Tools
Tools
Dineley, A, Natalia, F and Sudirman, S (2024) DATA AUGMENTATION FOR OCCLUSION-ROBUST TRAFFIC SIGN RECOGNITION USING DEEP LEARNING. ICIC Express Letters, Part B: Applications, 15 (4). pp. 381-388. ISSN 2185-2766
|
Text
DATA AUGMENTATION FOR OCCLUSION-ROBUST TRAFFIC SIGN RECOGNITION USING DEEP LEARNING.pdf - Published Version Download (2MB) | Preview |
Abstract
Traffic sign recognition is an essential feature for self-driving cars. It provides input to the decision-making process when maneuvering through traffic in real time. Correct identification and classification of traffic signs are a challenge because they may be occluded by natural entities, such as leaves and trees, or man-made such as graffiti. In this paper, we present the result of our study into achieving occlusion-robust traffic sign recognition by augmenting the data used to train deep learning models. The data augmentation is performed by applying random occlusion of varying coverage percentages to the traffic sign images. We investigated the performance of four different deep network architectures to recognize 11 German speed limit signs using transfer learning techniques on their respective pre-trained models (AlexNet, VGG19, ResNet50, and GoogLeNet). The results of our experiment show that our data augmentation technique improves the recognition accuracy at higher occlusion band (61%-70% occlusion) by 17% using GoogLeNet with a slight 2% hit in accuracy at lower occlusion band (1%-10% occlusion). Our study concludes that our data augmentation technique could significantly improve the recognition performance of all models when the traffic sign images are severely occluded.
| Item Type: | Article |
|---|---|
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Computer Science & Mathematics |
| Publisher: | ICIC International |
| SWORD Depositor: | A Symplectic |
| Date Deposited: | 24 Apr 2024 10:11 |
| Last Modified: | 24 Apr 2024 10:15 |
| DOI or ID number: | 10.24507/icicelb.15.04.381 |
| URI: | https://researchonline.ljmu.ac.uk/id/eprint/23129 |
 |
View Item |