Data-Augmented Deep Learning Models for Abnormal Road Manhole Cover Detection
Anomalous road manhole covers pose a potential risk to road safety in cities. In the development of smart cities, computer vision techniques use deep learning to automatically detect anomalous manhole covers to avoid these risks. One important problem is that a large amount of data are required to t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/5/2676 |
| _version_ | 1797614264277532672 |
|---|---|
| author | Dongping Zhang Xuecheng Yu Li Yang Daying Quan Hongmei Mi Ke Yan |
| author_facet | Dongping Zhang Xuecheng Yu Li Yang Daying Quan Hongmei Mi Ke Yan |
| author_sort | Dongping Zhang |
| collection | DOAJ |
| description | Anomalous road manhole covers pose a potential risk to road safety in cities. In the development of smart cities, computer vision techniques use deep learning to automatically detect anomalous manhole covers to avoid these risks. One important problem is that a large amount of data are required to train a road anomaly manhole cover detection model. The number of anomalous manhole covers is usually small, which makes it a challenge to create training datasets quickly. To expand the dataset and improve the generalization of the model, researchers usually copy and paste samples from the original data to other data in order to achieve data augmentation. In this paper, we propose a new data augmentation method, which uses data that do not exist in the original dataset as samples to automatically select the pasting position of manhole cover samples and predict the transformation parameters via visual prior experience and perspective transformations, making it more accurately capture the actual shape of manhole covers on a road. Without using other data enhancement processes, our method raises the mean average precision (mAP) by at least 6.8 compared with the baseline model. |
| first_indexed | 2024-03-11T07:10:08Z |
| format | Article |
| id | doaj.art-1466516890e54334b57211f13c2fa2fd |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T07:10:08Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-1466516890e54334b57211f13c2fa2fd2023-11-17T08:38:09ZengMDPI AGSensors1424-82202023-03-01235267610.3390/s23052676Data-Augmented Deep Learning Models for Abnormal Road Manhole Cover DetectionDongping Zhang0Xuecheng Yu1Li Yang2Daying Quan3Hongmei Mi4Ke Yan5Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, China Jiliang University, Hangzhou 310018, ChinaKey Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, China Jiliang University, Hangzhou 310018, ChinaKey Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, China Jiliang University, Hangzhou 310018, ChinaKey Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, China Jiliang University, Hangzhou 310018, ChinaKey Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, China Jiliang University, Hangzhou 310018, ChinaDepartment of Building, School of Design and Environment, National University of Singapore, Singapore 119077, SingaporeAnomalous road manhole covers pose a potential risk to road safety in cities. In the development of smart cities, computer vision techniques use deep learning to automatically detect anomalous manhole covers to avoid these risks. One important problem is that a large amount of data are required to train a road anomaly manhole cover detection model. The number of anomalous manhole covers is usually small, which makes it a challenge to create training datasets quickly. To expand the dataset and improve the generalization of the model, researchers usually copy and paste samples from the original data to other data in order to achieve data augmentation. In this paper, we propose a new data augmentation method, which uses data that do not exist in the original dataset as samples to automatically select the pasting position of manhole cover samples and predict the transformation parameters via visual prior experience and perspective transformations, making it more accurately capture the actual shape of manhole covers on a road. Without using other data enhancement processes, our method raises the mean average precision (mAP) by at least 6.8 compared with the baseline model.https://www.mdpi.com/1424-8220/23/5/2676data augmentationobject detectionroad manhole coverdeep learningconvolutional neural network |
| spellingShingle | Dongping Zhang Xuecheng Yu Li Yang Daying Quan Hongmei Mi Ke Yan Data-Augmented Deep Learning Models for Abnormal Road Manhole Cover Detection Sensors data augmentation object detection road manhole cover deep learning convolutional neural network |
| title | Data-Augmented Deep Learning Models for Abnormal Road Manhole Cover Detection |
| title_full | Data-Augmented Deep Learning Models for Abnormal Road Manhole Cover Detection |
| title_fullStr | Data-Augmented Deep Learning Models for Abnormal Road Manhole Cover Detection |
| title_full_unstemmed | Data-Augmented Deep Learning Models for Abnormal Road Manhole Cover Detection |
| title_short | Data-Augmented Deep Learning Models for Abnormal Road Manhole Cover Detection |
| title_sort | data augmented deep learning models for abnormal road manhole cover detection |
| topic | data augmentation object detection road manhole cover deep learning convolutional neural network |
| url | https://www.mdpi.com/1424-8220/23/5/2676 |
| work_keys_str_mv | AT dongpingzhang dataaugmenteddeeplearningmodelsforabnormalroadmanholecoverdetection AT xuechengyu dataaugmenteddeeplearningmodelsforabnormalroadmanholecoverdetection AT liyang dataaugmenteddeeplearningmodelsforabnormalroadmanholecoverdetection AT dayingquan dataaugmenteddeeplearningmodelsforabnormalroadmanholecoverdetection AT hongmeimi dataaugmenteddeeplearningmodelsforabnormalroadmanholecoverdetection AT keyan dataaugmenteddeeplearningmodelsforabnormalroadmanholecoverdetection |