Silhouette Orientation Volumes for Efficient Fall Detection in Depth Videos

A novel method to detect human falls in depth videos is presented in this paper. A fast and robust shape sequence descriptor, namely the Silhouette Orientation Volume (SOV), is used to represent actions and classify falls. The SOV descriptor provides high classification accuracy even with a combination of simple associated models, such as Bag-of-Words and the Naïve Bayes classifier. Experiments on the public SDU-Fall dataset show that this new approach achieves up to 91.89% fall detection accuracy with a single-view depth camera. The classification rate is about 5% higher than the results reported in the literature. An overall accuracy of 89.63% was obtained for the six-class action recognition, which is about 25% higher than the state of the art. Moreover, a perfect silhouette-based action recognition rate of 100% is achieved on the Weizmann action dataset.

[1]  Chittaranjan A. Mandal,et al.  Automatic Detection of Human Fall in Video , 2007, PReMI.

[2]  Kejun Wang,et al.  Video-Based Abnormal Human Behavior Recognition—A Review , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[3]  Yun Li,et al.  A Microphone Array System for Automatic Fall Detection , 2012, IEEE Transactions on Biomedical Engineering.

[4]  Szu-Hao Huang,et al.  Learning-based Human Fall Detection using RGB-D cameras , 2013, MVA.

[5]  Marjorie Skubic,et al.  Fall Detection in Homes of Older Adults Using the Microsoft Kinect , 2015, IEEE Journal of Biomedical and Health Informatics.

[6]  Ronen Basri,et al.  Actions as space-time shapes , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[7]  Bogdan Kwolek,et al.  Fall detection using ceiling-mounted 3D depth camera , 2015, 2014 International Conference on Computer Vision Theory and Applications (VISAPP).

[8]  Ennio Gambi,et al.  A Depth-Based Fall Detection System Using a Kinect® Sensor , 2014, Sensors.

[9]  Haibo Wang,et al.  Depth-Based Human Fall Detection via Shape Features and Improved Extreme Learning Machine , 2014, IEEE Journal of Biomedical and Health Informatics.

[10]  Dimitrios Makris,et al.  Fall detection system using Kinect’s infrared sensor , 2014, Journal of Real-Time Image Processing.

[11]  Liang Liu,et al.  Automatic fall detection based on Doppler radar motion signature , 2011, 2011 5th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth) and Workshops.

[12]  Yaser Mowafi,et al.  Fall detection for elderly using anatomical-plane-based representation , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[13]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[14]  Yingli Tian,et al.  Privacy Preserving Automatic Fall Detection for Elderly Using RGBD Cameras , 2012, ICCHP.

[15]  Janusz Konrad,et al.  Action Recognition From Video Using Feature Covariance Matrices , 2013, IEEE Transactions on Image Processing.

[16]  R. Bajcsy,et al.  Wearable Sensors for Reliable Fall Detection , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[17]  Chenyang Zhang,et al.  RGB-D Camera-based Daily Living Activity Recognition , 2022 .

[18]  Erdem Akagündüz Shape recognition using orientational and morphological scale-spaces of curvatures , 2015, IET Comput. Vis..

[19]  Nadia Magnenat-Thalmann,et al.  Fall detection based on skeleton extraction , 2012, VRCAI '12.

[20]  François Charpillet,et al.  Automatic Fall Detection System with a RGB-D Camera using a Hidden Markov Model , 2013, ICOST.

[21]  Peter J. Rousseeuw,et al.  Clustering by means of medoids , 1987 .

[22]  Robert Marti,et al.  Which is the best way to organize/classify images by content? , 2007, Image Vis. Comput..

[23]  Nadia Magnenat-Thalmann,et al.  Fall Detection Based on Body Part Tracking Using a Depth Camera , 2015, IEEE Journal of Biomedical and Health Informatics.

[24]  Haibo Wang,et al.  Shape feature encoding via Fisher Vector for efficient fall detection in depth-videos , 2015, Appl. Soft Comput..