TY - GEN
T1 - Adaptive Retraining of Visual Recognition-Model in Human Activity Recognition by Collaborative Humanoid Robots
AU - Nagrath, Vineet
AU - Hariz, Mossaab
AU - Yacoubi, Mounim A.El
N1 - Publisher Copyright:
© 2021, Springer Nature Switzerland AG.
PY - 2021/1/1
Y1 - 2021/1/1
N2 - We present a vision-based activity recognition system for centrally connected humanoid robots. The robots interact with several human participants who have varying behavioral styles and inter-activity-variability. A cloud server provides and updates the recognition model in all robots. The server continuously fetches the new activity videos recorded by the robots. It also fetches corresponding results and ground-truths provided by the human interacting with the robot. A decision on when to retrain the recognition model is made by an evolving performance-based logic. In the current article, we present the aforementioned adaptive recognition system with special emphasis on the partitioning logic employed for the division of new videos in training, cross-validation, and test groups of the next retraining instance. The distinct operating logic is based on class-wise recognition inaccuracies of the existing model. We compare this approach to a probabilistic partitioning approach in which the videos are partitioned with no performance considerations.
AB - We present a vision-based activity recognition system for centrally connected humanoid robots. The robots interact with several human participants who have varying behavioral styles and inter-activity-variability. A cloud server provides and updates the recognition model in all robots. The server continuously fetches the new activity videos recorded by the robots. It also fetches corresponding results and ground-truths provided by the human interacting with the robot. A decision on when to retrain the recognition model is made by an evolving performance-based logic. In the current article, we present the aforementioned adaptive recognition system with special emphasis on the partitioning logic employed for the division of new videos in training, cross-validation, and test groups of the next retraining instance. The distinct operating logic is based on class-wise recognition inaccuracies of the existing model. We compare this approach to a probabilistic partitioning approach in which the videos are partitioned with no performance considerations.
KW - Computer vision
KW - Dense interest point trajectories
KW - Distributed robot systems
KW - Human activity recognition
KW - Intersection-kernel svm model
KW - Learning and adaptive systems
KW - Online learning
U2 - 10.1007/978-3-030-55187-2_12
DO - 10.1007/978-3-030-55187-2_12
M3 - Conference contribution
AN - SCOPUS:85090098104
SN - 9783030551865
T3 - Advances in Intelligent Systems and Computing
SP - 124
EP - 143
BT - Intelligent Systems and Applications - Proceedings of the 2020 Intelligent Systems Conference IntelliSys Volume 2
A2 - Arai, Kohei
A2 - Kapoor, Supriya
A2 - Bhatia, Rahul
PB - Springer
T2 - Intelligent Systems Conference, IntelliSys 2020
Y2 - 3 September 2020 through 4 September 2020
ER -