Skripsi
DETEKSI KEPADATAN KENDARAAN MENGGUNAKAN YOLO DENGAN ALGORITMA 1-DIMENSIONAL CONVOLUTIONAL NEURAL NETWORK (1D CNN) BERDASARKAN REKAMAN CCTV DI JALAN KOTA PALEMBANG
This Automatic vehicle density detection on major roads in Palembang City is performed by combining the YOLOv8 method and the 1- Dimensional Convolutional Neural Network (1D-CNN) algorithm. YOLOv8 detects vehicle objects, namely cars and motorcycles, from image datasets and CCTV video recordings. The detection results, in the form of vehicle counts, are used as numerical input to the 1D-CNN model to classify traffic conditions into three categories: Smooth (50 vehicles). The dataset consists of 4,500 images that have undergone preprocessing and labeling. The data is divided into three parts: 80% for training, 10% for validation, and 10% for testing. YOLOv8 training yielded a mean Average Precision (mAP) of 75.4% and an average detection accuracy of 71.54%. The 1D-CNN model achieved a classification accuracy of 91.1%. System testing using 76 CCTV videos from several intersections in Palembang resulted in an average accuracy of 93.42%. These results show that the combination of YOLOv8 and 1D-CNN is effective for real-time traffic density monitoring and supports data-driven decision-making in urban traffic management.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2507005249 | T181790 | T1817902025 | Central Library (References) | Available but not for loan - Not for Loan |
No other version available