Skip to main content

2018 | OriginalPaper | Buchkapitel

Where Will They Go? Predicting Fine-Grained Adversarial Multi-agent Motion Using Conditional Variational Autoencoders

verfasst von : Panna Felsen, Patrick Lucey, Sujoy Ganguly

Erschienen in: Computer Vision – ECCV 2018

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Simultaneously and accurately forecasting the behavior of many interacting agents is imperative for computer vision applications to be widely deployed (e.g., autonomous vehicles, security, surveillance, sports). In this paper, we present a technique using conditional variational autoencoder which learns a model that “personalizes” prediction to individual agent behavior within a group representation. Given the volume of data available and its adversarial nature, we focus on the sport of basketball and show that our approach efficiently predicts context-specific agent motions. We find that our model generates results that are three times as accurate as previous state of the art approaches (5.74 ft vs. 17.95 ft).

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Anhänge
Nur mit Berechtigung zugänglich
Literatur
1.
Zurück zum Zitat Lee, N., Choi, W., Vernaza, P., Choy, C., Torr, P., Chandraker, M.: DESIRE: distance future prediction in dynamic scenes with interacting agents (2017) Lee, N., Choi, W., Vernaza, P., Choy, C., Torr, P., Chandraker, M.: DESIRE: distance future prediction in dynamic scenes with interacting agents (2017)
2.
Zurück zum Zitat Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., Fei-Fei, L., Savarese, S.: Social LSTM: human trajectory prediction in crowded spaces (2016) Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., Fei-Fei, L., Savarese, S.: Social LSTM: human trajectory prediction in crowded spaces (2016)
3.
Zurück zum Zitat Jain, A., Singh, A., Koppula, H., Soh, S., Saxena, A.: Recurrent neural networks for driver activity anticipation via sensory-fusion architecture (2016) Jain, A., Singh, A., Koppula, H., Soh, S., Saxena, A.: Recurrent neural networks for driver activity anticipation via sensory-fusion architecture (2016)
4.
Zurück zum Zitat Akhter, I., Simon, T., Khan, S., Matthews, I., Sheikh, Y.: Bilinear spatiotemporal basis models. ACM Trans. Graph. (TOG) (2012) Akhter, I., Simon, T., Khan, S., Matthews, I., Sheikh, Y.: Bilinear spatiotemporal basis models. ACM Trans. Graph. (TOG) (2012)
5.
Zurück zum Zitat Lucey, P., Bialkowski, A., Carr, P., Morgan, S., Matthews, I., Sheikh, Y.: Representing and discovering adversarial team behaviors using player roles (2013) Lucey, P., Bialkowski, A., Carr, P., Morgan, S., Matthews, I., Sheikh, Y.: Representing and discovering adversarial team behaviors using player roles (2013)
6.
Zurück zum Zitat Insafutdinov, E., et al.: ArtTrack: articulated multi-person tracking in the wild (2017) Insafutdinov, E., et al.: ArtTrack: articulated multi-person tracking in the wild (2017)
7.
Zurück zum Zitat Le, H., Yue, Y., Carr, P., Lucey, P.: Coordinated multi-agent imitation learning (2017) Le, H., Yue, Y., Carr, P., Lucey, P.: Coordinated multi-agent imitation learning (2017)
8.
Zurück zum Zitat Yamaguchi, K., Berg, A., Ortiz, L., Berg, T.: Who are you with and where are you going? (2011) Yamaguchi, K., Berg, A., Ortiz, L., Berg, T.: Who are you with and where are you going? (2011)
9.
Zurück zum Zitat Butt, A., Collins, R.: Multi-target tracking by lagrangian relaxation to min-cost network flow (2013) Butt, A., Collins, R.: Multi-target tracking by lagrangian relaxation to min-cost network flow (2013)
10.
Zurück zum Zitat Wang, S., Fowlkes, C.: Learning optimal parameters for multi-target tracking (2016) Wang, S., Fowlkes, C.: Learning optimal parameters for multi-target tracking (2016)
11.
Zurück zum Zitat Maksai, A., Wang, X., Fua, P.: What players do with the ball: a physically constrained interaction modeling (2016) Maksai, A., Wang, X., Fua, P.: What players do with the ball: a physically constrained interaction modeling (2016)
12.
Zurück zum Zitat Kim, K., Grundmann, M., Shamir, A., Matthews, I., Hodgins, J., Essa, I.: Motion fields to PRedict play evolution in dynamic sports scenes (2010) Kim, K., Grundmann, M., Shamir, A., Matthews, I., Hodgins, J., Essa, I.: Motion fields to PRedict play evolution in dynamic sports scenes (2010)
13.
Zurück zum Zitat Chen, J., Le, H., Carr, P., Yue, Y., Little, J.: Learning online smooth predictors for Realtime camera planning using recurrent decision trees (2016) Chen, J., Le, H., Carr, P., Yue, Y., Little, J.: Learning online smooth predictors for Realtime camera planning using recurrent decision trees (2016)
14.
Zurück zum Zitat Zheng, S., Yue, Y., Lucey, P.: Generating long-term trajectories using deep hierarchical networks (2016) Zheng, S., Yue, Y., Lucey, P.: Generating long-term trajectories using deep hierarchical networks (2016)
15.
Zurück zum Zitat Felsen, P., Agrawal, P., Malik, J.: What will happen next? Forecasting player moves in sports videos (2017) Felsen, P., Agrawal, P., Malik, J.: What will happen next? Forecasting player moves in sports videos (2017)
16.
Zurück zum Zitat Su, S., Hong, J.P., Shi, J., Park, H.S.: Social behavior prediction from first person videos. CoRR abs/1611.09464 (2016) Su, S., Hong, J.P., Shi, J., Park, H.S.: Social behavior prediction from first person videos. CoRR abs/1611.09464 (2016)
17.
Zurück zum Zitat Koren, Y., Bell, R., Volinksy, C.: Matrix factorization techniques for recommender systems. Computer 42(8) (2009)CrossRef Koren, Y., Bell, R., Volinksy, C.: Matrix factorization techniques for recommender systems. Computer 42(8) (2009)CrossRef
18.
Zurück zum Zitat Deng, Z., et al.: Factorized variational autoencoders for modeling audience reactions to movies (2017) Deng, Z., et al.: Factorized variational autoencoders for modeling audience reactions to movies (2017)
19.
Zurück zum Zitat Charles, J., Pfister, T., Magee, D., Hogg, D., Zisserman, A.: Personalizing human video pose estimation (2016) Charles, J., Pfister, T., Magee, D., Hogg, D., Zisserman, A.: Personalizing human video pose estimation (2016)
21.
Zurück zum Zitat Gregor, K., Danihelka, I., Graves, A., Wierstra, D.: DRAW: A recurrent neural network for image generation. CoRR abs/1502.04623 (2015) Gregor, K., Danihelka, I., Graves, A., Wierstra, D.: DRAW: A recurrent neural network for image generation. CoRR abs/1502.04623 (2015)
22.
Zurück zum Zitat Bowman, S.R., Vilnis, L., Vinyals, O., Dai, A.M., Józefowicz, R., Bengio, S.: Generating sentences from a continuous space. CoRR abs/1511.06349 (2015) Bowman, S.R., Vilnis, L., Vinyals, O., Dai, A.M., Józefowicz, R., Bengio, S.: Generating sentences from a continuous space. CoRR abs/1511.06349 (2015)
23.
Zurück zum Zitat Kingma, D., Mohamed, S., Rezende, D., Welling, M.: Semi-supervised learning with deep generative models (2014) Kingma, D., Mohamed, S., Rezende, D., Welling, M.: Semi-supervised learning with deep generative models (2014)
24.
Zurück zum Zitat Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models (2015) Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models (2015)
25.
Zurück zum Zitat van den Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. CoRR abs/1601.06759 (2016) van den Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. CoRR abs/1601.06759 (2016)
26.
Zurück zum Zitat Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting, June 2016 Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting, June 2016
27.
Zurück zum Zitat Walker, J., Doersch, C., Gupta, A., Hebert, M.: An uncertain future: Forecasting from static images using variational autoencoders. CoRR abs/1606.07873 (2016) Walker, J., Doersch, C., Gupta, A., Hebert, M.: An uncertain future: Forecasting from static images using variational autoencoders. CoRR abs/1606.07873 (2016)
28.
Zurück zum Zitat Sha, L., Lucey, P., Zheng, S., Kim, T., Yue, Y., Sridharan, S.: Fine-grained retrieval of sports plays using tree-based alignment of trajectories (2017) Sha, L., Lucey, P., Zheng, S., Kim, T., Yue, Y., Sridharan, S.: Fine-grained retrieval of sports plays using tree-based alignment of trajectories (2017)
Metadaten
Titel
Where Will They Go? Predicting Fine-Grained Adversarial Multi-agent Motion Using Conditional Variational Autoencoders
verfasst von
Panna Felsen
Patrick Lucey
Sujoy Ganguly
Copyright-Jahr
2018
DOI
https://doi.org/10.1007/978-3-030-01252-6_45

Premium Partner