A Novel Neural Network Model for Traffic Sign Detection and Recognition under Extreme Conditions

Abstract

Traffic sign detection is extremely important in autonomous driving and transportation safety systems. However, the accurate detection of traffic signs remains challenging, especially under extreme conditions. This paper proposes a novel model called Traffic Sign Yolo (TS-Yolo) based on the convolutional neural network to improve the detection and recognition accuracy of traffic signs, especially under low visibility and extremely restricted vision conditions. A copy-and-paste data augmentation method was used to build a large number of new samples based on existing traffic-sign datasets. Based on You Only Look Once (YoloV5), the mixed depth-wise convolution (MixConv) was employed to mix different kernel sizes in a single convolution operation, so that different patterns with various resolutions can be captured. Furthermore, the attentional feature fusion (AFF) module was integrated to fuse the features based on attention from same-layer to cross-layer scenarios, including short and long skip connections, and even performing the initial fusion with itself. The experimental results demonstrated that, using the YoloV5 dataset with augmentation, the precision was 71.92, which was increased by 34.56 compared with the data without augmentation, and the mean average precision mAP_0.5 was 80.05, which was increased by 33.11 compared with the data without augmentation. When MixConv and AFF were applied to the TS-Yolo model, the precision was 74.53 and 2.61 higher than that with data augmentation only, and the value of mAP_0.5 was 83.73 and 3.68 higher than that based on the YoloV5 dataset with augmentation only. Overall, the performance of the proposed method was competitive with the latest traffic sign detection approaches.

Recognition of terminal buds of densely-planted Chinese fir seedlings using improved YOLOv5 by integrating attention mechanism

“…In addition, due to the typical occlusion and overlapping of terminal buds of densely-planted Chinese fir seedlings and the differences in individual growth states, the generalization of the network trained using the original image data is poor. However, data augmentation can improve the diversity of target features and solve the problem of unbalanced or missing sample data ( Wan et al., 2021 ), enhancing the robustness and generalization of the trained model to a certain extent. Finally, this study introduces the TTA multi-scale test and WBF fusion algorithm in the inference and prediction stage.…”

Visual Recognition of Traffic Signs in Natural Scenes Based on Improved RetinaNet

“…Many researchers have attempted to increase the accuracy of traffic sign recognition using a variety of methods [ 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 , 21 ]. In general, there are three categories of traffic signs in China: indication, warning and prohibition, which are represented by blue, yellow and red, respectively.…”

A Real-Time Zanthoxylum Target Detection Method for an Intelligent Picking Robot under a Complex Background, Based on an Improved YOLOv5s Architecture

“…In the industrial field, Danyang Zhang et al [6] proposed a multiobject detection method based on deep convolution combined with relevant ideas of neural networks, which can realize nondestructive detection of rail surfaces and fastener defects. Haifeng Wang et al [7] proposed a traffic sign YOLO (TS-YOLO) model based on a convolutional neural network to improve the detection and recognition accuracy of traffic signs under conditions of extremely limited vision. Gang Tang et al [8] proposed an excellent ship detection method named "N-YOLO", which was based on YOLO, including a noise level classifier (NLC), SAR target potential area extraction module (STPAE) and detection module based on YOLOv5.…”