saLFIA: Semi-automatic Live Feeds Image Annotation Tool for Vehicle Classification Dataset

Deep learning’s reliance on abundant data with accurate annotations presents a significant drawback, as developing datasets is often time-consuming and costly for specific problems. To address this drawback, we propose a semi-automatic live-feed image annotation tool called saLFIA. Our case study utilized CCTV data from Indonesia’s toll roads as one of the sources for live-feed images. The primary contribution of saLFIA is a labeling tool designed to generate new datasets from public source images, focusing on vehicle classification using YOLOv3 and SSD algorithms. The evaluation results indicated that SSD achieved higher accuracy with fewer initial images, while YOLOv3 reached maximum accuracy with larger initial datasets, resulting in 8 misdetections out of 380 objects. The saLFIA tool simplifies the annotation process, presenting a labeling tool for creating annotated datasets in a single operation. saLFIA is available at URL https://github.com/gilangmantara/salfia.