Smart pet micturition behavior corrector: Utilization of computer vision for pet urinary activity detection, with adaptive deterrence, and progress monitoring

By: Hizole, Marc Gabriel V.; Panganiban, Justin Razzi V
Language: English Publisher: . . c2025Description: Capstone Project: (Bachelor of Science in Information Technology) - Pamantasan ng Lungsod ng Maynila, 2025Content type: text Media type: unmediated Carrier type: volumeGenre/Form: academic writingDDC classification: .
Contents:
ABSTRACT: Pet owners often struggle to prevent their pets from urinating in unwanted areas, especially since they cannot always be present to monitor and deter this behavior in real time. This study addresses this issue by developing an automated system for real-time detection, deterrence, and monitoring of pet urination activity. The study had three key objectives: to develop a real-time pet urination detection system using YOLOv8 to identify and record pets urination events based on visual cues, to create an adaptive audio deterrence system that adjusts alert intensity based on the severity of urination behavior, and to provide pet owners with progress reports, including a dashboard with urination activity logs and heat maps. The system was developed using Django for the backend and Arduino IDE for the ESP32. Additionally, the AGILE Scrum SDLC methodology was employed throughout the development process. The system uses a custom-trained object detection model in YOLOv8 for real-time identification of pet urination events, and a pre-trained YOLOv8 model along with Bot-SORT for general dog detection. For triggering adaptive audio alerts, an ESP32-controlled Bluetooth speaker. The system was effective in detecting urination activity through the combined custom-trained and pre-trained YOLOv8 models. Furthermore, the adaptive audio deterrence system was effective based on the frequency of urination incidents, with louder deterrents for repeated offenses and softer cues for minor ones. Moreover, the third objective was realized through the system’s dashboard which tracked pet urination activity, displaying data through a pie chart and a table of comprehensive information of urination incidents. Finally, the heat map feature provided real-time data visualizing frequent urination spots. These demonstrated the system’s success in fulfilling the study’s objectives.
Tags from this library: No tags from this library for this title. Log in to add tags.
    Average rating: 0.0 (0 votes)
Item type Current location Home library Collection Call number Status Date due Barcode Item holds
Thesis/Dissertation PLM
PLM
Filipiniana Section 		Filipiniana-Thesis T58.6 H59 2025 (Browse shelf) Available FT8850
Total holds: 0

ABSTRACT: Pet owners often struggle to prevent their pets from urinating in unwanted areas, especially since they cannot always be present to monitor and deter this behavior in real time. This study addresses this issue by developing an automated system for real-time detection, deterrence, and monitoring of pet urination activity. The study had three key objectives: to develop a real-time pet urination detection system using YOLOv8 to identify and record pets urination events based on visual cues, to create an adaptive audio deterrence system that adjusts alert intensity based on the severity of urination behavior, and to provide pet owners with progress reports, including a dashboard with urination activity logs and heat maps. The system was developed using Django for the backend and Arduino IDE for the ESP32. Additionally, the AGILE Scrum SDLC methodology was employed throughout the development process. The system uses a custom-trained object detection model in YOLOv8 for real-time identification of pet urination events, and a pre-trained YOLOv8 model along with Bot-SORT for general dog detection. For triggering adaptive audio alerts, an ESP32-controlled Bluetooth speaker. The system was effective in detecting urination activity through the combined custom-trained and pre-trained YOLOv8 models. Furthermore, the adaptive audio deterrence system was effective based on the frequency of urination incidents, with louder deterrents for repeated offenses and softer cues for minor ones. Moreover, the third objective was realized through the system’s dashboard which tracked pet urination activity, displaying data through a pie chart and a table of comprehensive information of urination incidents. Finally, the heat map feature provided real-time data visualizing frequent urination spots. These demonstrated the system’s success in fulfilling the study’s objectives.

Filipiniana

There are no comments for this item.

to post a comment.

© Copyright 2024 Phoenix Library Management System - Pinnacle Technologies, Inc. All Rights Reserved.