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 u...

Full description

Saved in:
Bibliographic Details
Main Authors: Umi Chasanah, Gilang Putra, Sahid Bismantoko, Sofwan Hidayat, Tri Widodo, Mohammad Rosyidi
Format: Article
Language:English
Published: ITB Journal Publisher 2024-10-01
Series:Journal of ICT Research and Applications
Subjects:
Online Access:https://journals.itb.ac.id/index.php/jictra/article/view/20047
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849687447025221632
author Umi Chasanah
Gilang Putra
Sahid Bismantoko
Sofwan Hidayat
Tri Widodo
Mohammad Rosyidi
author_facet Umi Chasanah
Gilang Putra
Sahid Bismantoko
Sofwan Hidayat
Tri Widodo
Mohammad Rosyidi
author_sort Umi Chasanah
collection DOAJ
description 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.
format Article
id doaj-art-5db341e16a104ff88fcd8cf0c5e89e90
institution DOAJ
issn 2337-5787
2338-5499
language English
publishDate 2024-10-01
publisher ITB Journal Publisher
record_format Article
series Journal of ICT Research and Applications
spelling doaj-art-5db341e16a104ff88fcd8cf0c5e89e902025-08-20T03:22:19ZengITB Journal PublisherJournal of ICT Research and Applications2337-57872338-54992024-10-01182saLFIA: Semi-automatic Live Feeds Image Annotation Tool for Vehicle Classification DatasetUmi Chasanah0Gilang Putra1Sahid Bismantoko2Sofwan Hidayat3Tri Widodo4Mohammad Rosyidi5Research Center for Artificial Intelligence and Cyber Security, National Research and Innovation Agency, Jalan Cisitu Sangkuriang, Bandung 40135Research Center for Artificial Intelligence and Cyber Security, National Research and Innovation Agency, Jalan Cisitu Sangkuriang, Bandung 40135Research Center for Computing, National Research and Innovation Agency, Jalan Raya Jakarta - Bogor KM 46 Cibinong 16911Research Center for Transportation Technology, National Research and Innovation Agency, Kawasan PUSPIPTEK, Tangerang Selatan 15314Research Center for Transportation Technology, National Research and Innovation Agency, Kawasan PUSPIPTEK, Tangerang Selatan 15314Research Center for Computing, National Research and Innovation Agency, Jalan Raya Jakarta - Bogor KM 46 Cibinong 16911 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. https://journals.itb.ac.id/index.php/jictra/article/view/20047annotation toolCCTVdatasetvehicle classificationYOLOSSD
spellingShingle Umi Chasanah
Gilang Putra
Sahid Bismantoko
Sofwan Hidayat
Tri Widodo
Mohammad Rosyidi
saLFIA: Semi-automatic Live Feeds Image Annotation Tool for Vehicle Classification Dataset
Journal of ICT Research and Applications
annotation tool
CCTV
dataset
vehicle classification
YOLO
SSD
title saLFIA: Semi-automatic Live Feeds Image Annotation Tool for Vehicle Classification Dataset
title_full saLFIA: Semi-automatic Live Feeds Image Annotation Tool for Vehicle Classification Dataset
title_fullStr saLFIA: Semi-automatic Live Feeds Image Annotation Tool for Vehicle Classification Dataset
title_full_unstemmed saLFIA: Semi-automatic Live Feeds Image Annotation Tool for Vehicle Classification Dataset
title_short saLFIA: Semi-automatic Live Feeds Image Annotation Tool for Vehicle Classification Dataset
title_sort salfia semi automatic live feeds image annotation tool for vehicle classification dataset
topic annotation tool
CCTV
dataset
vehicle classification
YOLO
SSD
url https://journals.itb.ac.id/index.php/jictra/article/view/20047
work_keys_str_mv AT umichasanah salfiasemiautomaticlivefeedsimageannotationtoolforvehicleclassificationdataset
AT gilangputra salfiasemiautomaticlivefeedsimageannotationtoolforvehicleclassificationdataset
AT sahidbismantoko salfiasemiautomaticlivefeedsimageannotationtoolforvehicleclassificationdataset
AT sofwanhidayat salfiasemiautomaticlivefeedsimageannotationtoolforvehicleclassificationdataset
AT triwidodo salfiasemiautomaticlivefeedsimageannotationtoolforvehicleclassificationdataset
AT mohammadrosyidi salfiasemiautomaticlivefeedsimageannotationtoolforvehicleclassificationdataset