Automated Vehicle Counting from Pre-Recorded Video Using You Only Look Once (YOLO) Object Detection Model
Different techniques are being applied for automated vehicle counting from video footage, which is a significant subject of interest to many researchers. In this context, the You Only Look Once (YOLO) object detection model, which has been developed recently, has emerged as a promising tool. In term...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/9/7/131 |
| _version_ | 1827732773895405568 |
|---|---|
| author | Mishuk Majumder Chester Wilmot |
| author_facet | Mishuk Majumder Chester Wilmot |
| author_sort | Mishuk Majumder |
| collection | DOAJ |
| description | Different techniques are being applied for automated vehicle counting from video footage, which is a significant subject of interest to many researchers. In this context, the You Only Look Once (YOLO) object detection model, which has been developed recently, has emerged as a promising tool. In terms of accuracy and flexible interval counting, the adequacy of existing research on employing the model for vehicle counting from video footage is unlikely sufficient. The present study endeavors to develop computer algorithms for automated traffic counting from pre-recorded videos using the YOLO model with flexible interval counting. The study involves the development of algorithms aimed at detecting, tracking, and counting vehicles from pre-recorded videos. The YOLO model was applied in TensorFlow API with the assistance of OpenCV. The developed algorithms implement the YOLO model for counting vehicles in two-way directions in an efficient way. The accuracy of the automated counting was evaluated compared to the manual counts, and was found to be about 90 percent. The accuracy comparison also shows that the error of automated counting consistently occurs due to undercounting from unsuitable videos. In addition, a benefit–cost (B/C) analysis shows that implementing the automated counting method returns 1.76 times the investment. |
| first_indexed | 2024-03-11T00:56:48Z |
| format | Article |
| id | doaj.art-7bee6584846e407eadeddbd7320e6d0a |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-03-11T00:56:48Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-7bee6584846e407eadeddbd7320e6d0a2023-11-18T19:56:56ZengMDPI AGJournal of Imaging2313-433X2023-06-019713110.3390/jimaging9070131Automated Vehicle Counting from Pre-Recorded Video Using You Only Look Once (YOLO) Object Detection ModelMishuk Majumder0Chester Wilmot1Department of Civil & Environmental Engineering, Louisiana State University, Baton Rouge, LA 70803, USADepartment of Civil & Environmental Engineering, Louisiana State University, Baton Rouge, LA 70803, USADifferent techniques are being applied for automated vehicle counting from video footage, which is a significant subject of interest to many researchers. In this context, the You Only Look Once (YOLO) object detection model, which has been developed recently, has emerged as a promising tool. In terms of accuracy and flexible interval counting, the adequacy of existing research on employing the model for vehicle counting from video footage is unlikely sufficient. The present study endeavors to develop computer algorithms for automated traffic counting from pre-recorded videos using the YOLO model with flexible interval counting. The study involves the development of algorithms aimed at detecting, tracking, and counting vehicles from pre-recorded videos. The YOLO model was applied in TensorFlow API with the assistance of OpenCV. The developed algorithms implement the YOLO model for counting vehicles in two-way directions in an efficient way. The accuracy of the automated counting was evaluated compared to the manual counts, and was found to be about 90 percent. The accuracy comparison also shows that the error of automated counting consistently occurs due to undercounting from unsuitable videos. In addition, a benefit–cost (B/C) analysis shows that implementing the automated counting method returns 1.76 times the investment.https://www.mdpi.com/2313-433X/9/7/131automated vehicle countingYou Only Look Once (YOLO)object detectionTensorFlowOpenCVpre-recorded video |
| spellingShingle | Mishuk Majumder Chester Wilmot Automated Vehicle Counting from Pre-Recorded Video Using You Only Look Once (YOLO) Object Detection Model Journal of Imaging automated vehicle counting You Only Look Once (YOLO) object detection TensorFlow OpenCV pre-recorded video |
| title | Automated Vehicle Counting from Pre-Recorded Video Using You Only Look Once (YOLO) Object Detection Model |
| title_full | Automated Vehicle Counting from Pre-Recorded Video Using You Only Look Once (YOLO) Object Detection Model |
| title_fullStr | Automated Vehicle Counting from Pre-Recorded Video Using You Only Look Once (YOLO) Object Detection Model |
| title_full_unstemmed | Automated Vehicle Counting from Pre-Recorded Video Using You Only Look Once (YOLO) Object Detection Model |
| title_short | Automated Vehicle Counting from Pre-Recorded Video Using You Only Look Once (YOLO) Object Detection Model |
| title_sort | automated vehicle counting from pre recorded video using you only look once yolo object detection model |
| topic | automated vehicle counting You Only Look Once (YOLO) object detection TensorFlow OpenCV pre-recorded video |
| url | https://www.mdpi.com/2313-433X/9/7/131 |
| work_keys_str_mv | AT mishukmajumder automatedvehiclecountingfromprerecordedvideousingyouonlylookonceyoloobjectdetectionmodel AT chesterwilmot automatedvehiclecountingfromprerecordedvideousingyouonlylookonceyoloobjectdetectionmodel |