TY - GEN
T1 - LSTM-based early recognition of motion patterns
AU - Weber, Markus
AU - Liwicki, Marcus
AU - Stricker, Didier
AU - Scholzel, Christopher
AU - Uchida, Seiichi
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014/12/4
Y1 - 2014/12/4
N2 - In this paper a method for Early Recognition (ER) of Motion Templates (MTs) is presented. We define ER as an algorithm to provide recognition results before a motion sequence is completed. In our experiments we apply Long Short-Term Memory (LSTM) and optimize the training for the task of recognizing the motion template as early as possible. The evaluation has shown that the recognition accuracy for a frame-by-frame classification the LSTM achieves a recognition accuracy of 88% if no training data of the person him/herself is included, and 92% if the training data also contains motion sequences of the person. Furthermore, the average earliness - the number of time frames it takes before the LSTM correctly classifies a motion pattern - is around 24.77 frames, which is less than a second with the used tracking technology, i.e., the Microsoft Kinect.
AB - In this paper a method for Early Recognition (ER) of Motion Templates (MTs) is presented. We define ER as an algorithm to provide recognition results before a motion sequence is completed. In our experiments we apply Long Short-Term Memory (LSTM) and optimize the training for the task of recognizing the motion template as early as possible. The evaluation has shown that the recognition accuracy for a frame-by-frame classification the LSTM achieves a recognition accuracy of 88% if no training data of the person him/herself is included, and 92% if the training data also contains motion sequences of the person. Furthermore, the average earliness - the number of time frames it takes before the LSTM correctly classifies a motion pattern - is around 24.77 frames, which is less than a second with the used tracking technology, i.e., the Microsoft Kinect.
UR - https://www.scopus.com/pages/publications/84919883876
UR - https://www.scopus.com/pages/publications/84919883876#tab=citedBy
U2 - 10.1109/ICPR.2014.611
DO - 10.1109/ICPR.2014.611
M3 - Conference contribution
AN - SCOPUS:84919883876
T3 - Proceedings - International Conference on Pattern Recognition
SP - 3552
EP - 3557
BT - 2014 22nd International Conference on Pattern Recognition
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 22nd International Conference on Pattern Recognition, ICPR 2014
Y2 - 24 August 2014 through 28 August 2014
ER -