ABSTRACT
Human activity modeling and recognition using wearable sensors is important in pervasive healthcare, with applications including quantitative assessment of motor function, rehabilitation, and elder care. Previous human activity recognition techniques use a "whole-motion" model in which continuous sensor streams are divided into windows with a fixed time duration whose length is chosen such that all the relevant information in each activity signal can be extracted from each window. In this paper, we present a statistical motion primitive-based framework for human activity representation and recognition. Our framework is based on Bag-of-Features (BoF), which builds activity models using histograms of primitive symbols. We experimentally validate the effectiveness the BoF-based framework for recognizing nine activity classes and evaluate six factors which impact the performance of the framework. The factors include window size, choices of features, methods to construct motion primitives, motion vocabulary size, weighting schemes of motion primitive assignments, and learning machine kernel functions. Finally, we demonstrate that our statistical BoF-based framework can achieve much better performance compared to a non-statistical string-matching-based approach.
- Tâm Huynh and Bernt Schiele. Analyzing features for activity recognition. In Joint conference on Smart objects and ambient intelligence: innovative context-aware services: usages and technologies (sOc-EUSAI), pages 159--163, Grenoble, France, 2005. Google ScholarDigital Library
- Hassan Ghasemzadeh, Jaime Barnes, Eric Guenterberg, and Roozbeh Jafari. A phonological expression for physical movement monitoring in body sensor networks. In IEEE International Conference on Mobile Ad Hoc and Sensor Systems (MASS), pages 58--68, Atlanta, Georgia, USA, 2008.Google ScholarCross Ref
- Xuedong Huang, Alex Acero, and Hsiao-Wuen Hon. Spoken Language Processing: A Guide to Theory, Algorithm, and System Development. Prentice Hall PTR, Upper Saddle River, NJ, USA, 1st edition, 2001. Google ScholarDigital Library
- Richard O. Duda, Peter E. Hart, and David G. Stork. Pattern Classification. Wiley-Interscience, 2nd edition, November 2001.Google Scholar
- Preben Fihl, Michael B. Holte, Thomas B. Moeslund, and Lars Reng. Action recognition using motion primitives and probabilistic edit distance. In International Conference on Articulated Motion and Deformable Objects (AMDO), pages 375--384, Andratx, Mallorca, Spain, 2006. Google ScholarDigital Library
- Thomas Stiefmeier, Daniel Roggen, and Gerhard Tröster. Gestures are strings: efficient online gesture spotting and classification using string matching. In International Conference on Body Area Networks (BodyNets), pages 16:1--16:8, Florence, Italy, 2007. Google ScholarDigital Library
- Thomas Stiefmeier, Daniel Roggen, and Gerhard Tröster. Fusion of string-matched templates for continuous activity recognition. In IEEE International Symposium on Wearable Computers (ISWC), pages 1--4, Boston, MA, USA, 2007. Google ScholarDigital Library
- Hassan Ghasemzadeh, Vitali Loseu, and Roozbeh Jafari. Collaborative signal processing for action recognition in body sensor networks: a distributed classification algorithm using motion transcripts. In ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN), pages 244--255, Stockholm, Sweden, 2010. Google ScholarDigital Library
- Anil K. Jain, Robert P. W. Duin, and Jianchang Mao. Statistical pattern recognition: A review. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(1):4--37, 2000. Google ScholarDigital Library
- Jianguo Zhang, Marcin Marszalek, Svetlana Lazebnik, and Cordelia Schmid. Local features and kernels for classification of texture and object categories: A comprehensive study. International Journal of Computer Vision, 73:213--238, June 2007. Google ScholarDigital Library
- Ling Bao and Stephen S. Intille. Activity recognition from user-annotated acceleration data. In International Conference on Pervasive Computing, pages 1--17, Linz/Vienna, Austria, 2004.Google ScholarCross Ref
- Nishkam Ravi, Nikhil Dandekar, Prreetham Mysore, and Michael L. Littman. Activity recognition from accelerometer data. In Conference on Innovative Applications of Artificial Intelligence (IAAI), pages 1541--1546, Pittsburgh, Pennsylvania, USA, 2005. Google ScholarDigital Library
- Abdullah Mueen, Eamonn Keogh, and Neal Young. Logical-shapelets: an expressive primitive for time series classification. In ACM SIGKDD international conference on Knowledge discovery and data mining, pages 1154--1162, San Diego, California, USA, 2011. Google ScholarDigital Library
- http://www.motionnode.com.Google Scholar
- Tâm Huynh, Ulf Blanke, and Bernt Schiele. Scalable recognition of daily activities with wearable sensors. In International conference on Location-and context-awareness (LoCA), pages 50--67, Oberpfaffenhofen, Germany, 2007. Google ScholarDigital Library
- Andreas Krause, Daniel P. Siewiorek, Asim Smailagic, and Jonny Farringdon. Unsupervised, dynamic identification of physiological and activity context in wearable computing. In IEEE International Symposium Wearable Computers (ISWC), pages 88--97, White Plains, NY, USA, 2003. Google ScholarDigital Library
- Mi Zhang and Alexander A. Sawchuk. A feature selection-based framework for human activity recognition using wearable multimodal sensors. In International Conference on Body Area Networks (BodyNets), Beijing, China, November 2011. Google ScholarDigital Library
- Dean M. Karantonis, Michael R. Narayanan, Merryn Mathie, Nigel H. Lovell, and Branko G. Celler. Implementation of a Real-Time Human Movement Classifier Using a Triaxial Accelerometer for Ambulatory Monitoring. IEEE Transactions on Information Technology in Biomedicine, 10(1):156--167, 2006. Google ScholarDigital Library
- Chih-Chung Chang, Chih-Wei Hsu, and Chih-Jen Lin. A practical guide to support vector classification. Bioinformatics, 1(1):1--16, 2010.Google Scholar
- Vladimir N. Vapnik. The nature of statistical learning theory. Springer-Verlag New York, Inc., New York, NY, USA, 1995. Google ScholarDigital Library
Index Terms
- Motion primitive-based human activity recognition using a bag-of-features approach
Recommendations
A bag-of-features-based framework for human activity representation and recognition
SAGAware '11: Proceedings of the 2011 international workshop on Situation activity & goal awarenessHuman activity recognition using wearable sensors is an important topic in ubiquitous computing. In this paper, we present a statistical motion primitive-based framework for human activity representation and recognition. Our framework is based on Bag-of-...
A spanning tree-based human activity prediction system using life logs from depth silhouette-based human activity recognition
CAIP'11: Proceedings of the 14th international conference on Computer analysis of images and patterns - Volume Part IIn this work, we propose a Human Activity Prediction (HAP) system using activity sequence spanning trees constructed from a life-log created by a video sensor-based daily Human Activity Recognition (HAR) system using time-sequential Independent ...
View-invariant human activity recognition based on shape and motion features
Recognizing human activities from image sequences is an active area of research in computer vision. Most of the previous approaches on activity recognition focus on recognition from a single view and ignore the issue of view invariance, and they deal ...
Comments