Detect, Track and Classify Using YOLOv9 and ByteTrack
About Project:
Face Detection: Trained using YOLOv9.
Custom Class Detection: Trained with YOLOv9, detecting 14 classes:
['firearm', 'knife/Sword', 'smoke', 'tank', 'warship', 'Missile', 'artillery', 'nudity', 'lingerie', 'aircraft', 'Cigarettes/Cigars/e-cigarettes', 'fire', 'cut/blood', 'bruise']
Classification: Frame-wise classification for violence, normal, and nudity classes, also using YOLOv9.
Combined the above three models (face detection, custom class detection, and classification) and final output displayed in video