Skip to main content

2018 | OriginalPaper | Buchkapitel

Recognizing Human Activities in Videos Using Improved Dense Trajectories over LSTM

verfasst von : Krit Karan Singh, Snehasis Mukherjee

Erschienen in: Computer Vision, Pattern Recognition, Image Processing, and Graphics

Verlag: Springer Singapore

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

search-config
loading …

Abstract

We propose a deep learning based technique to classify actions based on Long Short Term Memory (LSTM) networks. The proposed scheme first learns spatial temporal features from the video, using an extension of the Convolutional Neural Networks (CNN) to 3D. A Recurrent Neural Network (RNN) is then trained to classify each sequence considering the temporal evolution of the learned features for each time step. Experimental results on the CMU MoCap, UCF 101, Hollywood 2 dataset show the efficacy of the proposed approach. We extend the proposed framework with an efficient motion feature, to enable handling significant camera motion. The proposed approach outperforms the existing deep models for each dataset.

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!

Literatur
1.
Zurück zum Zitat Ziaeefar, M., Bergevin, R.: Semantic human activity recognition: a literature review. Pattern Recognit. 48(8), 2329–2345 (2015)CrossRef Ziaeefar, M., Bergevin, R.: Semantic human activity recognition: a literature review. Pattern Recognit. 48(8), 2329–2345 (2015)CrossRef
2.
Zurück zum Zitat Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: CVPR, pp. 1–8 (2008) Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: CVPR, pp. 1–8 (2008)
3.
Zurück zum Zitat Chen, M.Y., Hauptmann, A.: MoSIFT: recognizing human actions in surveillance videos. Technical report CMU-CS-09-161. Carnegie Mellon University (2009) Chen, M.Y., Hauptmann, A.: MoSIFT: recognizing human actions in surveillance videos. Technical report CMU-CS-09-161. Carnegie Mellon University (2009)
4.
Zurück zum Zitat Dollar, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse spatio-temporal features. In: Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, pp. 65–72 (2005) Dollar, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse spatio-temporal features. In: Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, pp. 65–72 (2005)
5.
Zurück zum Zitat Singh, S., Arora, C., Jawahar, C.V.: First person action recognition using deep learned descriptors. In: CVPR 2016 (2016) Singh, S., Arora, C., Jawahar, C.V.: First person action recognition using deep learned descriptors. In: CVPR 2016 (2016)
6.
Zurück zum Zitat Mukherjee, S., Biswas, S.K., Mukherjee, D.P.: Recognizing human action at a distance in video by key poses. IEEE Trans. Circ. Syst. Video Technol. 21(9), 1228–1241 (2011)CrossRef Mukherjee, S., Biswas, S.K., Mukherjee, D.P.: Recognizing human action at a distance in video by key poses. IEEE Trans. Circ. Syst. Video Technol. 21(9), 1228–1241 (2011)CrossRef
7.
Zurück zum Zitat Mukherjee, S., Biswas, S.K., Mukherjee, D.P.: Recognizing interactions between human performers by ‘Dominating Pose Doublet’. Mach. Vis. Appl. 25(4), 1033–1052 (2014)CrossRef Mukherjee, S., Biswas, S.K., Mukherjee, D.P.: Recognizing interactions between human performers by ‘Dominating Pose Doublet’. Mach. Vis. Appl. 25(4), 1033–1052 (2014)CrossRef
8.
Zurück zum Zitat Wang, H., Klaser, A., Schmid, C., Liu, C.-L.: Dense trajectories and motion boundary descriptors for action recognition. Int. J. Comput. Vis. 103(1), 60–79 (2013)MathSciNetCrossRef Wang, H., Klaser, A., Schmid, C., Liu, C.-L.: Dense trajectories and motion boundary descriptors for action recognition. Int. J. Comput. Vis. 103(1), 60–79 (2013)MathSciNetCrossRef
10.
Zurück zum Zitat Wang, H., Schmid, C.: Action recognition with improved trajectories. In: ICCV, pp. 3551–3558 (2013) Wang, H., Schmid, C.: Action recognition with improved trajectories. In: ICCV, pp. 3551–3558 (2013)
11.
Zurück zum Zitat Buddubariki, V., Tulluri, S.G., Mukherjee, S.: Event recognition in egocentric videos using a novel trajectory based feature. In: ICVGIP, pp. 76:1–76:8. ACM (2016) Buddubariki, V., Tulluri, S.G., Mukherjee, S.: Event recognition in egocentric videos using a novel trajectory based feature. In: ICVGIP, pp. 76:1–76:8. ACM (2016)
12.
Zurück zum Zitat Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human action classes from videos in the wild. In: CRCV-TR-12-01, November 2012 Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human action classes from videos in the wild. In: CRCV-TR-12-01, November 2012
14.
Zurück zum Zitat Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE T-PAMI 35(1), 221–231 (2013)CrossRef Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE T-PAMI 35(1), 221–231 (2013)CrossRef
15.
Zurück zum Zitat Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015) Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015)
16.
Zurück zum Zitat Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR (2014) Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR (2014)
17.
Zurück zum Zitat Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep convolutional descriptors. In: CVPR (2015) Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep convolutional descriptors. In: CVPR (2015)
18.
Zurück zum Zitat Donahue, J., Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR (2015) Donahue, J., Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR (2015)
20.
Zurück zum Zitat Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: CVPR (2009) Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: CVPR (2009)
23.
Zurück zum Zitat Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)MathSciNetCrossRef Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)MathSciNetCrossRef
Metadaten
Titel
Recognizing Human Activities in Videos Using Improved Dense Trajectories over LSTM
verfasst von
Krit Karan Singh
Snehasis Mukherjee
Copyright-Jahr
2018
Verlag
Springer Singapore
DOI
https://doi.org/10.1007/978-981-13-0020-2_8