A Novel Memory and Time-Efficient ALPR System Based on YOLOv5
With the rapid development of deep learning techniques, new innovative license plate recognition systems have gained considerable attention from researchers all over the world. These systems have numerous applications, such as law enforcement, parking lot management, toll terminals, traffic regulati...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/14/5283 |
| _version_ | 1797415997852876800 |
|---|---|
| author | Piyush Batra Imran Hussain Mohd Abdul Ahad Gabriella Casalino Mohammad Afshar Alam Aqeel Khalique Syed Imtiyaz Hassan |
| author_facet | Piyush Batra Imran Hussain Mohd Abdul Ahad Gabriella Casalino Mohammad Afshar Alam Aqeel Khalique Syed Imtiyaz Hassan |
| author_sort | Piyush Batra |
| collection | DOAJ |
| description | With the rapid development of deep learning techniques, new innovative license plate recognition systems have gained considerable attention from researchers all over the world. These systems have numerous applications, such as law enforcement, parking lot management, toll terminals, traffic regulation, etc. At present, most of these systems rely heavily on high-end computing resources. This paper proposes a novel memory and time-efficient automatic license plate recognition (ALPR) system developed using YOLOv5. This approach is ideal for IoT devices that usually have less memory and processing power. Our approach incorporates two stages, i.e., using a custom transfer learned model for license plate detection and an LSTM-based OCR engine for recognition. The dataset that we used for this research was our dataset consisting of images from the Google open images dataset and the Indian License plate dataset. Along with training YOLOv5 models, we also trained YOLOv4 models on the same dataset to illustrate the size and performance-wise comparison. Our proposed ALPR system results in a 14 megabytes model with a mean average precision of 87.2% and 4.8 ms testing time on still images using Nvidia T4 GPU. The complete system with detection and recognition on the other hand takes about 85 milliseconds. |
| first_indexed | 2024-03-09T05:57:32Z |
| format | Article |
| id | doaj.art-b711aa4c9af64c84bc89cb3cd0d5a38c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T05:57:32Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b711aa4c9af64c84bc89cb3cd0d5a38c2023-12-03T12:12:58ZengMDPI AGSensors1424-82202022-07-012214528310.3390/s22145283A Novel Memory and Time-Efficient ALPR System Based on YOLOv5Piyush Batra0Imran Hussain1Mohd Abdul Ahad2Gabriella Casalino3Mohammad Afshar Alam4Aqeel Khalique5Syed Imtiyaz Hassan6Department of Computer Science and Engineering, Jamia Hamdard, New Delhi 110062, IndiaDepartment of Computer Science and Engineering, Jamia Hamdard, New Delhi 110062, IndiaDepartment of Computer Science and Engineering, Jamia Hamdard, New Delhi 110062, IndiaDepartment of Computer Science, University of Bari, 70125 Bari, ItalyDepartment of Computer Science and Engineering, Jamia Hamdard, New Delhi 110062, IndiaDepartment of Computer Science and Engineering, Jamia Hamdard, New Delhi 110062, IndiaDepartment of CS and IT, Maulana Azad National Urdu University, Hyderabad 500032, IndiaWith the rapid development of deep learning techniques, new innovative license plate recognition systems have gained considerable attention from researchers all over the world. These systems have numerous applications, such as law enforcement, parking lot management, toll terminals, traffic regulation, etc. At present, most of these systems rely heavily on high-end computing resources. This paper proposes a novel memory and time-efficient automatic license plate recognition (ALPR) system developed using YOLOv5. This approach is ideal for IoT devices that usually have less memory and processing power. Our approach incorporates two stages, i.e., using a custom transfer learned model for license plate detection and an LSTM-based OCR engine for recognition. The dataset that we used for this research was our dataset consisting of images from the Google open images dataset and the Indian License plate dataset. Along with training YOLOv5 models, we also trained YOLOv4 models on the same dataset to illustrate the size and performance-wise comparison. Our proposed ALPR system results in a 14 megabytes model with a mean average precision of 87.2% and 4.8 ms testing time on still images using Nvidia T4 GPU. The complete system with detection and recognition on the other hand takes about 85 milliseconds.https://www.mdpi.com/1424-8220/22/14/5283ALPRYOLOv5IoTOCRvehicle license plate detection and recognitionurban mobility |
| spellingShingle | Piyush Batra Imran Hussain Mohd Abdul Ahad Gabriella Casalino Mohammad Afshar Alam Aqeel Khalique Syed Imtiyaz Hassan A Novel Memory and Time-Efficient ALPR System Based on YOLOv5 Sensors ALPR YOLOv5 IoT OCR vehicle license plate detection and recognition urban mobility |
| title | A Novel Memory and Time-Efficient ALPR System Based on YOLOv5 |
| title_full | A Novel Memory and Time-Efficient ALPR System Based on YOLOv5 |
| title_fullStr | A Novel Memory and Time-Efficient ALPR System Based on YOLOv5 |
| title_full_unstemmed | A Novel Memory and Time-Efficient ALPR System Based on YOLOv5 |
| title_short | A Novel Memory and Time-Efficient ALPR System Based on YOLOv5 |
| title_sort | novel memory and time efficient alpr system based on yolov5 |
| topic | ALPR YOLOv5 IoT OCR vehicle license plate detection and recognition urban mobility |
| url | https://www.mdpi.com/1424-8220/22/14/5283 |
| work_keys_str_mv | AT piyushbatra anovelmemoryandtimeefficientalprsystembasedonyolov5 AT imranhussain anovelmemoryandtimeefficientalprsystembasedonyolov5 AT mohdabdulahad anovelmemoryandtimeefficientalprsystembasedonyolov5 AT gabriellacasalino anovelmemoryandtimeefficientalprsystembasedonyolov5 AT mohammadafsharalam anovelmemoryandtimeefficientalprsystembasedonyolov5 AT aqeelkhalique anovelmemoryandtimeefficientalprsystembasedonyolov5 AT syedimtiyazhassan anovelmemoryandtimeefficientalprsystembasedonyolov5 AT piyushbatra novelmemoryandtimeefficientalprsystembasedonyolov5 AT imranhussain novelmemoryandtimeefficientalprsystembasedonyolov5 AT mohdabdulahad novelmemoryandtimeefficientalprsystembasedonyolov5 AT gabriellacasalino novelmemoryandtimeefficientalprsystembasedonyolov5 AT mohammadafsharalam novelmemoryandtimeefficientalprsystembasedonyolov5 AT aqeelkhalique novelmemoryandtimeefficientalprsystembasedonyolov5 AT syedimtiyazhassan novelmemoryandtimeefficientalprsystembasedonyolov5 |