Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 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

VisionTraj: A Noise-Robust Trajectory Recovery Framework based on Large-scale Camera Network (2312.06428v1)

Published 11 Dec 2023 in cs.CV, cs.AI, cs.IR, and cs.LG

Abstract: Trajectory recovery based on the snapshots from the city-wide multi-camera network facilitates urban mobility sensing and driveway optimization. The state-of-the-art solutions devoted to such a vision-based scheme typically incorporate predefined rules or unsupervised iterative feedback, struggling with multi-fold challenges such as lack of open-source datasets for training the whole pipeline, and the vulnerability to the noises from visual inputs. In response to the dilemma, this paper proposes VisionTraj, the first learning-based model that reconstructs vehicle trajectories from snapshots recorded by road network cameras. Coupled with it, we elaborate on two rational vision-trajectory datasets, which produce extensive trajectory data along with corresponding visual snapshots, enabling supervised vision-trajectory interplay extraction. Following the data creation, based on the results from the off-the-shelf multi-modal vehicle clustering, we first re-formulate the trajectory recovery problem as a generative task and introduce the canonical Transformer as the autoregressive backbone. Then, to identify clustering noises (e.g., false positives) with the bound on the snapshots' spatiotemporal dependencies, a GCN-based soft-denoising module is conducted based on the fine- and coarse-grained Re-ID clusters. Additionally, we harness strong semantic information extracted from the tracklet to provide detailed insights into the vehicle's entry and exit actions during trajectory recovery. The denoising and tracklet components can also act as plug-and-play modules to boost baselines. Experimental results on the two hand-crafted datasets show that the proposed VisionTraj achieves a maximum +11.5% improvement against the sub-best model.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. The ind dataset: A drone dataset of naturalistic road user trajectories at german intersections. In 2020 IEEE Intelligent Vehicles Symposium (IV), pages 1929–1934. IEEE, 2020.
  2. 3d vehicle trajectory reconstruction in monocular video data using environment structure constraints. In Proceedings of the European Conference on Computer Vision (ECCV), pages 35–50, 2018.
  3. A simple framework for contrastive learning of visual representations. In International conference on machine learning, pages 1597–1607. PMLR, 2020.
  4. Adaptive hierarchical spatiotemporal network for traffic forecasting. arXiv preprint arXiv:2306.09386, 2023.
  5. Rntrajrec: Road network enhanced trajectory recovery with spatial-temporal transformer. In 2023 IEEE 39th International Conference on Data Engineering (ICDE), pages 829–842. IEEE, 2023.
  6. Virtual track: Applications and challenges of the rfid system on roads. IEEE Network, 28(1):42–47, 2014.
  7. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018.
  8. Constgat: Contextual spatial-temporal graph attention network for travel time estimation at baidu maps. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 2697–2705, 2020.
  9. An interdisciplinary review of smart vehicular traffic and its applications and challenges. Journal of Sensor and Actuator Networks, 8(1):13, 2019.
  10. Traffic control systems handbook. Technical report, United States. Federal Highway Administration. Office of Transportation …, 2005.
  11. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining, pages 855–864, 2016.
  12. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  13. A unified probabilistic framework for spatiotemporal passenger crowdedness inference within urban rail transit network. arXiv preprint arXiv:2306.08343, 2023.
  14. A survey of advances in vision-based vehicle re-identification. Computer Vision and Image Understanding, 182:50–63, 2019.
  15. Vehicle re-identification and trajectory reconstruction using multiple moving cameras in the carla driving simulator. In 2022 IEEE International Conference on Big Data (Big Data), pages 1858–1865. IEEE, 2022.
  16. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7871–7880, 2020.
  17. Urban mobility analytics: A deep spatial–temporal product neural network for traveler attributes inference. Transportation Research Part C: Emerging Technologies, 124:102921, 2021.
  18. A critical perceptual pre-trained model for complex trajectory recovery. arXiv preprint arXiv:2311.02631, 2023.
  19. A semisupervised end-to-end framework for transportation mode detection by using gps-enabled sensing devices. IEEE Internet of Things Journal, 9(10):7842–7852, 2022.
  20. Ziyue Li. Tensor topic models with graphs and applications on individualized travel patterns. In 2021 IEEE 37th International Conference on Data Engineering (ICDE), pages 2756–2761. IEEE, 2021.
  21. Long-short term spatiotemporal tensor prediction for passenger flow profile. IEEE Robotics and Automation Letters, 5(4):5010–5017, 2020.
  22. Individualized passenger travel pattern multi-clustering based on graph regularized tensor latent dirichlet allocation. Data Mining and Knowledge Discovery, 36(4):1247–1278, 2022.
  23. Tensor dirichlet process multinomial mixture model for passenger trajectory clustering. arXiv preprint arXiv:2306.13794, 2023.
  24. Dynamic causal graph convolutional network for traffic prediction. arXiv preprint arXiv:2306.07019, 2023.
  25. Pre-training context and time aware location embeddings from spatial-temporal trajectories for user next location prediction. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 4241–4248, 2021.
  26. Vehicle trajectory recovery on road network based on traffic camera video data. In Proceedings of the 29th International Conference on Advances in Geographic Information Systems, pages 389–398, 2021.
  27. City-scale multi-camera vehicle tracking guided by crossroad zones. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4129–4137, 2021.
  28. Large-scale vehicle re-identification in urban surveillance videos. In 2016 IEEE international conference on multimedia and expo (ICME), pages 1–6. IEEE, 2016.
  29. Vehicle trajectory completion for automatic number plate recognition data: A temporal knowledge graph-based method. International Journal of Pattern Recognition and Artificial Intelligence, 2023.
  30. Jointly contrastive representation learning on road network and trajectory. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pages 1501–1510, 2022.
  31. Hmm with non-emitting states for map matching. In European Conference on Data Analysis (ECDA), Date: 2018/07/04-2018/07/06, Location: Paderborn, Germany, 2018.
  32. Hidden markov map matching through noise and sparseness. In Proceedings of the 17th ACM SIGSPATIAL international conference on advances in geographic information systems, pages 336–343, 2009.
  33. A hybrid hmm model for travel path inference with sparse gps samples. Transportation, 45:233–246, 2018.
  34. Vehicle trajectory reconstruction on urban traffic network using automatic license plate recognition data. IEEE Access, 9:49110–49120, 2021.
  35. Mtrajrec: Map-constrained trajectory recovery via seq2seq multi-task learning. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pages 1410–1419, 2021.
  36. Moshe Sniedovich. Dijkstra’s algorithm revisited: the dynamic programming connexion. Control and cybernetics, 35(3):599–620, 2006.
  37. Large-scale vehicle trajectory reconstruction with camera sensing network. In Proceedings of the 27th Annual International Conference on Mobile Computing and Networking, pages 188–200, 2021.
  38. Attention is all you need. Advances in neural information processing systems, 30, 2017.
  39. V2i-carla: a novel dataset and a method for vehicle reidentification-based v2i environment. IEEE Transactions on Instrumentation and Measurement, 71:1–9, 2022.
  40. Deep trajectory recovery with fine-grained calibration using kalman filter. IEEE Transactions on Knowledge and Data Engineering, 33(3):921–934, 2019.
  41. Deep Trajectory Recovery with Fine-Grained Calibration using Kalman Filter. IEEE Transactions on Knowledge and Data Engineering, 33(3):921–934, March 2021. Conference Name: IEEE Transactions on Knowledge and Data Engineering.
  42. Deep trajectory recovery with fine-grained calibration using kalman filter. IEEE Transactions on Knowledge and Data Engineering, 2019.
  43. Correlated time series self-supervised representation learning via spatiotemporal bootstrapping. arXiv preprint arXiv:2306.06994, 2023.
  44. A general dynamic sequential learning framework for vehicle trajectory reconstruction using automatic vehicle location or identification data. Physica A: Statistical Mechanics and its Applications, 608:128243, 2022.
  45. Learning effective road network representation with hierarchical graph neural networks. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 6–14, 2020.
  46. Unsupervised path representation learning with curriculum negative sampling. arXiv preprint arXiv:2106.09373, 2021.
  47. Box-grained reranking matching for multi-camera multi-target tracking. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3096–3106, 2022.
  48. Simulating content consistent vehicle datasets with attribute descent. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VI 16, pages 775–791. Springer, 2020.
  49. Spatio-temporal vehicle trajectory recovery on road network based on traffic camera video data. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 4413–4421, 2022.
  50. City-scale vehicle trajectory data from traffic camera videos. Scientific Data, 10(1):711, 2023.
  51. Trajectory forecasting from detection with uncertainty-aware motion encoding. arXiv preprint arXiv:2202.01478, 2022.
  52. Reducing uncertainty of low-sampling-rate trajectories. In 2012 IEEE 28th international conference on data engineering, pages 1144–1155. IEEE, 2012.
  53. Platoon trajectory completion in a mixed traffic environment under sparse observation. IEEE Transactions on Intelligent Transportation Systems, 23(9):16217–16226, 2022.
Citations (3)
View on Semantic Scholar

Summary

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

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