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.
Aeolian sand is an important construction material in many desert regions. In order to study its engineering properties, samples were extracted from two sections within Yulin city, Shaanxi province of China. One set was collected from a site along the G210 highway that connects Yulin city and Inner Mongolia, and the other sampling site was along the provincial highway S204 that connects Yulin and Jingbian city. Sieve analyses using square mesh and round mesh sieves were conducted to determine the particle size distribution of the collected sand samples. In addition, scanning electron microscopy (SEM) and X-ray diffraction (XRD) were used to characterize the surface microstructure and mineral composition of the sand particles, respectively. Based on the sieve analyses results, the size distribution of the Aeolian sand particles in this region is mainly between 0.075 mm and 0.3 mm with low clay content (0.69–10.3%). Also, it was found that the square mesh is more effective than the round mesh for conducting sieve analysis of Aeolian sand, with the 0.15 mm sieve identified as the key sieve size. Using the percentage passing rates in the 0.15 mm square sieve as a classification index, the particle gradation of the sand particles was simplified into three classes: Class A (less than 30%), Class B (between 30% and 60%), and Class C (more than 60%). SEM observation revealed different profile configurations on the surfaces of the Aeolian sand particles including intensive pitting, corrosion marks, and cracks, while the XRD results indicated the presence of quartz and feldspar in more than 95% of the entire mineral composition of the sand particles. Minerals that are deleterious to cement and mortar used in road construction were present in negligible amounts. From the particle size characterization, it is possible to use Aeolian sand as a subgrade material in road construction due its lower clay content. Also, the negligible amount of minerals such as calcite and chlorite in the Aeolian sand mineral composition indicates its potential for use in cement and mortar without causing any complex chemical reactions. The findings of this study indicate the possibility of utilizing the Aeolian sand deposits in Yulin area as a road construction material and also provide a theoretical guide to encourage its widespread application in this regard.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.