Discriminative context learning with gated recurrent unit for group activity recognition

Pil Soo Kim, Dong Gyu Lee, Seong Whan Lee

Research output: Contribution to journalArticlepeer-review

47 Citations (Scopus)

Abstract

In this study, we address the problem of similar local motions that create confusion within different group activities. To reduce the influences of motions, we propose a discriminative group context feature (DGCF) that considers prominent sub-events. Moreover, we adopt a gated recurrent unit (GRU) model that can learn temporal changes in a sequence. In real-world scenarios, people perform activities with different temporal lengths. The GRU model handles an arbitrary length of data for training with nonlinear hidden units in the network. However, when we use a deep neural network model, data scarcity causes overfitting problems. Data augmentation methods for images are ineffective for trajectory data augmentation. Thus, we also propose a method for trajectory augmentation. We evaluate the effectiveness of the proposed method on three datasets. In our experiments on each dataset, we show that the proposed method outperforms the competing state-of-the-art methods for group activity recognition.

Original languageEnglish
Pages (from-to)149-161
Number of pages13
JournalPattern Recognition
Volume76
DOIs
Publication statusPublished - 2018 Apr

Bibliographical note

Funding Information:
This work was supported by Institute for Information & communications Technology Promotion(IITP) grant funded by the Korea government(MSIT) [No. B0101-15-0552, Development of Predictive Visual Intelligence Technology] and [No. R7117-16-0157, Development of Smart Car Vision Techniques based on Deep Learning for Pedestrian Safety]. Pil-Soo Kim received the B.S. degree in the Department of Information and Communications Engineering at Sungkonghoe University, Seoul, Korea, in 2015. He is currently a M.S. student in the Department of Computer and Radio Communications Engineering at Korea University, Seoul. His research interests include computer vision and pattern recognition. Dong-Gyu Lee received the B.S. degree in Computer Engineering at Kwangwoon University, Seoul, Korea, in 2011. He is currently a Ph.D. student in the Department of Computer and Radio Communications Engineering, at Korea University, Seoul. His research interests include computer vision, machine learning, and computational models of vision. Seong-Whan Lee received his B.S. degree in Computer Science and Statistics from Seoul National University, Seoul, in 1984, and his M.S. and Ph.D. degrees in Computer Science from the Korea Advanced Institute of Science and Technology, Seoul, Korea, in 1986 and 1989, respectively. Currently, he is the Hyundai-Kia Motor Chair Professor and the head of the Department of Brain and Cognitive Engineering at Korea University. He is a fellow of the IEEE, IAPR, and the Korea Academy of Science and Technology. His research interests include pattern recognition, artificial intelligence and brain engineering.

Publisher Copyright:
© 2017 Elsevier Ltd

Keywords

  • Data augmentation
  • Gated recurrent unit
  • Group activity recognition
  • Recurrent neural network
  • Sequence modeling
  • Video surveillance

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Discriminative context learning with gated recurrent unit for group activity recognition'. Together they form a unique fingerprint.

Cite this