URBAN TRAFFIC FLOW ANALYSIS BASED ON DEEP LEARNING CAR DETECTION FROM CCTV IMAGE SERIES
Traffic flow analysis is fundamental for urban planning and management of road traffic infrastructure. Automatic number plate recognition (ANPR) systems are conventional methods for vehicle detection and travel times estimation. However, such systems are specifically focused on car plates, providing...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2018-09-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-4/499/2018/isprs-archives-XLII-4-499-2018.pdf |
| _version_ | 1819091037113548800 |
|---|---|
| author | M. V. Peppa D. Bell T. Komar W. Xiao |
| author_facet | M. V. Peppa D. Bell T. Komar W. Xiao |
| author_sort | M. V. Peppa |
| collection | DOAJ |
| description | Traffic flow analysis is fundamental for urban planning and management of road traffic infrastructure. Automatic number plate recognition (ANPR) systems are conventional methods for vehicle detection and travel times estimation. However, such systems are specifically focused on car plates, providing a limited extent of road users. The advance of open-source deep learning convolutional neural networks (CNN) in combination with freely-available closed-circuit television (CCTV) datasets have offered the opportunities for detection and classification of various road users. The research, presented here, aims to analyse traffic flow patterns through fine-tuning pre-trained CNN models on domain-specific low quality imagery, as captured in various weather conditions and seasons of the year 2018. Such imagery is collected from the North East Combined Authority (NECA) Travel and Transport Data, Newcastle upon Tyne, UK. Results show that the fine-tuned MobileNet model with 98.2 % precision, 58.5 % recall and 73.4 % harmonic mean could potentially be used for a real time traffic monitoring application with big data, due to its fast performance. Compared to MobileNet, the fine-tuned Faster region proposal R-CNN model, providing a better harmonic mean (80.4 %), recall (68.8 %) and more accurate estimations of car units, could be used for traffic analysis applications that demand higher accuracy than speed. This research ultimately exploits machine learning alogrithms for a wider understanding of traffic congestion and disruption under social events and extreme weather conditions. |
| first_indexed | 2024-12-21T22:33:21Z |
| format | Article |
| id | doaj.art-2b83801831ab478c84b0ac40319719ee |
| institution | Directory Open Access Journal |
| issn | 1682-1750 2194-9034 |
| language | English |
| last_indexed | 2024-12-21T22:33:21Z |
| publishDate | 2018-09-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-2b83801831ab478c84b0ac40319719ee2022-12-21T18:48:01ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342018-09-01XLII-449950610.5194/isprs-archives-XLII-4-499-2018URBAN TRAFFIC FLOW ANALYSIS BASED ON DEEP LEARNING CAR DETECTION FROM CCTV IMAGE SERIESM. V. Peppa0D. Bell1T. Komar2W. Xiao3School of Engineering, Newcastle University, Newcastle upon Tyne, UKSchool of Engineering, Newcastle University, Newcastle upon Tyne, UKSchool of Engineering, Newcastle University, Newcastle upon Tyne, UKSchool of Engineering, Newcastle University, Newcastle upon Tyne, UKTraffic flow analysis is fundamental for urban planning and management of road traffic infrastructure. Automatic number plate recognition (ANPR) systems are conventional methods for vehicle detection and travel times estimation. However, such systems are specifically focused on car plates, providing a limited extent of road users. The advance of open-source deep learning convolutional neural networks (CNN) in combination with freely-available closed-circuit television (CCTV) datasets have offered the opportunities for detection and classification of various road users. The research, presented here, aims to analyse traffic flow patterns through fine-tuning pre-trained CNN models on domain-specific low quality imagery, as captured in various weather conditions and seasons of the year 2018. Such imagery is collected from the North East Combined Authority (NECA) Travel and Transport Data, Newcastle upon Tyne, UK. Results show that the fine-tuned MobileNet model with 98.2 % precision, 58.5 % recall and 73.4 % harmonic mean could potentially be used for a real time traffic monitoring application with big data, due to its fast performance. Compared to MobileNet, the fine-tuned Faster region proposal R-CNN model, providing a better harmonic mean (80.4 %), recall (68.8 %) and more accurate estimations of car units, could be used for traffic analysis applications that demand higher accuracy than speed. This research ultimately exploits machine learning alogrithms for a wider understanding of traffic congestion and disruption under social events and extreme weather conditions.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-4/499/2018/isprs-archives-XLII-4-499-2018.pdf |
| spellingShingle | M. V. Peppa D. Bell T. Komar W. Xiao URBAN TRAFFIC FLOW ANALYSIS BASED ON DEEP LEARNING CAR DETECTION FROM CCTV IMAGE SERIES The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | URBAN TRAFFIC FLOW ANALYSIS BASED ON DEEP LEARNING CAR DETECTION FROM CCTV IMAGE SERIES |
| title_full | URBAN TRAFFIC FLOW ANALYSIS BASED ON DEEP LEARNING CAR DETECTION FROM CCTV IMAGE SERIES |
| title_fullStr | URBAN TRAFFIC FLOW ANALYSIS BASED ON DEEP LEARNING CAR DETECTION FROM CCTV IMAGE SERIES |
| title_full_unstemmed | URBAN TRAFFIC FLOW ANALYSIS BASED ON DEEP LEARNING CAR DETECTION FROM CCTV IMAGE SERIES |
| title_short | URBAN TRAFFIC FLOW ANALYSIS BASED ON DEEP LEARNING CAR DETECTION FROM CCTV IMAGE SERIES |
| title_sort | urban traffic flow analysis based on deep learning car detection from cctv image series |
| url | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-4/499/2018/isprs-archives-XLII-4-499-2018.pdf |
| work_keys_str_mv | AT mvpeppa urbantrafficflowanalysisbasedondeeplearningcardetectionfromcctvimageseries AT dbell urbantrafficflowanalysisbasedondeeplearningcardetectionfromcctvimageseries AT tkomar urbantrafficflowanalysisbasedondeeplearningcardetectionfromcctvimageseries AT wxiao urbantrafficflowanalysisbasedondeeplearningcardetectionfromcctvimageseries |