Details
| Original language | English |
|---|---|
| Title of host publication | XXIV ISPRS Congress (2022 edition) |
| Pages | 287-293 |
| Number of pages | 7 |
| Publication status | Published - 1 Jun 2022 |
| Event | 2022 24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow, Commission IV - Nice, France Duration: 6 Jun 2022 → 11 Jun 2022 |
Publication series
| Name | International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives |
|---|---|
| Publisher | International Society for Photogrammetry and Remote Sensing |
| Number | B4-2022 |
| Volume | 43 |
| ISSN (Print) | 1682-1750 |
Abstract
Traffic regulators at intersections act as an essential factor that influences traffic flow and, subsequently, the route choices of commuters. A digital map that provides up-to-date traffic control information is beneficial not only for facilitating the commuters' trips, but also for energy-saving and environmental protection. In this paper, instead of using expensive surveying methods, we propose an automatic way based on a Conditional Variational Autoencoder (CVAE) to recognize traffic regulators, i. e., arm rules at intersections, by leveraging the GPS data collected from vehicles and the satellite imagery retrieved from digital maps, i. e., Google Maps. We apply a Long Short-Term Memory to extract the motion dynamics over a GPS sequence traversed through the intersection. Simultaneously, we build a Convolutional Neural Network (CNN) to extract the grid-based local imagery information associated with each step of the GPS positions. Moreover, a self-attention mechanism is adopted to extract the spatial and temporal features over both the GPS and grid sequences. The extracted temporal and spatial features are then combined for detecting the traffic arm rules. To analyze the performance of our method, we tested it on a GPS dataset collected by driving vehicles in Hannover, a medium-sized German city. Compared to a Random Forest model and an Encoder-Decoder model, our proposed model achieved better results with both accuracy and F1-score of 0.90 for the three-class (arm rules of uncontrolled, traffic light, and priority sign) task. We also carried out ablation studies to further investigate the effectiveness of the GPS input branch, the image input branch, and the self-attention mechanism in our model.
Keywords
- Attention Mechanism, Classification, Deep Learning, Generative Model, Traffic Regulation
ASJC Scopus subject areas
- Computer Science(all)
- Information Systems
- Social Sciences(all)
- Geography, Planning and Development
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
XXIV ISPRS Congress (2022 edition). 2022. p. 287-293 (International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives; Vol. 43, No. B4-2022).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Traffic Control Recognition with an Attention Mechanism Using Speed-Profile and Satellite Imagery data
AU - Cheng, Hao
AU - Lei, Haoran
AU - Zourlidou, Stefania
AU - Sester, Monika
N1 - Funding Information: This work is supported by the German Research Foundation (DFG) via the project GRK2159 i.c.sens.
PY - 2022/6/1
Y1 - 2022/6/1
N2 - Traffic regulators at intersections act as an essential factor that influences traffic flow and, subsequently, the route choices of commuters. A digital map that provides up-to-date traffic control information is beneficial not only for facilitating the commuters' trips, but also for energy-saving and environmental protection. In this paper, instead of using expensive surveying methods, we propose an automatic way based on a Conditional Variational Autoencoder (CVAE) to recognize traffic regulators, i. e., arm rules at intersections, by leveraging the GPS data collected from vehicles and the satellite imagery retrieved from digital maps, i. e., Google Maps. We apply a Long Short-Term Memory to extract the motion dynamics over a GPS sequence traversed through the intersection. Simultaneously, we build a Convolutional Neural Network (CNN) to extract the grid-based local imagery information associated with each step of the GPS positions. Moreover, a self-attention mechanism is adopted to extract the spatial and temporal features over both the GPS and grid sequences. The extracted temporal and spatial features are then combined for detecting the traffic arm rules. To analyze the performance of our method, we tested it on a GPS dataset collected by driving vehicles in Hannover, a medium-sized German city. Compared to a Random Forest model and an Encoder-Decoder model, our proposed model achieved better results with both accuracy and F1-score of 0.90 for the three-class (arm rules of uncontrolled, traffic light, and priority sign) task. We also carried out ablation studies to further investigate the effectiveness of the GPS input branch, the image input branch, and the self-attention mechanism in our model.
AB - Traffic regulators at intersections act as an essential factor that influences traffic flow and, subsequently, the route choices of commuters. A digital map that provides up-to-date traffic control information is beneficial not only for facilitating the commuters' trips, but also for energy-saving and environmental protection. In this paper, instead of using expensive surveying methods, we propose an automatic way based on a Conditional Variational Autoencoder (CVAE) to recognize traffic regulators, i. e., arm rules at intersections, by leveraging the GPS data collected from vehicles and the satellite imagery retrieved from digital maps, i. e., Google Maps. We apply a Long Short-Term Memory to extract the motion dynamics over a GPS sequence traversed through the intersection. Simultaneously, we build a Convolutional Neural Network (CNN) to extract the grid-based local imagery information associated with each step of the GPS positions. Moreover, a self-attention mechanism is adopted to extract the spatial and temporal features over both the GPS and grid sequences. The extracted temporal and spatial features are then combined for detecting the traffic arm rules. To analyze the performance of our method, we tested it on a GPS dataset collected by driving vehicles in Hannover, a medium-sized German city. Compared to a Random Forest model and an Encoder-Decoder model, our proposed model achieved better results with both accuracy and F1-score of 0.90 for the three-class (arm rules of uncontrolled, traffic light, and priority sign) task. We also carried out ablation studies to further investigate the effectiveness of the GPS input branch, the image input branch, and the self-attention mechanism in our model.
KW - Attention Mechanism
KW - Classification
KW - Deep Learning
KW - Generative Model
KW - Traffic Regulation
UR - http://www.scopus.com/inward/record.url?scp=85132154897&partnerID=8YFLogxK
U2 - 10.5194/isprs-archives-XLIII-B4-2022-287-2022
DO - 10.5194/isprs-archives-XLIII-B4-2022-287-2022
M3 - Conference contribution
AN - SCOPUS:85132154897
T3 - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
SP - 287
EP - 293
BT - XXIV ISPRS Congress (2022 edition)
T2 - 2022 24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow, Commission IV
Y2 - 6 June 2022 through 11 June 2022
ER -