ABSTRACT
3D sensing hardware, such as the Microsoft Kinect, allows new interaction paradigms that would be difficult to accomplish with traditional RGB cameras alone. One basic step in realizing these new methods of animal-computer interaction is posture and behavior detection and classification. In this paper, we present a system capable of identifying static postures for canines that does not rely on hand-labeled data at any point during the process. We create a model of the canine based on measurements automatically obtained in from the first few captured frames, reducing the burden on users. We also present a preliminary evaluation of the system with five dogs, which shows that the system can identify the "standing," "sitting," and "lying" postures with approximately 70%, 69%, and 94% accuracy, respectively.
Supplemental Material
- Rita Brugarolas, David L. Roberts, Barbara Sherman, and Alper Bozkurt. 2013. Machine learning based posture estimation for a wireless canine machine interface. In Biomedical Wireless Technologies, Networks, and Sensing Systems (BioWireleSS), 2013 IEEE Topical Conference on. IEEE, 10--12.Google Scholar
- Melody Moore Jackson, Clint Zeagler, Giancarlo Valentin, Alex Martin, Vincent Martin, Adil Delawalla, Wendy Blount, Sarah Eiring, Ryan Hollis, Yash Kshirsagar, and others. 2013. FIDO-facilitating interactions for dogs with occupations: wearable dog-activated interfaces. In Proceedings of the International Symposium on Wearable Computers. ACM, 81--88. Google ScholarDigital Library
- Sean Mealin, Steven Howell, and David L. Roberts. 2016. Towards Unsupervised Canine Posture Classification via Depth Shadow Detection and Infrared Reconstruction for Improved Image Segmentation Accuracy. In Proceedings of The 5th International Conference on Biomimetic and Biohybrid Systems (LM 2016). Springer, 155--166.Google ScholarCross Ref
- Patricia Pons, Javier Jaén, and Alejandro Catalá. 2016. Detecting Animals' Body Postures Using Depth-Based Tracking Systems. In Animal Computer Interaction Symposia - Measuring Behavior.Google Scholar
- Michael Winters, Rita Brugarolas, John Majikes, Sean Mealin,, Sherrie Yuschak, Barbara Sherman, Alper Bozkurt, and David L. Roberts. 2015. Knowledge Engineering for Unsupervised Canine Posture Detection from IMU Data. In Proceedings of The Second International Congress on Animal Human Computer Interaction (ACI 2015) at the 12th International Conference on Advances in Computer Entertainment Technology (ACE 2015). Google ScholarDigital Library
- Mariko Yamamoto, Takefumi Kikusui, and Mitsuaki Ohta. 2009. Influence of delayed timing of owners' actions on the behaviors of their dogs, Canis familiaris. Journal of Veterinary Behavior: Clinical Applications and Research 4, 1 (2009), 11--18.Google ScholarCross Ref
Index Terms
- Semi-supervised classification of static canine postures using the Microsoft Kinect
Recommendations
Knowledge engineering for unsupervised canine posture detection from IMU data
ACE '15: Proceedings of the 12th International Conference on Advances in Computer Entertainment TechnologyTraining animals is a process that requires a significant investment of time and energy on the part of the trainer. One of the most basic training tasks is to train dogs to perform postures on cue. While it might be easy for a human trainer to see when ...
Semi-supervised multi-label classification using incomplete label information
Highlights- An inductive semi-supervised method called Smile is proposed for multi-label classification using incomplete label information.
AbstractClassifying multi-label instances using incompletely labeled instances is one of the fundamental tasks in multi-label learning. Most existing methods regard this task as supervised weak-label learning problem and assume sufficient ...
Semi-supervised document classification using heterogeneous rule selection
ICEC '17: Proceedings of the International Conference on Electronic CommerceIn traditional supervised classification, a large set of labeled data is required to train the model. However, labeled data are often hard to obtain and expensive, because human efforts are needed for the labeling. Therefore, semi-supervised learning ...
Comments