Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
162 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Probabilistic Image-Driven Traffic Modeling via Remote Sensing (2403.05521v2)

Published 8 Mar 2024 in cs.CV

Abstract: This work addresses the task of modeling spatiotemporal traffic patterns directly from overhead imagery, which we refer to as image-driven traffic modeling. We extend this line of work and introduce a multi-modal, multi-task transformer-based segmentation architecture that can be used to create dense city-scale traffic models. Our approach includes a geo-temporal positional encoding module for integrating geo-temporal context and a probabilistic objective function for estimating traffic speeds that naturally models temporal variations. We evaluate our method extensively using the Dynamic Traffic Speeds (DTS) benchmark dataset and significantly improve the state-of-the-art. Finally, we introduce the DTS++ dataset to support mobility-related location adaptation experiments.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (52)
  1. Uber Movement: Speeds calculation methodology. Technical report, Uber Technologies, Inc., 2019.
  2. Using convolutional networks and satellite imagery to identify patterns in urban environments at a large scale. In ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2017.
  3. Measuring traffic. Statistical Science, pages 581–597, 2007.
  4. Geoff Boeing. OSMnx: New methods for acquiring, constructing, analyzing, and visualizing complex street networks. Computers, Environment and Urban Systems, 65:126–139, 2017.
  5. Does transportation network centrality determine housing price? Journal of Transport Geography, 103:103397, 2022.
  6. A survey on visual traffic simulation: Models, evaluations, and applications in autonomous driving. 39(1):287–308, 2020.
  7. The promises of big data and small data for travel behavior (aka human mobility) analysis. Transportation research part C: emerging technologies, 68:285–299, 2016.
  8. Estimating vehicle and pedestrian activity from town and city traffic cameras. Sensors, 21(13):4564, 2021.
  9. Michael Crawshaw. Multi-task learning with deep neural networks: A survey. arXiv preprint arXiv:2009.09796, 2020.
  10. Multimodal trajectory predictions for autonomous driving using deep convolutional networks. In International Conference on Robotics and Automation, 2019.
  11. Coatnet: Marrying convolution and attention for all data sizes. In Advances in Neural Information Processing Systems, 2021.
  12. Traffic noise estimation from satellite imagery with deep learning. In International Geoscience and Remote Sensing Symposium, 2022.
  13. WA Falcon. Pytorch lightning. GitHub. Note: https://github.com/PyTorchLightning/pytorch-lightning, 3, 2019.
  14. Rethinking efficient lane detection via curve modeling. In IEEE Conference on Computer Vision and Pattern Recognition, 2022.
  15. Vision-based vehicle speed estimation: A survey. IET Intelligent Transport Systems, 15(8):987–1005, 2021.
  16. Are we ready for autonomous driving? the kitti vision benchmark suite. In IEEE Conference on Computer Vision and Pattern Recognition, 2012.
  17. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In AAAI Conference on Artificial Intelligence, 2019.
  18. Rasternet: Modeling free-flow speed using lidar and overhead imagery. In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.
  19. Improving traffic behaviour and safety through urban design. In Proceedings of the Institution of Civil Engineers - Civil Engineering, pages 39–47, 2005.
  20. Dagmapper: Learning to map by discovering lane topology. In IEEE International Conference on Computer Vision, 2019.
  21. Squeeze-and-excitation networks. In IEEE Conference on Computer Vision and Pattern Recognition, 2018.
  22. A weakly supervised approach for estimating spatial density functions from high-resolution satellite imagery. In ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, 2018.
  23. Computer vision for autonomous vehicles: Problems, datasets and state of the art. Foundations and Trends® in Computer Graphics and Vision, 12(1–3):1–308, 2020.
  24. Rethinking positional encoding in language pre-training. In International Conference on Learning Representations, 2020.
  25. Adam: A method for stochastic optimization. In International Conference on Learning Representations, 2014.
  26. Citywide reconstruction of traffic flow using the vehicle-mounted moving camera in the carla driving simulator. In IEEE International Conference on Intelligent Transportation Systems, 2022.
  27. Traffic flow prediction with vehicle trajectories. In AAAI Conference on Artificial Intelligence, 2021.
  28. Swin transformer: Hierarchical vision transformer using shifted windows. In IEEE Conference on Computer Vision and Pattern Recognition, 2021.
  29. Swin transformer v2: Scaling up capacity and resolution. In IEEE Conference on Computer Vision and Pattern Recognition, 2022.
  30. Deep learning in remote sensing applications: A meta-analysis and review. ISPRS journal of photogrammetry and remote sensing, 152:166–177, 2019.
  31. Presence-only geographical priors for fine-grained image classification. In IEEE International Conference on Computer Vision, 2019.
  32. Data to the people: a review of public and proprietary data for transport models. Transport reviews, 42(4):415–440, 2022.
  33. Community design, street networks, and public health. Journal of Transport & Health, 1(4):326–340, 2014.
  34. Deeproadmapper: Extracting road topology from aerial images. In IEEE International Conference on Computer Vision, 2017.
  35. Towards indirect top-down road transport emissions estimation. In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.
  36. Combining satellite imagery and open data to map road safety. In AAAI Conference on Artificial Intelligence, 2017.
  37. Pytorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems, 2019.
  38. A multimodal approach to mapping soundscapes. In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.
  39. Learning a dynamic map of visual appearance. In IEEE Conference on Computer Vision and Pattern Recognition, 2020.
  40. Implicit neural representations with periodic activation functions. In Advances in Neural Information Processing Systems, 2020.
  41. Remote estimation of free-flow speeds. In IEEE International Geoscience and Remote Sensing Symposium, 2019.
  42. Openstreetmap: Challenges and opportunities in machine learning and remote sensing. IEEE Geoscience and Remote Sensing Magazine, 9(1):184–199, 2020.
  43. A spatio-temporal analysis of the impact of congestion on traffic safety on major roads in the uk. Transportmetrica A: Transport Science, 9(2):124–148, 2013.
  44. Pvt v2: Improved baselines with pyramid vision transformer. Computational Visual Media, 2022.
  45. Dynamic traffic modeling from overhead imagery. In IEEE Conference on Computer Vision and Pattern Recognition, 2020.
  46. Understanding and mapping natural beauty. In IEEE International Conference on Computer Vision, 2017a.
  47. A unified model for near and remote sensing. In IEEE International Conference on Computer Vision, 2017b.
  48. Revisiting near/remote sensing with geospatial attention. In IEEE Conference on Computer Vision and Pattern Recognition, 2022.
  49. Segformer: Simple and efficient design for semantic segmentation with transformers. In Advances in Neural Information Processing Systems, 2021.
  50. Projecting your view attentively: Monocular road scene layout estimation via cross-view transformation. In IEEE Conference on Computer Vision and Pattern Recognition, 2021.
  51. Spatio-temporal graph structure learning for traffic forecasting. In AAAI Conference on Artificial Intelligence, 2020.
  52. D-linknet: Linknet with pretrained encoder and dilated convolution for high resolution satellite imagery road extraction. In IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now