Journal ArticleDOI
Support vector machine approach to fall recognition based on simplified expression of human skeleton action and fast detection of start key frame using torso angle
Reads0
Chats0
TLDR
A fall detection method for indoor environments based on the Kinect sensor and analysis of three-dimensional skeleton joints information is proposed and can be used in real-time video surveillance because of its time efficiency and robustness.Abstract:
Falls sustained by subjects can have severe consequences, especially for elderly persons living alone. A fall detection method for indoor environments based on the Kinect sensor and analysis of three-dimensional skeleton joints information is proposed. Compared with state-of-the-art methods, the authors' method provides two major improvements. First, possible fall activity is quantified and represented by a one-dimensional float array with only 32 items, followed by fall recognition using a support vector machine (SVM). Unlike typical deep learning methods, the input parameters of their method are dramatically reduced. Hence, videos are trained and recognised by an SVM with a low time cost. Second, the torso angle is imported to detect the start key frame of a possible fall, which is much more efficient than using a sliding window. Their approach is evaluated on the telecommunication systems team (TST) fall detection dataset v2. The results show that their approach achieves an accuracy of 92.05%, better than other typical methods. According to the characters of machine learning, when more samples are imported, their method is expected to achieve a higher accuracy and stronger capability of fall-like discrimination. It can be used in real-time video surveillance because of its time efficiency and robustness.read more
Citations
More filters
Posted Content
Video Based Fall Detection Using Human Poses
Ziwei Chen,Yiye Wang,Wankou Yang +2 more
TL;DR: Wang et al. as discussed by the authors proposed a video based fall detection approach using human poses, which achieved a high accuracy of 99.83% on large benchmark action recognition dataset NTU RGB+D and real-time performance of 18 FPS on a non-GPU platform and 63 FPS on GPU platform.
Fuzzy Support Vector Machine based Fall Detection Method for Traumatic Brain Injuries A New Systematic Approach of Combining Fuzzy Logic with Support Vector Machine to Achieve Higher Accuracy in Fall Detection System
TL;DR: In this paper , the authors propose a method to solve the problem of "missing links".http://www.ijacsa.thesai.org/index.cfm
References
More filters
Journal ArticleDOI
A survey on fall detection: Principles and approaches
TL;DR: A comprehensive survey of different systems for fall detection and their underlying algorithms is given, divided into three main categories: wearable device based, ambience device based and vision based.
Journal ArticleDOI
Fall detection system using Kinect's infrared sensor
TL;DR: A novel fall detection system based on the Kinect sensor that is capable of detecting walking falls accurately and robustly without taking into account any false positive activities (i.e. lying on the floor).
Journal ArticleDOI
A depth-based fall detection system using a Kinect® sensor.
TL;DR: An automatic, privacy-preserving, fall detection method for indoor environments, based on the usage of the Microsoft Kinect® depth sensor in an “on-ceiling” configuration, and on the analysis of depth frames, which shows the effectiveness of the proposed solution, even in complex scenarios.
Book ChapterDOI
Fall detection from depth map video sequences
TL;DR: An occlusion robust method is presented based on two features: human centroid height relative to the ground and body velocity, which is an efficient solution to detect falls as the vast majority of falls ends on the ground or near the ground.
Journal ArticleDOI
Space-Time Behavior-Based Correlation-OR-How to Tell If Two Underlying Motion Fields Are Similar Without Computing Them?
E. Shechtman,Michal Irani +1 more
TL;DR: A behavior-based similarity measure is introduced that tells us whether two different space-time intensity patterns of two different video segments could have resulted from a similar underlying motion field, thus allowing to correlate dynamic behaviors and actions.