Efficient Video Object Detection of Indoor Furniture and Home Appliances
Fuangfar Pensiri, Phasuwut Chunnapiya, Wanida Khamprapai, Porawat Visutsak · 2024
Video object detection extends the principles of object detection in still images to the realm of moving pictures. It involves identifying and localizing objects of interest within each frame of a video sequence. In this work, we propose an efficient method for video object detection of indoor furniture and home appliances using YOLO, data augmentation, and a novel frame sampling technique. We tested our proposed method in a real-world environment, and performance measurements demonstrate a 24.73% increase in mean average precision (mAP50-95) and an 89.77% reduction in processing time compared to the standard YOLOv7 baseline.