Image-Based Learning to Measure the Space Mean Speed on a Stretch of Road without the Need to Tag Images with Labels
Space mean speed cannot be directly measured in the field, although it is a basic parameter that is used to evaluate traffic conditions. An end-to-end convolutional neural network (CNN) was adopted to measure the space mean speed based solely on two consecutive road images. However, tagging images w...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/19/5/1227 |
| _version_ | 1798005563932540928 |
|---|---|
| author | Jincheol Lee Seungbin Roh Johyun Shin Keemin Sohn |
| author_facet | Jincheol Lee Seungbin Roh Johyun Shin Keemin Sohn |
| author_sort | Jincheol Lee |
| collection | DOAJ |
| description | Space mean speed cannot be directly measured in the field, although it is a basic parameter that is used to evaluate traffic conditions. An end-to-end convolutional neural network (CNN) was adopted to measure the space mean speed based solely on two consecutive road images. However, tagging images with labels (=true space mean speeds) by manually positioning and tracking every vehicle on road images is a formidable task. The present study was focused on naïve animation images provided by a traffic simulator, because these contain perfect information concerning vehicle movement to attain labels. The animation images, however, seem far-removed from actual photos taken in the field. A cycle-consistent adversarial network (CycleGAN) bridged the reality gap by mapping the animation images into seemingly realistic images that could not be distinguished from real photos. A CNN model trained on the synthesized images was tested on real photos that had been manually labeled. The test performance was comparable to those of state-of-the-art motion-capture technologies. The proposed method showed that deep-learning models to measure the space mean speed could be trained without the need for time-consuming manual annotation. |
| first_indexed | 2024-04-11T12:42:16Z |
| format | Article |
| id | doaj.art-a159e765096e4681ba354c0bdfd51346 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T12:42:16Z |
| publishDate | 2019-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a159e765096e4681ba354c0bdfd513462022-12-22T04:23:28ZengMDPI AGSensors1424-82202019-03-01195122710.3390/s19051227s19051227Image-Based Learning to Measure the Space Mean Speed on a Stretch of Road without the Need to Tag Images with LabelsJincheol Lee0Seungbin Roh1Johyun Shin2Keemin Sohn3Department of Urban Engineering, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul 156-756, KoreaDepartment of Urban Engineering, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul 156-756, KoreaDepartment of Urban Engineering, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul 156-756, KoreaDepartment of Urban Engineering, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul 156-756, KoreaSpace mean speed cannot be directly measured in the field, although it is a basic parameter that is used to evaluate traffic conditions. An end-to-end convolutional neural network (CNN) was adopted to measure the space mean speed based solely on two consecutive road images. However, tagging images with labels (=true space mean speeds) by manually positioning and tracking every vehicle on road images is a formidable task. The present study was focused on naïve animation images provided by a traffic simulator, because these contain perfect information concerning vehicle movement to attain labels. The animation images, however, seem far-removed from actual photos taken in the field. A cycle-consistent adversarial network (CycleGAN) bridged the reality gap by mapping the animation images into seemingly realistic images that could not be distinguished from real photos. A CNN model trained on the synthesized images was tested on real photos that had been manually labeled. The test performance was comparable to those of state-of-the-art motion-capture technologies. The proposed method showed that deep-learning models to measure the space mean speed could be trained without the need for time-consuming manual annotation.http://www.mdpi.com/1424-8220/19/5/1227space mean speedconvolutional neural network (CNN)cycle-consistent adversarial network (CycleGAN)traffic surveillancetraffic prediction |
| spellingShingle | Jincheol Lee Seungbin Roh Johyun Shin Keemin Sohn Image-Based Learning to Measure the Space Mean Speed on a Stretch of Road without the Need to Tag Images with Labels Sensors space mean speed convolutional neural network (CNN) cycle-consistent adversarial network (CycleGAN) traffic surveillance traffic prediction |
| title | Image-Based Learning to Measure the Space Mean Speed on a Stretch of Road without the Need to Tag Images with Labels |
| title_full | Image-Based Learning to Measure the Space Mean Speed on a Stretch of Road without the Need to Tag Images with Labels |
| title_fullStr | Image-Based Learning to Measure the Space Mean Speed on a Stretch of Road without the Need to Tag Images with Labels |
| title_full_unstemmed | Image-Based Learning to Measure the Space Mean Speed on a Stretch of Road without the Need to Tag Images with Labels |
| title_short | Image-Based Learning to Measure the Space Mean Speed on a Stretch of Road without the Need to Tag Images with Labels |
| title_sort | image based learning to measure the space mean speed on a stretch of road without the need to tag images with labels |
| topic | space mean speed convolutional neural network (CNN) cycle-consistent adversarial network (CycleGAN) traffic surveillance traffic prediction |
| url | http://www.mdpi.com/1424-8220/19/5/1227 |
| work_keys_str_mv | AT jincheollee imagebasedlearningtomeasurethespacemeanspeedonastretchofroadwithouttheneedtotagimageswithlabels AT seungbinroh imagebasedlearningtomeasurethespacemeanspeedonastretchofroadwithouttheneedtotagimageswithlabels AT johyunshin imagebasedlearningtomeasurethespacemeanspeedonastretchofroadwithouttheneedtotagimageswithlabels AT keeminsohn imagebasedlearningtomeasurethespacemeanspeedonastretchofroadwithouttheneedtotagimageswithlabels |