TY - JOUR
T1 - Weight analysis for various prohibitory sign detection and recognition using deep learning
AU - Dewi, Christine
AU - Chen, Rung-Ching
AU - Yu, Hui
PY - 2020/8/29
Y1 - 2020/8/29
N2 - Traffic sign recognition is meaningful for real-world applications such as self-sufficient driving, traffic surveillance, and driver safety. However, traffic sign recognition is a hard problem because different sizes, illuminations, and noises affect the sign detection and recognition. This work recognizes Taiwan’s prohibitory signs using deep learning methods. First, we develop a traffic sign database since there is no such kind of database available in Taiwan. Next, we adopt three different You Only Look Once (Yolo) networks (Yolo A, Yolo B, and Yolo C) and three various Yolo V3 SPP networks (Yolo D, Yolo E, and Yolo F) for prohibitory sign recognition. Finally, we conduct the comparative experiment of Yolo V3 and Yolo V3 SPP with different weights provided by the darknet framework (the best weight, the final weight, and the last weight). Experimental results show that the mean average precision (mAP) observation of all models that the Yolo V3 SPP is better than other models. Yolo D took the optimum average accuracy at 99.0%, followed by Yolo E and Yolo F 98.9%. The accuracy of Yolo V3 SPP is growing within the detection time, but it needs more time to identify the sign.
AB - Traffic sign recognition is meaningful for real-world applications such as self-sufficient driving, traffic surveillance, and driver safety. However, traffic sign recognition is a hard problem because different sizes, illuminations, and noises affect the sign detection and recognition. This work recognizes Taiwan’s prohibitory signs using deep learning methods. First, we develop a traffic sign database since there is no such kind of database available in Taiwan. Next, we adopt three different You Only Look Once (Yolo) networks (Yolo A, Yolo B, and Yolo C) and three various Yolo V3 SPP networks (Yolo D, Yolo E, and Yolo F) for prohibitory sign recognition. Finally, we conduct the comparative experiment of Yolo V3 and Yolo V3 SPP with different weights provided by the darknet framework (the best weight, the final weight, and the last weight). Experimental results show that the mean average precision (mAP) observation of all models that the Yolo V3 SPP is better than other models. Yolo D took the optimum average accuracy at 99.0%, followed by Yolo E and Yolo F 98.9%. The accuracy of Yolo V3 SPP is growing within the detection time, but it needs more time to identify the sign.
U2 - 10.1007/s11042-020-09509-x
DO - 10.1007/s11042-020-09509-x
M3 - Article
SN - 1380-7501
JO - Multimedia Tools and Applications
JF - Multimedia Tools and Applications
ER -