Traffic accidents caused by the appearance of wild animals on the road represent a significant traffic safety problem. These accidents often occur due to the presence of wild animals near the road, which can be due to factors such as the proximity of forests, pastures, watering holes or other wildlife habitats along the roads. Most often, these accidents result in direct collisions between vehicles and wild animals, which can cause serious injuries to drivers, passengers, wildlife, as well as material damage to vehicles and road infrastructure. Night driving, bad weather conditions and insufficient road visibility further increase the risk of such accidents. The Vehicle-Wildlife Collision Avoidance (VWCA) system on rural roads includes the detection of wild animals near and along the road as well as warning the driver for the ability to react quickly in the moment of danger. The system includes real-time tracking of wildlife near the road and on the road. The implementation of a vehicle-wildlife collision avoidance system has the potential to protect the lives and health of all living beings, as well as the property of drivers in difficult driving conditions [21].
Figure 1. shows the section of the country road between the danger signs on the road, more precisely Point 1 and Point 2, which represent the starting and ending points of the road section from different directions. On the observed section of the road, there is a possible danger of the appearance of wild animals near the roadway, which is marked with danger signs on the road (Point 8 and Point 3, Fig. 1.).
Point 1 and Point 2 are located at a distance of 150–250 meters from the wildlife traffic sign on the road, but viewed from opposite directions. A distance of 150–250 meters represents the length of the vehicle's stopping distance in the event of an emergency. Between Point 1 and Point 2 in the road infrastructure, RSUs (Road Side Unit) are distributed along the entire length of the section between the mentioned points. Thus, RSUs cover the entire length of the road section, even along the road at Point 1 and Point 2, so that wild animals cannot enter the road without first being detected. Point 4 shows detected wild animals that approached the observed road section. The RSU consists of a sensor assembly and a communication device. RSU are located in infrastructure next to roads should preferably have low energy requirements. The type of sensor installed in the RSU, which meets low energy requirements, are PIR (Passive InfraRed) sensors. The two slots that make up the PIR sensor are made of IR (InfraRed) material that signals the movement of wildlife [22, 23]. In the presence of IR radiation from wildlife, the sensor detects the radiation and directly converts it into electrical impulses. Information about the change in the thermal radiation of wildlife enables the detection of objects.
Detection of the presence of wildlife using the PIR sensor is possible at a distance of up to 7 m with a coverage angle of 120 degrees and an overlap angle of 10 degrees. In order to ensure complete coverage of the zone of operation of the RSU, it is necessary to place them at a distance of approximately 12 meters. The task of RSU enriched with PIR sensors is to provide information about the presence of wildlife [24]. In the RSU, data is collected and, if necessary, local data processing is performed, and then the relevant data is sent via a communication device to the central processing and data storage in the cloud, Point 7 and Point 6 in Fig. 1. The communication device shown in Point 5 in Fig. 1. depends from infrastructure requirements, network coverage, terrain configuration, vegetation density, presence of obstacles on the side of the road, etc. Also, the communication device enables the transfer of data from the RSU to further distribution via the Internet.
Processes Flow of the VWCA system from RSU to users is shown in Fig. 2.
The Process Flow in the VWCA system consists of five processes:
1) Data collection process. The data collection process is carried out using sensor systems placed along the road. Sensor systems consist of RSUs that contain a PIR motion sensor, an Raspberry Pi device, a communication device, and a power source.
2) Data fusion process. The data fusion process is performed with RSU 1 ... RSU n nodes. The collected data form a database that is located in the cloud on a web server.
3) Data processing. Data processing is also done in the cloud on a web server. The collected data is processed in such a way as to give priority to data on potential road hazards. Therefore, each processed data will not have the same priority during processing.
4) Data analysis process. Collected data is analyzed to identify potential wildlife hazards on the road. The analyzed data will not have the same priority during the distribution of the data, the priority is given to the data that detects wildlife near the road.
5) Data distribution process. The data distribution process is directed towards the driver through the web application. The distribution of data is carried out for the purpose of timely reaction of the driver, in order to avoid direct contact of the vehicle with wildlife.
Data processing and distribution processes should be completed in the shortest possible time, in order to increase the time required for the driver to stop the vehicle or reduce the driving speed. The process of data distribution has the role of informing and warning drivers about the appearance of wildlife near the road, and it can be realized with the help of a software application designed for the web environment. The VWCA system is scalable and can be adapted to vehicles using multicast in a cooperatively connected vehicular communication network (CVCN).