Human Motion Analysis and Simulation Tools: A Survey

Human Motion Analysis and Simulation Tools: A Survey

João F. Nunes (Instituto Politécnico de Viana do Castelo e Laboratório de Inteligência Artificial e Ciência dos Computadores da Universidade do Porto, Portugal), Pedro M. Moreira (Instituto Politécnico de Viana do Castelo e Laboratório de Inteligência Artificial e Ciência dos Computadores da Universidade do Porto, Portugal) and João Manuel R. S. Tavares (Instituto de Ciência e Inovação em Engenharia Mecânica e Engenharia Industrial, Departamento de Engenharia Mecânica, Faculdade de Engenharia, Universidade do Porto, Portugal)
DOI: 10.4018/978-1-4666-8823-0.ch012
OnDemand PDF Download:


Computational systems to identify objects represented in image sequences and tracking their motion in a fully automatic manner, enabling a detailed analysis of the involved motion and its simulation are extremely relevant in several fields of our society. In particular, the analysis and simulation of the human motion has a wide spectrum of relevant applications with a manifest social and economic impact. In fact, usage of human motion data is fundamental in a broad number of domains (e.g.: sports, rehabilitation, robotics, surveillance, gesture-based user interfaces, etc.). Consequently, many relevant engineering software applications have been developed with the purpose of analyzing and/or simulating the human motion. This chapter presents a detailed, broad and up to date survey on motion simulation and/or analysis software packages that have been developed either by the scientific community or commercial entities. Moreover, a main contribution of this chapter is an effective framework to classify and compare motion simulation and analysis tools.
Chapter Preview

Historical Perspective

Since the early days of science, the topic of motion analysis aroused a great interest in many researchers with different backgrounds, interests and motivations, like Hippocrates (460-370 BC), Aristotle (384-322 BC), Galen (129-217), Vesalius (1514-1564) and Galileo (1564-1642), among others. Leonardo Da Vinci (1452-1519) was the first to accurately depict the human adult spinal posture with its curvatures, articulations and number of vertebrae. He was particularly interested in the structure of the human body and how it relates to performance and also how to estimate its center of gravity and its balance. In his sketchbooks he stated that

is indispensable for a painter to become totally familiar with the anatomy of nerves, bones, muscles, and sinews, such that he understands for their various motions and stresses, which sinews or which muscle causes a particular motion.

Key Terms in this Chapter

(Computer) Simulation: Is fundamentally an imitation of a real process or system over time. The simulation process encompasses the design of a model of the system and conducting experiments in order to understand its behavior and performance under different conditions (variables).

EMG: Denoting Electromyography is a technique that is able to record the electrical activity of skeletal muscles. With EMG it is possible to analyze muscle properties such as activity, force, fatigue, etc.

Kinematics: Is the study of motion independently from the forces that produced that motion. It includes the study of geometrical and time based properties of motion such as position, velocity and acceleration.

RGB-D Camera (Depth Sensor): Are a specific type of depth sensing devices that work in association with a RGB camera, that are able to augment the conventional image with depth information (related with the distance to the sensor) in a per-pixel basis.

Real-Time: Refers to the ability that the system can process input and produce a result within a specified amount of time that should be small enough to be considered timeliness.

Data Fusion: Refers to a process of combining data, related to a same entity, acquired from multiple sources into an integrated representation, suitable for subsequent unified computational processing and analysis.

Kinetics: (Also referred as Dynamics) is the study of motion of bodies having mass and its relationship to its causes such as forces and torques.

Computer Vision: Is a discipline that studies methods and algorithms that are able to acquire, process and understand entities represented in images. The ultimate goal is to produce decisions and/or descriptions about the represented entities.

Machine Learning: Is a discipline that focuses on the study of algorithms that are able to learn from data and self-improve through experience.

Musculoskeletal Model: A computational model that encompasses a skeleton consisting in rigid body segments (bones) connected by joints. The skeleton may have several constraints (e.g.: maximum joint angles). Muscles spanning from joints are connected to bones via tendons. Muscles are able to generate forces and movement. These models are very useful on biomechanical analysis and simulation.

Complete Chapter List

Search this Book: