Abstract
Human activity recognition (HAR) has a great impact on human-robot collaboration (HRC), especially in industrial works. However, it is difficult to find industrial activity data. With a goal of making the interactions between humans and robots more straightforward, we organized Bento Packaging Activity Recognition Challenge as a part of The 3rd International Conference on Activity and Behavior Computing. Here, the term Bento refers to a single-serving lunch box originated in Japan. We provided ten Bento packing activities data. The activities are performed by four subjects with a moving conveyor belt. In this work, we analyze and summarize the approaches of submission of the challenge. The challenge started on June 1st, 2021, and continued until August 25th, 2021. The participant teams used the given dataset to predict the ten activities, and they were evaluated using accuracy. The winning team used an ensemble model and achieved around 64% accuracy on testing data. To further improve the accuracy of the testing data, models particularly designed for small data with larger intra-class similarity could help.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Liu, L., Peng, Y., Wang, S., Liu, M., Huang, Z.: Complex activity recognition using time series pattern dictionary learned from ubiquitous sensors. Inf. Sci. 340–341, 41–57 (2016). https://doi.org/10.1016/j.ins.2016.01.020; https://sciencedirect.com/science/article/pii/S0020025516000311
Lee, S.U., Hofmann, A., Williams, B.: A model-based human activity recognition for human–robot collaboration. In: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 736–743 (2019). https://doi.org/10.1109/IROS40897.2019.8967650
Roitberg, A., Perzylo, A., Somani, N., Giuliani, M., Rickert, M., Knoll, A.: Human activity recognition in the context of industrial human–robot interaction. In: Signal and Information Processing Association Annual Summit and Conference (APSIPA), Asia-Pacific, pp. 1–10 (2014). https://doi.org/10.1109/APSIPA.2014.7041588
Alia, S.S., Lago, P., Takeda, S., Adachi, K., Benaissa, B., Ahad, M.A.R., Inoue, S.: Summary of the cooking activity recognition challenge, pp. 1–13. Springer, Singapore (2021). https://doi.org/10.1007/978-981-15-8269-1_1
Damen, D., Doughty, H., Farinella, G.M., Fidler, S., Furnari, A., Kazakos, E., Moltisanti, D., Munro, J., Perrett, T., Price, W., Wray, M.: Scaling egocentric vision: the epic-kitchens dataset. In: European Conference on Computer Vision (ECCV) (2018)
Fabian Caba Heilbron Victor Escorcia, B.G., Niebles, J.C.: Activitynet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961–970 (2015)
Wikipedia: Bento—Wikipedia, the free encyclopedia. http://en.wikipedia.org/w/index.php?title=Bento&oldid=1040941536 (2021). Online; Accessed 11 Oct 2021
Motion Capture Company. http://motionanalysis.com/movement-analysis/
Yeasin Arafat Pritom Md. Sohanur Rahman, H.R.R.M.A.K., Ahad, M.A.R.: Lunch-box preparation activity understanding from mocap data using handcrafted features. In: Bento Packaging Activity Recognition Challenge
Adrita Anwar Malisha Islam Tapotee, P.S., Ahad, M.A.R.: Identification of food packaging activity using mocap sensor data. In: Bento Packaging Activity Recognition Challenge
Faizul Sayem Md. Mamun Sheikh, M.A.R.A.: Bento packaging activity recognition based on statistical features. In: Bento Packaging Activity Recognition Challenge
Promit Basak, A.H.M., Nazmus Sakib, S.M.T.S.D.U.M.A.R.A.: Can ensemble of classifiers provide better recognition results in packaging activity? In: Bento Packaging Activity Recognition Challenge
Jahir Ibna Rafiq Shamaun Nabi, A.A., Hossain, S.: Bento packaging activity recognition from motion capture data. In: Bento Packaging Activity Recognition Challenge
Björn Friedrich Tetchi Ange-Michel Orsot, A.H.: Using k-nearest-neighbours feature selection for activity recognition. In: Bento Packaging Activity Recognition Challenge
Fujii, A., Yoshida, K., K.S.K.M.: Bento packaging activity recognition with convolutional lstm using autocorrelation function and majority vote. In: Bento Packaging Activity Recognition Challenge
Powers, D.: Evaluation: from precision, recall and f-factor to roc, informedness, markedness & correlation. Mach. Learn. Technol. 2 (2008)
Alia, S.S., Lago, P., Adachi, K., Tahera Hossain, Goto, H., Okita, T., Inoue, S.: Summary of the 2nd nurse care activity recognition challenge using lab and field data. In: UbiComp/ISWC’20 Adjunct: ACM International Joint Conference on Pervasive and Ubiquitous Computing and ACM International Symposium on Wearable Computers. ACM (2020)
Alia, S.S., Lago, P., Takeda, S., Adachi, K., Benaissa, B., Ahad, M.A.R., Inoue, S.: Summary of the cooking activity recognition challenge. In: Human Activity Recognition Challenge. Springer, Berlin (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
See Table 3.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Adachi, K., Alia, S.S., Nahid, N., Kaneko, H., Lago, P., Inoue, S. (2022). Summary of the Bento Packaging Activity Recognition Challenge. In: Ahad, M.A.R., Inoue, S., Roggen, D., Fujinami, K. (eds) Sensor- and Video-Based Activity and Behavior Computing. Smart Innovation, Systems and Technologies, vol 291. Springer, Singapore. https://doi.org/10.1007/978-981-19-0361-8_17
Download citation
DOI: https://doi.org/10.1007/978-981-19-0361-8_17
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-0360-1
Online ISBN: 978-981-19-0361-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)