In this paper, we present a novel approach to recover a 3D human pose in real-time from a single depth image using principal direction analysis (PDA). Human body parts are first recognized from a human depth silhouette via trained random forests (RFs). PDA is applied to each recognized body part, which is presented as a set of points in 3D, to estimate its principal direction. Finally, a 3D human pose is recovered by mapping the principal direction to each body part of a 3D synthetic human model. We perform both quantitative and qualitative evaluations of our proposed 3D human pose recovering methodology. We show that our proposed approach has a low average reconstruction error of 7.07 degrees for four key joint angles and performs more reliably on a sequence of unconstrained poses than conventional methods. In addition, our methodology runs at a speed of 20 FPS on a standard PC, indicating that our system is suitable for real-time applications. Our 3D pose recovery methodology is applicable to applications ranging from human computer interactions to human activity recognition.

Human pose recognition has become an active research topic lately in the field of human computer interface (HCI).However it presents technical challenges due to the complexity of human motion.In this paper, we propose a novel methodology for human upper body pose recognition using labeled (i.e., recognized) human body parts in depth silhouettes.Our proposed method performs human upper body parts labeling using trained random forests (RFs) and utilizes support vector machines (SVMs) to recognize various upper body poses.To train RFs, we create a database of synthetic depth silhouettes of the upper body and their corresponding upper body parts labeled maps using a commercial computer graphics package.Once the body parts get labeled with the trained RFs, a skeletal upper body model is generated from the labeled body parts.Then, SVMs are trained with a set of joint angle features to recognize seven upper body poses.The experimental results show the mean recognition rate of 97.62%.Our proposed method should be useful as a near field HCI technique to be used in applications such as smart computer interfaces.

Human fall in the elderly population is one of the major causes of injury or bone fracture: it can be a cause of various injuries (e.g., fracture, concussion, and joint inflammation). It also could be a possible cause of death in a severe case. To detect human fall, various fall detection algorithms have been devised. Most fall detection algorithms rely on signals from a single accelerometer or gyroscope and use a threshold-based method to detect the human fall. However, these algorithms need careful adjustment of a threshold for each subject and cannot detect the direction of falls. In this study, we propose a novel fall recognition algorithm using a pair of a tri-axial accelerometer and a tri-axial gyroscope. Our fall recognition algorithm utilizes a set of augmented features including autoregressive (AR) modeling coefficients of signals, signal magnitude area (SMA), and gradients of angles from the sensors. After Linear Discriminant Analysis (LDA) of the augmented features, an Artificial Neural Nets (ANNs) is utilized to recognize four directional human falls: namely forward fall, backward fall, right-side fall, and left-side fall. Our recognition results show the mean recognition rate of 95.8%. Our proposed fall recognition technique should be useful in the investigation of fall-related injuries and possibly in the prevention of falls for the elderly.