NORMA eResearch @NCI Library

Deer Surveillance System in Public Parks Using Deep Learning

Cardenas Rodríguez, Mardwin Alejandro (2022) Deer Surveillance System in Public Parks Using Deep Learning. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (2MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


The importance of disease transmission between wild animals and people is one of the most serious issue while people trying to get too close to wildlife. This research developed a method for detecting persons who are not following park regulations by utilizing deep learning approaches to detect people and deers in photos or videos. The suggested system used a YOLOv5 object detection algorithm to detect humans approaching deer too closely. The presented method was designed to be used in a drone video, and the system was well-trained to spot people and deer on camera or videos. The most significant limitation of this study was the lack of drone videos from the Phoenix park, as flying a drone is not permitted. We could not turn the video into a top-down image for distance estimation in the 2-D area because there were no camera specifications to do it, Despite the limitations mentioned above, the model was effectively trained to recognize people and deer, as well as to provide a document with the labels and the coordinates of the object detected in the image for further processing.

Item Type: Thesis (Masters)
Uncontrolled Keywords: YOLOv5; Deep Learning; Surveillance System; Object Recognition
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QL Zoology
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 19 Jan 2023 15:33
Last Modified: 06 Mar 2023 15:44

Actions (login required)

View Item View Item