Human Fall Detection using Skeleton Features

Unintentional falls of people, when left without serve may cause severe injuries and in extreme cases, they may even lead to loss of lives. In order to provide timely medication, detection of fall events when occurred is necessary.Any action can be considered as the specific motion of various bone key points. So, in our work, we considered bone key points as feature extractors. The MediaPipe framework developed by Google is used to detect the bone key features and its coordinates on the human skeleton. The data obtained is then normalized with respect to the boundary box drawn around humans. Machine learning classifiers, RF, SVM and Deep Learning model, DNN are then used individually to recognise and classify the action into fall or non-fall events. NTU-RGB+D dataset is used in our work. Real time detection using a webcam is also tested. The accuracy achieved by DNN model is 97.63% and that of SVM and RF classifiers is 83.3% and 99.34% respectively. Thus, the highest accuracy is achieved by RF classifier which is 99.34%.

[1]  Mahesh D. Sawarbandhe,et al.  Suspicious Human Activity Detection Using Pose Estimation and LSTM , 2021, 2021 International Symposium of Asian Control Association on Intelligent Robotics and Industrial Automation (IRIA).

[2]  Guangzhe Zhao,et al.  Falling motion detection algorithm based on deep learning , 2021, IET Image Process..

[3]  C. Jyotsna,et al.  Deep Learning Approach for Suspicious Activity Detection from Surveillance Video , 2020, 2020 2nd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA).

[4]  Qingzhen Xu,et al.  Fall prediction based on key points of human bones , 2020 .

[5]  Sungjoo Kang,et al.  Human-skeleton based Fall-Detection Method using LSTM for Manufacturing Industries , 2019, 2019 34th International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC).

[6]  Ke Wang,et al.  Skeleton Based Fall Detection with Convolutional Neural Network , 2019, 2019 Chinese Control And Decision Conference (CCDC).

[7]  Jacques Demongeot,et al.  A Novel Monitoring System for Fall Detection in Older People , 2018, IEEE Access.

[8]  Jie Luo,et al.  Highly Portable, Sensor-Based System for Human Fall Monitoring , 2017, Sensors.

[9]  Abdelhamid Bouchachia,et al.  Activity recognition for indoor fall detection using convolutional neural network , 2017, 2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA).

[10]  Tao Xu,et al.  Fall prediction based on biomechanics equilibrium using Kinect , 2017, Int. J. Distributed Sens. Networks.

[11]  Bo Yao,et al.  A Big Bang–Big Crunch Type-2 Fuzzy Logic System for Machine-Vision-Based Event Detection and Summarization in Real-World Ambient-Assisted Living , 2016, IEEE Transactions on Fuzzy Systems.

[12]  Rahebeh Niaraki Asli,et al.  Recognition and Classification of Human Behavior in Intelligent Surveillance Systems using Hidden Markov Model , 2015 .

[13]  Turgay Tugay Bilgin,et al.  A data mining approach for fall detection by using k-nearest neighbour algorithm on wireless sensor network data , 2012, IET Commun..

[14]  Ehud Rivlin,et al.  Robust Real-Time Unusual Event Detection using Multiple Fixed-Location Monitors , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Carlos Vázquez,et al.  Real-time automatic detection of vandalism behavior in video sequences , 2007, 2007 IEEE International Conference on Systems, Man and Cybernetics.

[16]  G. Johansson.  Visual perception of biological motion and a model for its analysis , 1973 .

[17]  V. R. Satpute,et al.  Camera Handoff for Multi-camera Surveillance , 2021, Algorithms for Intelligent Systems.

[18]  Ashvini Chaturvedi,et al.  Wearable Sensor-Based Human Fall Detection Wireless System , 2019 .

[19]  Sarita Chaudhary,et al.  Multiple Anomalous Activity Detection in Videos , 2018 .

[20]  Viacheslav V. Voronin,et al.  Classification of a two-dimensional pose using a human skeleton , 2017 .

[21]  Kishore Kulat,et al.  Real-Time Abandoned Object Detection Using Video Surveillance , 2016 .

[22]  Vikas Tripathi,et al.  Robust Abnormal Event Recognition via Motion and Shape Analysis at ATM Installations , 2015, J. Electr. Comput. Eng..

[23]  C. Todd,et al.  World Health Organisation Global Report on Falls Prevention in Older Age , 2007 .