Next Article in Journal
Experimental Investigation of the Physical Properties and Microstructure of Slate under Wetting and Drying Cycles Using Micro-CT and Ultrasonic Wave Velocity Tests
Next Article in Special Issue
Wideband Anti-Jamming Based on Free Space Optical Communication and Photonic Signal Processing
Previous Article in Journal
CNN Training with Twenty Samples for Crack Detection via Data Augmentation
Previous Article in Special Issue
Smart Contract Centric Inference Engine For Intelligent Electric Vehicle Transportation System
Open AccessArticle

A Multiscale Recognition Method for the Optimization of Traffic Signs Using GMM and Category Quality Focal Loss

1
School of Electronic Information, Hangzhou Dianzi University, Hangzhou 310018, China
2
Zhejiang Provincial Key Lab of Equipment Electronics, Hangzhou 310018, China
3
Department of Electronic and Computer Engineering, Brunel University London, London UB8 3PH, UK
4
The College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China
*
Author to whom correspondence should be addressed.
Sensors 2020, 20(17), 4850; https://doi.org/10.3390/s20174850
Received: 2 August 2020 / Revised: 24 August 2020 / Accepted: 25 August 2020 / Published: 27 August 2020
Effective traffic sign recognition algorithms can assist drivers or automatic driving systems in detecting and recognizing traffic signs in real-time. This paper proposes a multiscale recognition method for traffic signs based on the Gaussian Mixture Model (GMM) and Category Quality Focal Loss (CQFL) to enhance recognition speed and recognition accuracy. Specifically, GMM is utilized to cluster the prior anchors, which are in favor of reducing the clustering error. Meanwhile, considering the most common issue in supervised learning (i.e., the imbalance of data set categories), the category proportion factor is introduced into Quality Focal Loss, which is referred to as CQFL. Furthermore, a five-scale recognition network with a prior anchor allocation strategy is designed for small target objects i.e., traffic sign recognition. Combining five existing tricks, the best speed and accuracy tradeoff on our data set (40.1% mAP and 15 FPS on a single 1080Ti GPU), can be achieved. The experimental results demonstrate that the proposed method is superior to the existing mainstream algorithms, in terms of recognition accuracy and recognition speed. View Full-Text
Keywords: image recognition; traffic sign; Gaussian Mixture Model; multiscale recognition; category imbalance image recognition; traffic sign; Gaussian Mixture Model; multiscale recognition; category imbalance
Show Figures

Figure 1

MDPI and ACS Style

Gao, M.; Chen, C.; Shi, J.; Lai, C.S.; Yang, Y.; Dong, Z. A Multiscale Recognition Method for the Optimization of Traffic Signs Using GMM and Category Quality Focal Loss. Sensors 2020, 20, 4850. https://doi.org/10.3390/s20174850

AMA Style

Gao M, Chen C, Shi J, Lai CS, Yang Y, Dong Z. A Multiscale Recognition Method for the Optimization of Traffic Signs Using GMM and Category Quality Focal Loss. Sensors. 2020; 20(17):4850. https://doi.org/10.3390/s20174850

Chicago/Turabian Style

Gao, Mingyu; Chen, Chao; Shi, Jie; Lai, Chun S.; Yang, Yuxiang; Dong, Zhekang. 2020. "A Multiscale Recognition Method for the Optimization of Traffic Signs Using GMM and Category Quality Focal Loss" Sensors 20, no. 17: 4850. https://doi.org/10.3390/s20174850

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop