RGB cams vs RGB-D sensors: Low cost motion capture technologies performances and limitations

摘要: Motion capture of the human body has being performed for decades with a growing number technologies, aims and application fields; but only recent optical markerless technologies based on silhouette recognition depth sensors which have been developed videogames control interface brought motion to broad diffusion. Actually, nowadays there are low cost hardware software suitable wide range applications that may vary from entertainment domain (e.g., videogames, virtual characters in movies) biomechanical biomedical gait analysis or orthopedic rehabilitation) huge industrial sectors. In this quick evolving scenario it is hard tell technology most any desired goal. The aim paper answer issue by presenting benchmark compares RGB RGB-D used track performing people variety conditions. order contrast solutions, several different tasks selected, simultaneously captured post-processed exactly same way. test campaign designed evaluate pros cons according important feature technology, such as volume acquisition, accuracy joint position tracking fast movements. Actors were asked perform tasks, among free movements arms, legs full body, gait, interacting machine. around scene their disposition considered well. We Sony PS Eye cameras Microsoft Kinect solutions iPisoft data elaboration. gathered results organized, compared discussed stressing performances limitations combination and, at last, we proposed best candidate some key applications.