Authors :
Amerasinghe N.D.K; Udara I.W.A.S.; Somabandu B.P.S.; Jayakody J.A.B.U.; Nelum Amarasena; Rivoni De Zoysa
Volume/Issue :
Volume 8 - 2023, Issue 10 - October
Google Scholar :
https://tinyurl.com/bdend7k2
Scribd :
https://tinyurl.com/kjvmm7eh
DOI :
https://doi.org/10.5281/zenodo.10061027
Abstract :
This research paper presents a mobile
application-based solution for real-time road safety
aimed at mitigating animal-vehicle conflicts in Sri
Lanka. The proposed system is developed in response to
the increasing incidents of animal-vehicle collisions,
which pose significant risks to both human safety and
wildlife conservation efforts. By combining knowledge-
based case studies and crowd-sourcing techniques, the
application aims to identify animal habitats and
behaviors based on user location, enabling drivers to
take proactive measures to prevent such accidents.
Image processing is used to identify objects using
YOLOv7 technology. Ultrasonic sensors, a
microcontroller, the Doppler Effect, and relative velocity
calculations are used to segment the signal-to-noise ratio
and alert the driver of any nearby animals. The research
also provides guidelines for implementing methods to
reduce animal-vehicle collisions and raises awareness
among the public regarding the importance of road
safety in wildlife-rich areas. Upon detection of the
animal, the system emits an anti-frequency range
tailored to specific species, effectively deterring them
from approaching the vehicle. Through the mobile
application, users can access real-time alerts, receive
feedback from others, and contribute to a collective
effort in ensuring safer roads for both humans and
animals.
This research paper presents a mobile
application-based solution for real-time road safety
aimed at mitigating animal-vehicle conflicts in Sri
Lanka. The proposed system is developed in response to
the increasing incidents of animal-vehicle collisions,
which pose significant risks to both human safety and
wildlife conservation efforts. By combining knowledge-
based case studies and crowd-sourcing techniques, the
application aims to identify animal habitats and
behaviors based on user location, enabling drivers to
take proactive measures to prevent such accidents.
Image processing is used to identify objects using
YOLOv7 technology. Ultrasonic sensors, a
microcontroller, the Doppler Effect, and relative velocity
calculations are used to segment the signal-to-noise ratio
and alert the driver of any nearby animals. The research
also provides guidelines for implementing methods to
reduce animal-vehicle collisions and raises awareness
among the public regarding the importance of road
safety in wildlife-rich areas. Upon detection of the
animal, the system emits an anti-frequency range
tailored to specific species, effectively deterring them
from approaching the vehicle. Through the mobile
application, users can access real-time alerts, receive
feedback from others, and contribute to a collective
effort in ensuring safer roads for both humans and
animals.
