Abstract
Prediction of trajectories such as that of pedestrians is crucial to the performance of autonomous agents. While previous works have leveraged conditional generative models like GANs and VAEs for learning the likely future trajectories, accurately modeling the dependency structure of these multimodal distributions, particularly over long time horizons remains challenging. Normalizing flow based generative models can model complex distributions admitting exact inference. These include variants with split coupling invertible transformations that are easier to parallelize compared to their autoregressive counterparts. To this end, we introduce a novel Haar wavelet based block autoregressive model leveraging split couplings, conditioned on coarse trajectories obtained from Haar wavelet based transformations at different levels of granularity. This yields an exact inference method that models trajectories at different spatio-temporal resolutions in a hierarchical manner. We illustrate the advantages of our approach for generating diverse and accurate trajectories on two real-world datasets – Stanford Drone and Intersection Drone.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., Fei-Fei, L., Savarese, S.: Social LSTM: human trajectory prediction in crowded spaces. In: CVPR (2016)
Ardizzone, L., Lüth, C., Kruse, J., Rother, C., Köthe, U.: Guided image generation with conditional invertible neural networks. arXiv preprint arXiv:1907.02392 (2019)
Bhattacharyya, A., Hanselmann, M., Fritz, M., Schiele, B., Straehle, C.N.: Conditional flow variational autoencoders for structured sequence prediction. In: BDL@NeurIPS (2019)
Bhattacharyya, A., Mahajan, S., Fritz, M., Schiele, B., Roth, S.: Normalizing flows with multi-scale autoregressive priors. In: CVPR (2020)
Bhattacharyya, A., Schiele, B., Fritz, M.: Accurate and diverse sampling of sequences based on a “best of many” sample objective. In: CVPR (2018)
Bock, J., Krajewski, R., Moers, T., Vater, L., Runde, S., Eckstein, L.: The ind dataset: a drone dataset of naturalistic vehicle trajectories at german intersections. arXiv preprint arXiv:1911.07602 (2019)
Chandra, R., Bhattacharya, U., Bera, A., Manocha, D.: Traphic: trajectory prediction in dense and heterogeneous traffic using weighted interactions. In: CVPR (2019)
Chen, T.Q., Behrmann, J., Duvenaud, D.K., Jacobsen, J.H.: Residual flows for invertible generative modeling. In: NeurIPS (2019)
Cremer, C., Li, X., Duvenaud, D.: Inference suboptimality in variational autoencoders. In: ICML (2018)
Deo, N., Trivedi, M.M.: Convolutional social pooling for vehicle trajectory prediction. In: CVPR Workshop (2018)
Deo, N., Trivedi, M.M.: Scene induced multi-modal trajectory forecasting via planning. In: ICRA Workshop (2019)
Dinh, L., Krueger, D., Bengio, Y.: Nice: non-linear independent components estimation. In: ICLR (2015)
Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real NVP. In: ICLR (2017)
Felsen, P., Lucey, P., Ganguly, S.: Where will they go? Predicting fine-grained adversarial multi-agent motion using conditional variational autoencoders. In: ECCV (2018)
Goodfellow, I.J., et al.: Generative adversarial nets. In: NIPS (2014)
Gupta, A., Johnson, J., Fei-Fei, L., Savarese, S., Alahi, A.: Social gan: socially acceptable trajectories with generative adversarial networks. In: CVPR (2018)
Haar, A.: Zur theorie der orthogonalen funktionensysteme. Math. Ann. 69(3), 331–371 (1910)
Helbing, D., Molnar, P.: Social force model for pedestrian dynamics. Phys. Rev. E 51, 4282 (1995)
Ho, J., Chen, X., Srinivas, A., Duan, Y., Abbeel, P.: Flow++: improving flow-based generative models with variational dequantization and architecture design. In: ICML (2019)
Huang, C.W., Dinh, L., Courville, A.: Augmented normalizing flows: bridging the gap between generative flows and latent variable models. arXiv preprint arXiv:2002.07101 (2020)
Kim, S., Lee, S.G., Song, J., Kim, J., Yoon, S.: Flowavenet: a generative flow for raw audio. In: ICML (2019)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: ICLR (2014)
Kingma, D.P., Dhariwal, P.: Glow: generative flow with invertible 1x1 convolutions. In: NeurIPS (2018)
Kirichenko, P., Izmailov, P., Wilson, A.G.: Why normalizing flows fail to detect out-of-distribution data. arXiv preprint arXiv:2006.08545 (2020)
Kumar, M., et al.: Videoflow: a flow-based generative model for video. In: ICLR (2020)
Lee, A.X., Zhang, R., Ebert, F., Abbeel, P., Finn, C., Levine, S.: Stochastic adversarial video prediction. arXiv preprint arXiv:1804.01523 (2018)
Lee, N., Choi, W., Vernaza, P., Choy, C.B., Torr, P.H., Chandraker, M.: Desire: distant future prediction in dynamic scenes with interacting agents. In: CVPR (2017)
Ma, Y., Zhu, X., Zhang, S., Yang, R., Wang, W., Manocha, D.: Trafficpredict: trajectory prediction for heterogeneous traffic-agents. In: AAAI (2019)
Mangalam, K., Girase, H., Agarwal, S., Lee, K.-H., Adeli, E., Malik, J., Gaidon, A.: It Is not the journey but the destination: endpoint conditioned trajectory prediction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 759–776. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58536-5_45
van den Oord, A., et al.: Wavenet: a generative model for raw audio. In: ISCA Speech Synthesis Workshop (2016)
van den Oord, A., Kalchbrenner, N., Espeholt, L., Kavukcuoglu, K., Vinyals, O., Graves, A.: Conditional image generation with PixelCNN decoders. In: NIPS (2016)
Pajouheshgar, E., Lampert, C.H.: Back to square one: probabilistic trajectory forecasting without bells and whistles. In: NeurIPs Workshop (2018)
Porwik, P., Lisowska, A.: The haar-wavelet transform in digital image processing: its status and achievements. Machine graphics and vision 13(1/2), 79–98 (2004)
Rhinehart, N., Kitani, K.M., Vernaza, P.: R2p2: a reparameterized pushforward policy for diverse, precise generative path forecasting. In: ECCV (2018)
Robicquet, A., Sadeghian, A., Alahi, A., Savarese, S.: Learning social etiquette: human trajectory understanding in crowded scenes. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 549–565. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_33
Sadeghian, A., Kosaraju, V., Sadeghian, A., Hirose, N., Rezatofighi, S.H., Savarese, S.: Sophie: an attentive gan for predicting paths compliant to social and physical constraints. In: CVPR (2019)
Sadeghian, A., Legros, F., Voisin, M., Vesel, R., Alahi, A., Savarese, S.: Car-net: clairvoyant attentive recurrent network. In: ECCV (2018)
Yamaguchi, K., Berg, A.C., Ortiz, L.E., Berg, T.L.: Who are you with and where are you going? In: CVPR (2011)
Yuan, Y., Kitani, K.: Diverse trajectory forecasting with determinantal point processes. In: ICLR (2020)
Zhao, T., et al.: Multi-agent tensor fusion for contextual trajectory prediction. In: CVPR (2019)
Ziegler, Z.M., Rush, A.M.: Latent normalizing flows for discrete sequences. In: ICML (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Bhattacharyya, A., Straehle, CN., Fritz, M., Schiele, B. (2021). Haar Wavelet Based Block Autoregressive Flows for Trajectories. In: Akata, Z., Geiger, A., Sattler, T. (eds) Pattern Recognition. DAGM GCPR 2020. Lecture Notes in Computer Science(), vol 12544. Springer, Cham. https://doi.org/10.1007/978-3-030-71278-5_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-71278-5_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-71277-8
Online ISBN: 978-3-030-71278-5
eBook Packages: Computer ScienceComputer Science (R0)