Research on Traffic Sign Detection Based on Convolutional Neural Network

Wang, Zhongyu; Guo, Hui

doi:10.1145/3356422.3356457

Cited by 8 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang and Guo [11] suggested the YOLO neural network model is configured using an updated CNN model focused on the YOLO model, darknet 53. By adding batch normalization and RPN networks, it can enhance network architecture for traffic sign detection.…”

Section: Related Workmentioning

confidence: 99%

Road Sign Detection Using Variants of YOLO and R-CNN: An Analysis from the Perspective of Bangladesh

Lima

Kabir

Das

et al. 2021

Lecture Notes on Data Engineering and Communications Technologies

View full text Add to dashboard Cite

Road sign detection represents a feature that assures the safety of drivers, vehicles, and pedestrians by efficiently detecting road signs. This feature is designed to notify drivers about road signs whether he is missing the signs or not. This detecting and recognizing feature of the road signs' has improved a part of the advanced driver assistance system (ADAS). ADAS is an automated technology containing cameras and sensors intended to help the drivers with road signs, while traveling to a new road or having no knowledge about road signs. Before the work analysis, this topic has shown formidability as it has a real-time processing solution. This paper analyzed seven architectures for detecting the road signs: YOLO, YOLOv2, YOLOv3, PP-YOLO model and R-CNN, Fast R-CNN, Faster R-CNN. We have built a dataset based on Bangladesh's road sign named the "BD Road Sign 2021 (BDRS 2021)" dataset to evaluate the architectures. This dataset contains 16 categories (16 types of road-sign), and each has 168 images. Finally, we applied the seven advanced architectures to find the effective one to detect Bangladesh's road signs. This study implies that YOLOv3 and Faster R-CNN perform comparatively better for road sign detection.

show abstract

Section: Related Workmentioning

confidence: 99%

Road Sign Detection Using Variants of YOLO and R-CNN: An Analysis from the Perspective of Bangladesh

Lima

Kabir

Das

et al. 2021

Lecture Notes on Data Engineering and Communications Technologies

View full text Add to dashboard Cite

show abstract

“…Balado [7] proposed an algorithm to achieve a better detection rate, but still could not reach a real time processing frame rate. Research on traffic sign detection based on CNN proposed by Wang [8] produced a detection rate of 5 FPS which is far from the real time processing standard. A multi-scale cascaded R-CNN is proposed by Zhang [9] and Liu [10] to overcome the problem of false detection when traffic signs are in small sizes.…”

Section: Previous Workmentioning

confidence: 99%

“…Input from camera is resized using a bilinear interpolation algorithm which performs linear interpolation algorithm twice in different directions. This method uses four nearest point to calculate the point in the center of four points chosen [20,8]. Resizing is used to reduce the number of iteration when performing convolution in a frame.…”

Section: Figure 1 the Proposed Av System Diagrammentioning

confidence: 99%

Traffic sign detection optimization using color and shape segmentation as pre-processing system

Handoko¹,

Pratama²,

Yohanes³

2021

TELKOMNIKA

View full text Add to dashboard Cite

One of performance indicators in an autonomous vehicle (AV) is its ability to accommodate rapid environment changing; and performance of traffic sign detection (TSD) system is one of them. A low frame rate of TSD impacts to late decision making and may cause to a fatal accident. Meanwhile, adding any GPU to TSD will significantly increases its cost and make it unaffordable. This paper proposed a pre-processing system for TSD which implement a color and a shape segmentation to increase the system speed. These segmentation systems filter input frames such that the number of frames sent to artificial intelligence (AI) system is reduced. As a result, workload of AI system is decreased and its frame rate increases. HSV threshold is used in color segmentation to filter frames with no desired color. This algorithm ignores the saturation when performing color detection. Further, an edge detection feature is employed in shape segmentation to count the total contours of an object. Using German traffic sign recognition benchmark dataset as model, the pre-processing system filters 97% of frames with no traffic sign objects and has an accuracy of 88%. TSD system proposed allows a frame rate improvement up to 32 frame per second (FPS) when You Only Look Once (YOLO) algorithm is used. This is an open access article under the CC BY-SA license.

show abstract

“…Neural networks are being used more frequently to detect targets as deep learning technology advances; examples of these algorithms include Faster R-CNN [ 6 ], SSD [ 7 ], and YOLO [ 8 ], etc., which are primarily separated into single-stage and two-stage detection approaches. A previous study [ 9 ] presented an enhanced detection network based on YOLOv1 to address the issues of low accuracy and slow detection speed of standard traffic sign detection methods. This network enhanced traffic sign detection speed and lowered the hardware requirements of the detection system.…”

Section: Introductionmentioning

confidence: 99%

Traffic Sign Recognition Based on the YOLOv3 Algorithm

Gong

Song

et al. 2022

Sensors

View full text Add to dashboard Cite

Traffic sign detection is an essential component of an intelligent transportation system, since it provides critical road traffic data for vehicle decision-making and control. To solve the challenges of small traffic signs, inconspicuous characteristics, and low detection accuracy, a traffic sign recognition method based on improved (You Only Look Once v3) YOLOv3 is proposed. The spatial pyramid pooling structure is fused into the YOLOv3 network structure to achieve the fusion of local features and global features, and the fourth feature prediction scale of 152 × 152 size is introduced to make full use of the shallow features in the network to predict small targets. Furthermore, the bounding box regression is more stable when the distance-IoU (DIoU) loss is used, which takes into account the distance between the target and anchor, the overlap rate, and the scale. The Tsinghua–Tencent 100K (TT100K) traffic sign dataset’s 12 anchors are recalculated using the K-means clustering algorithm, while the dataset is balanced and expanded to address the problem of an uneven number of target classes in the TT100K dataset. The algorithm is compared to YOLOv3 and other commonly used target detection algorithms, and the results show that the improved YOLOv3 algorithm achieves a mean average precision (mAP) of 77.3%, which is 8.4% higher than YOLOv3, especially in small target detection, where the mAP is improved by 10.5%, greatly improving the accuracy of the detection network while keeping the real-time performance as high as possible. The detection network’s accuracy is substantially enhanced while keeping the network’s real-time performance as high as possible.

show abstract

Research on Traffic Sign Detection Based on Convolutional Neural Network

Cited by 8 publications

References 8 publications

Road Sign Detection Using Variants of YOLO and R-CNN: An Analysis from the Perspective of Bangladesh

Road Sign Detection Using Variants of YOLO and R-CNN: An Analysis from the Perspective of Bangladesh

Traffic sign detection optimization using color and shape segmentation as pre-processing system

Traffic Sign Recognition Based on the YOLOv3 Algorithm

Contact Info

Product

Resources

About