Authors :
Dr. Arulmurugan L; Pradeep S; Nikhil Raghav V; Bharath Kumar S P
Volume/Issue :
Volume 8 - 2023, Issue 10 - October
Google Scholar :
https://tinyurl.com/52nm9mwn
Scribd :
https://tinyurl.com/yc72bdtu
DOI :
https://doi.org/10.5281/zenodo.10049773
Abstract :
In forest and agricultural field human and
animal conflict is a major problem where enormous
amount if resources are lost and human and animal life
are endangered. Due to this animal lives are endangered.
People lose their crops, cattle and in some extreme cases
they lose their lives. In current era of continuously
developing IOT sensors and cloud technology, Image
processing in remote areas became easy and cheap. To
tackle this problem, we have developed a system with
cameras and remote cloud server to capture live footage
of area to be protected and processing the footage in a
live server to detect animal intrusion. For hardware
components, we have used ESP32 camera module with
Wifi to capture live footages. The captured footage is
sent to a remote server or PC for further processing. A
yolov5 based pre-trained algorithm is used for object
detection. To achieve maximum accuracy the algorithm
is trained with thousands of animal photos multiple
times until desired accuracy is reached (~98%). The
footage is processed and based on the type of animal
detected a message or alert is sent to the farmer or forest
department from the server and a speaker can be used to
scare the animals.
Keywords :
Animal Detection, ESP32 CAM, Yolov5.
In forest and agricultural field human and
animal conflict is a major problem where enormous
amount if resources are lost and human and animal life
are endangered. Due to this animal lives are endangered.
People lose their crops, cattle and in some extreme cases
they lose their lives. In current era of continuously
developing IOT sensors and cloud technology, Image
processing in remote areas became easy and cheap. To
tackle this problem, we have developed a system with
cameras and remote cloud server to capture live footage
of area to be protected and processing the footage in a
live server to detect animal intrusion. For hardware
components, we have used ESP32 camera module with
Wifi to capture live footages. The captured footage is
sent to a remote server or PC for further processing. A
yolov5 based pre-trained algorithm is used for object
detection. To achieve maximum accuracy the algorithm
is trained with thousands of animal photos multiple
times until desired accuracy is reached (~98%). The
footage is processed and based on the type of animal
detected a message or alert is sent to the farmer or forest
department from the server and a speaker can be used to
scare the animals.
Keywords :
Animal Detection, ESP32 CAM, Yolov5.
