Cover Image

Real-time attribute based deep learning network for traffic sign detection

Traffic sign detection is one of the key components of the Advanced Driving Assistant System (ADAS), which aims to detect and classify street signs in real time. However, traffic sign detection has challenges in real applications requiring high precision and real-time recall. Those challenges are du...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohamed Elhawary, Hossamelden, Suddamalla, Upendra, Shapiai, Mohd. Ibrahim, Wong, Anthony, Zamzuri, Hairi
Format: Conference or Workshop Item
Published: 2022
Subjects:
T Technology (General)
Online Access:http://eprints.utm.my/id/eprint/98694/
http://dx.doi.org/10.1109/ICITEE56407.2022.9954110
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.98694
record_format eprints
spelling my.utm.986942023-02-02T05:47:10Z http://eprints.utm.my/id/eprint/98694/ Real-time attribute based deep learning network for traffic sign detection Mohamed Elhawary, Hossamelden Suddamalla, Upendra Shapiai, Mohd. Ibrahim Wong, Anthony Zamzuri, Hairi T Technology (General) Traffic sign detection is one of the key components of the Advanced Driving Assistant System (ADAS), which aims to detect and classify street signs in real time. However, traffic sign detection has challenges in real applications requiring high precision and real-time recall. Those challenges are due to the small object size and class imbalance. Recently, researchers have proposed several techniques to improve the detection quality by enriching the features through a multiscale network, introducing attention mechanisms and augmentation techniques to improve the features of tiny objects. To overcome class imbalance researchers proposed cascaded networks and various loss functions. However, those existing techniques and mechanisms added more complexity to the model. Meanwhile, the imbalance affects single-stage networks such as YOLO, which causes a lower recall for minor classes. We proposed a new training method for a single-stage detection network, known as Real Time Attribute Based Deep Learning Detection Network (Real Time-Attribute DL). We introduced new attributes to the loss and Non-Maximum Suppression (NMS) to reduce the class number by categorizing it based on the shape of the traffic sign while maintaining the same number of classes. Our proposed method extends the YOLO detection head to have four main parameters: objectiveness, regression, class, and attribute. We modify the loss function to train the network jointly between class and attribute. We validate our proposed technique with Tsinghua-Tencent 100K(TT100K) as a benchmark dataset. The results show that our proposed technique improves the recall index from 85.85% to 94.26% in yolov4-tiny-31 with a 0.8% improvement in precision and improves the recall index from 93.51% to 96.68% in yolov4 with a drop by 2% in precision without adding extra complexity to the main network. The proposed technique offers a better recall index than the baseline, especially for imbalanced datasets such as TT100K datasets. 2022 Conference or Workshop Item PeerReviewed Mohamed Elhawary, Hossamelden and Suddamalla, Upendra and Shapiai, Mohd. Ibrahim and Wong, Anthony and Zamzuri, Hairi (2022) Real-time attribute based deep learning network for traffic sign detection. In: 14th International Conference on Information Technology and Electrical Engineering, ICITEE 2022, 18 - 19 October 2022, Yogyakarta, Indonesia. http://dx.doi.org/10.1109/ICITEE56407.2022.9954110
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
topic T Technology (General)
spellingShingle T Technology (General)
Mohamed Elhawary, Hossamelden
Suddamalla, Upendra
Shapiai, Mohd. Ibrahim
Wong, Anthony
Zamzuri, Hairi
Real-time attribute based deep learning network for traffic sign detection
description Traffic sign detection is one of the key components of the Advanced Driving Assistant System (ADAS), which aims to detect and classify street signs in real time. However, traffic sign detection has challenges in real applications requiring high precision and real-time recall. Those challenges are due to the small object size and class imbalance. Recently, researchers have proposed several techniques to improve the detection quality by enriching the features through a multiscale network, introducing attention mechanisms and augmentation techniques to improve the features of tiny objects. To overcome class imbalance researchers proposed cascaded networks and various loss functions. However, those existing techniques and mechanisms added more complexity to the model. Meanwhile, the imbalance affects single-stage networks such as YOLO, which causes a lower recall for minor classes. We proposed a new training method for a single-stage detection network, known as Real Time Attribute Based Deep Learning Detection Network (Real Time-Attribute DL). We introduced new attributes to the loss and Non-Maximum Suppression (NMS) to reduce the class number by categorizing it based on the shape of the traffic sign while maintaining the same number of classes. Our proposed method extends the YOLO detection head to have four main parameters: objectiveness, regression, class, and attribute. We modify the loss function to train the network jointly between class and attribute. We validate our proposed technique with Tsinghua-Tencent 100K(TT100K) as a benchmark dataset. The results show that our proposed technique improves the recall index from 85.85% to 94.26% in yolov4-tiny-31 with a 0.8% improvement in precision and improves the recall index from 93.51% to 96.68% in yolov4 with a drop by 2% in precision without adding extra complexity to the main network. The proposed technique offers a better recall index than the baseline, especially for imbalanced datasets such as TT100K datasets.
format Conference or Workshop Item
author Mohamed Elhawary, Hossamelden
Suddamalla, Upendra
Shapiai, Mohd. Ibrahim
Wong, Anthony
Zamzuri, Hairi
author_facet Mohamed Elhawary, Hossamelden
Suddamalla, Upendra
Shapiai, Mohd. Ibrahim
Wong, Anthony
Zamzuri, Hairi
author_sort Mohamed Elhawary, Hossamelden
title Real-time attribute based deep learning network for traffic sign detection
title_short Real-time attribute based deep learning network for traffic sign detection
title_full Real-time attribute based deep learning network for traffic sign detection
title_fullStr Real-time attribute based deep learning network for traffic sign detection
title_full_unstemmed Real-time attribute based deep learning network for traffic sign detection
title_sort real-time attribute based deep learning network for traffic sign detection
publishDate 2022
url http://eprints.utm.my/id/eprint/98694/
http://dx.doi.org/10.1109/ICITEE56407.2022.9954110
_version_ 1758578007056842752
score 13.211869

Similar Items