Sistem Monitoring Kerapihan Laboratorium Berdasarkan Computer Vision Menggunakan YOLOv8 Dengan Object Detection

Sari, Dwi Kartika Sari (2026) Sistem Monitoring Kerapihan Laboratorium Berdasarkan Computer Vision Menggunakan YOLOv8 Dengan Object Detection. Diploma thesis, Institut Teknologi Sepuluh Nopember.

Text 2040211024_Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (3MB) | Request a copy

Abstract

Kondisi laboratorium yang tidak rapi setelah digunakan, seperti masih terdapat barang di atas meja, dapat mengganggu aktivitas praktikum berikutnya dan memerlukan pemeriksaan secara manual oleh petugas. Penelitian ini bertujuan merancang dan mengimplementasikan sistem monitoring kondisi laboratorium berdasarkan computer vision menggunakan metode YOLOv8 dengan object detection. Sistem mendeteksi objek Person, Table, Laptop, dan Item, kemudian memanfaatkan Region of Interest (ROI) pada meja serta metode overlap untuk menentukan apakah suatu objek berada di atas meja. Monitoring kondisi meja dilakukan ketika hasil perhitungan orang menunjukkan tidak ada orang di dalam laboratorium, sedangkan hasil deteksi dan status meja ditampilkan melalui dashboard, dicatat ke dalam file log dan dikirimkan melalui email sebagai notifikasi. Model dilatih menggunakan pembagian dataset 70% data pelatihan, 20% data validasi, dan 10% data uji. Hasil pelatihan menunjukkan performa yang baik dengan nilai rata-rata dari precision 87%, recall 89%, F1-Score 88%, dan Accuracy 94%. Berdasarkan hasil implementasi, sistem menghasilkan informasi mengenai kondisi meja dalam keadaan rapi maupun berantakan berdasarkan analisis overlap antara bounding box objek dan Region of Interest (ROI) meja, serta menyediakan mekanisme pengiriman notifikasi melalui email ketika laboratorium dalam kondisi kosong dan masih terdapat barang yang tertinggal di atas meja. ===================================================================================================================================
Unkempt laboratory conditions after use, such as still on the table, may with subsequent practical activities and require manual manual inspection by the officer. This study aims to design and implement a computer vision-based laboratory condition monitoring system using the YOLOv8 method with object detection. The system detects Person, Table, Laptop, and Item objects, then uses the Region of Interest (ROI) on the table as well as the overlap method to determine whether an object is on table. Monitoring of table conditions is performed when the results of the person calculation show on one in the laboratory, while the results of the detection and status of the table are displayed through the dashboard, recorded into the log file and sent via email as a notification. Models were trained using a dataset 70% training data, 20% validation data, and 10% test data. The training results showed good performance with an mAP@50 score of 93% and an mAP@50-95 score of 79% during the training process. Implementation of the system succeeded in detecting real-time laboratory conditions with an average value of 87%, recall 89%, F1-Score 88%, and accuracy 94%. Based on the results of the implementation, the system generates information about the condition of the table in a neat or messy state based on an analysis of the overlap between the building box object and the Region of Interest (ROI) table, and provide an email notification delivery mechanism when the laboratory is empty and there are still items left on the table

Item Type:	Thesis (Diploma)
Uncontrolled Keywords:	computer vision, object detection, YOLOv8, sistem notifikasi ============================================================ computer vision, object detection, YOLOv8, notification system
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques. Image analysis--Data processing. T Technology > TA Engineering (General). Civil engineering (General) > TA593.35 Instruments, cameras, etc. T Technology > TA Engineering (General). Civil engineering (General) > TA660.F7 Structural frames.
Divisions:	Faculty of Vocational > 36304-Automation Electronic Engineering
Depositing User:	Dwi Kartika Sari
Date Deposited:	07 Aug 2026 07:38
Last Modified:	07 Aug 2026 07:38
URI:	http://repository.its.ac.id/id/eprint/144208

Actions (login required)

View Item