correctly and effectively so that additional capital investment could be justified. It was necessary to clearly establish not only what the definition of performance would be, but how that performance would be measured and evaluated.
Methods/Targets: The WDS provides the area's wildlife with greater protection and motorists within the corridor a safer commute than ever before. Extensive field testing confirmed the very high degree of accuracy of the system, providing drivers with confidence that when the signs are activated, wildlife is nearby.
Results/Activities: The solution consists of a suite of Intelligent Transportation System components integrated with high-performance security technologies. A series of volumetric radar-based presence detectors are located along the identified corridors. These detectors monitor the 3-dimensional area of the roadway and the immediately adjacent shoulders to detect the presence of large animals on or in proximity to the roadway. Thermal and color cameras record the presence of the animals and overall operation of the system to assist with calibration and verification. The radar detectors are augmented with specialized video analytics in key areas to mitigate detection challenges introduced by terrain or other features. A field-located central control system analyzes the detection data from all sensors. When a large animal is detected, the control system activates a series of warning signs that advise motorists of the presence of animals to help ensure the safety of the animals and the travelling public.
Extensive testing and data validation was undertaken to verify the correct performance and accuracy of the system. Due to the remote nature of the sites, particular attention was paid to the reliability and resiliency of the system. Each corridor operates autonomously, with system notifications and performance monitored remotely from the Ministry's Regional Transportation Management Centre.
Accurately and reliably detecting wildlife on roadways and effectively actioning that data into useful notifications to drivers is a complex problem. Factors such as weather, terrain, the unpredictable nature of wildlife, and the remoteness of these locations combine to make deploying an effective system a very challenging endeavor. This problem is not limited to BC. As such, PBX conducted significant research on approaches taken by other jurisdictions in North America. Numerous possible technical solutions were identified and analyzed.
Discussion/Deliverables: The system has a demonstrated impact on driver behavior, with vehicles traveling measurably slower through the corridor when the warning signs are activated, resulting in a reduction of WVCs by 79% and 23%, respectively, along the two corridors.