Automatic Recognition of Traffic Signs Based on Visual Inspection
The automatic recognition of traffic signs is essential to autonomous driving, assisted driving, and driving safety. Currently, convolutional neural network (CNN) is the most popular deep learning algorithm in traffic sign recognition. However, the CNN cannot capture the poses, perspectives, and dir...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9353477/ |
| _version_ | 1828908265281421312 |
|---|---|
| author | Shouhui He Lei Chen Shaoyun Zhang Zhuangxian Guo Pengjie Sun Hong Liu Hongda Liu |
| author_facet | Shouhui He Lei Chen Shaoyun Zhang Zhuangxian Guo Pengjie Sun Hong Liu Hongda Liu |
| author_sort | Shouhui He |
| collection | DOAJ |
| description | The automatic recognition of traffic signs is essential to autonomous driving, assisted driving, and driving safety. Currently, convolutional neural network (CNN) is the most popular deep learning algorithm in traffic sign recognition. However, the CNN cannot capture the poses, perspectives, and directions of the image, nor accurately recognize traffic signs from different perspectives. To solve the problem, the authors presented an automatic recognition algorithm for traffic signs based on visual inspection. For the accuracy of visual inspection, a region of interest (ROI) extraction method was designed through content analysis and key information recognition. Besides, a Histogram of Oriented Gradients (HOG) method was developed for image detection to prevent projection distortion. Furthermore, a traffic sign recognition learning architecture was created based on CapsNet, which relies on neurons to represent target parameters like dynamic routing, path pose and direction, and effectively capture the traffic sign information from different angles or directions. Finally, our model was compared with several baseline methods through experiments on LISA (Laboratory for Intelligent and Safe Automobiles) traffic sign dataset. The model performance was measured by mean average precision (MAP), time, memory, floating point operations per second (FLOPS), and parameter number. The results show that our model consumed shorter time yet better recognition performance than baseline methods, including CNN, support vector machine (SVM), and region-based fully convolutional network (R-FCN) ResNet 101. |
| first_indexed | 2024-12-13T18:07:25Z |
| format | Article |
| id | doaj.art-37134150a1834f57817371a5d7483e34 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-13T18:07:25Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-37134150a1834f57817371a5d7483e342022-12-21T23:36:02ZengIEEEIEEE Access2169-35362021-01-019432534326110.1109/ACCESS.2021.30590529353477Automatic Recognition of Traffic Signs Based on Visual InspectionShouhui He0https://orcid.org/0000-0003-4284-7915Lei Chen1https://orcid.org/0000-0002-3954-3470Shaoyun Zhang2https://orcid.org/0000-0001-6515-1932Zhuangxian Guo3https://orcid.org/0000-0002-0810-2429Pengjie Sun4https://orcid.org/0000-0002-7120-7469Hong Liu5https://orcid.org/0000-0002-5655-4024Hongda Liu6https://orcid.org/0000-0001-6529-2831Linyi University, Linyi, ChinaLinyi University, Linyi, ChinaLinyi University, Linyi, ChinaLinyi University, Linyi, ChinaLinyi University, Linyi, ChinaLinyi University, Linyi, ChinaLinyi Audit Bureau, Linyi, ChinaThe automatic recognition of traffic signs is essential to autonomous driving, assisted driving, and driving safety. Currently, convolutional neural network (CNN) is the most popular deep learning algorithm in traffic sign recognition. However, the CNN cannot capture the poses, perspectives, and directions of the image, nor accurately recognize traffic signs from different perspectives. To solve the problem, the authors presented an automatic recognition algorithm for traffic signs based on visual inspection. For the accuracy of visual inspection, a region of interest (ROI) extraction method was designed through content analysis and key information recognition. Besides, a Histogram of Oriented Gradients (HOG) method was developed for image detection to prevent projection distortion. Furthermore, a traffic sign recognition learning architecture was created based on CapsNet, which relies on neurons to represent target parameters like dynamic routing, path pose and direction, and effectively capture the traffic sign information from different angles or directions. Finally, our model was compared with several baseline methods through experiments on LISA (Laboratory for Intelligent and Safe Automobiles) traffic sign dataset. The model performance was measured by mean average precision (MAP), time, memory, floating point operations per second (FLOPS), and parameter number. The results show that our model consumed shorter time yet better recognition performance than baseline methods, including CNN, support vector machine (SVM), and region-based fully convolutional network (R-FCN) ResNet 101.https://ieeexplore.ieee.org/document/9353477/Traffic signsautomatic recognition systemCapsNettraffic safety |
| spellingShingle | Shouhui He Lei Chen Shaoyun Zhang Zhuangxian Guo Pengjie Sun Hong Liu Hongda Liu Automatic Recognition of Traffic Signs Based on Visual Inspection IEEE Access Traffic signs automatic recognition system CapsNet traffic safety |
| title | Automatic Recognition of Traffic Signs Based on Visual Inspection |
| title_full | Automatic Recognition of Traffic Signs Based on Visual Inspection |
| title_fullStr | Automatic Recognition of Traffic Signs Based on Visual Inspection |
| title_full_unstemmed | Automatic Recognition of Traffic Signs Based on Visual Inspection |
| title_short | Automatic Recognition of Traffic Signs Based on Visual Inspection |
| title_sort | automatic recognition of traffic signs based on visual inspection |
| topic | Traffic signs automatic recognition system CapsNet traffic safety |
| url | https://ieeexplore.ieee.org/document/9353477/ |
| work_keys_str_mv | AT shouhuihe automaticrecognitionoftrafficsignsbasedonvisualinspection AT leichen automaticrecognitionoftrafficsignsbasedonvisualinspection AT shaoyunzhang automaticrecognitionoftrafficsignsbasedonvisualinspection AT zhuangxianguo automaticrecognitionoftrafficsignsbasedonvisualinspection AT pengjiesun automaticrecognitionoftrafficsignsbasedonvisualinspection AT hongliu automaticrecognitionoftrafficsignsbasedonvisualinspection AT hongdaliu automaticrecognitionoftrafficsignsbasedonvisualinspection |