A Survey of Human Action Recognition and Posture Prediction

Human action recognition and posture prediction aim to recognize and predict respectively the action and postures of persons in videos.They are both active research topics in computer vision community,which have attracted considerable attention from academia and industry.They are also the precondition for intelligent interaction and human-computer cooperation,and they help the machine perceive the external environment.In the past decade,tremendous progress has been made in the field,especially after the emergence of deep learning technologies.Hence,it is necessary to make a comprehensive review of recent developments.In this paper,firstly,we attempt to present the background,and then discuss research progresses.Secondly,we introduce datasets,various typical feature representation methods,and explore advanced human action recognition and posture prediction algorithms.Finally,facing the challenges in the field,this paper puts forward the research focus,and introduces the importance of action recognition and posture prediction by taking interactive cognition in self-driving vehicle as an example.

Real-Time Optimal Reach-Posture Prediction in a New Interactive Virtual Environment

Human posture prediction is a key factor for the design and evaluation of workspaces, in a virtual environment using virtual humans. This work presents a new interface and virtual environment for the direct human optimized posture prediction （D-HOPP） approach to predicting realistic reach postures of digital humans, where reach postures entail the use of the torso, arms, and neck. D-HOPP is based on the contention where depending on what type of task is being completed, and human posture is governed by different human performance measures. A human performance measure is a physics-based metric, such as energy or discomfort, and serves as an objective function in an optimization formulation. The problem is formulated as a single-objective optimization （SO0） problem with a single performance measure and as multiobjective-optimization （MOO） problem with multiple combined performance measures. We use joint displacement, change in potential energy, and musculoskeletal discomfort as performance measures. D-HOPP is equipped with an extensive yet intuitive user-interface, and the results are presented in an interactive virtual environment.

Simulation of the Interaction between Driver and Seat

Test is one of methods to acquire human-seat pressure distribution in driving, with the deficiency of being uneasy to obtain the stress information of soft tissue inside human body and the sheer force of interface between human and seat, which can be obtained by simulation. But current simulation method focuses mainly on calculation itself other than combining it with posture prediction and cab packaging parameters, which cause it difficult to acquire accurate pressure calculation results without accurate posture of human body, and make it almost meaningless to design optimization. Therefore, a human body geometric model with posture change capability is built and linked up with Cascade Prediction Model（CPM）, which takes cab packaging parameters as inputs. A detailed finite element model of driver human body is constructed and used to conduct the driver-seat interaction simulation between human body and seat. Good accordance of pressure distribution is observed between simulation and test, which validates the simulation. In addition to the distribution pattern, curves on key sections are used to analyze the pressure and shear stress on the seat surface, as well as soft tissue stress inside human body. The simulation shows that the maximum stress of buttocks locates under the ischial tuberosity, and the maximum stress of trunk occurs near the scapula posterior and the lower waist. These are the places where fatigue usually occurs. The maximum pressure of seat appears at the driver-seat contact area corresponding to the driver＇s maximum skin tissue stress. In order to guide the seat design and cab packaging and study the influence of posture to pressure distribution, finite element models for different levels of cab packaging parameters are created by using CPM. The pressure distributions are calculated and their tendencies varying with cab packaging parameters are obtained. The method presented provides a new way to accurately simulate the interaction between driver human body and seat, and to guide the seat design and cab packaging so as to improve seating comfort.