Depth Images Processing Algorithm to Analyze and Correct in Real Time the Verticality of Multiple Sclerosis Patients during Exercise Gonzalo Eguiluz-Perez DeustoTech-Life Unit, DeustoTech Institute of Technology University of Deusto Bilbao 48007, Spain +34-94-413-90-03 geguiluz@deusto.es Begonya Garcia-Zapirain DeustoTech-Life Unit, DeustoTech Institute of Technology University of Deusto Bilbao 48007, Spain +34-94-413-90-03 mbgarciazapi@deusto.es ABSTRACT Any person with Multiple Sclerosis (MS), regardless of the severity of their disability, needs regular physical activity. Poorly performed exercises could aggravate muscle imbalances and worsen the patient’s health. In this paper, we propose a human body verticality detection system using a time-of-flight camera as a tool to detect incorrect postures and improve them in real time. The prototype uses a depth images processing algorithm to analyze and evaluate the position of patients during exercise. Preliminary results, based on a test with people without musculoskeletal problems and/or neurodegenerative diseases are promising and suggest that the system may be useful both for patients and medical professionals. Keywords Image processing, Time-of-flight, Verticality Improvement 1. INTRODUCTION Multiple sclerosis (MS) is a chronic inflammatory demyelinating disease (CIDD) of the central nervous system leading to progressive impairment of various Central Nervous System (CNS) [1] that poses many complications for the affected person; both physical and psychosocial. Patients with chronic disorders need to exercise and keep exercising continuously to improve their condition and motor skills. Rehabilitation is a comprehensive and continuous time-limited process with defined goals to promote and achieve optimal levels of physical independence and functional abilities of people with disabilities. It also envisages achieving the necessary psychological, social, vocational and economic levels so that they can lead an independent life. Rehabilitation based on video and multimedia applications, either web-based or stand-alone applications, tries to make the therapeutic process more attractive to the patient, increasing motivation and improving treatment efficacy [2–6]. These approaches incorporate an environment where the patient is able to work with an interactive application to perform the rehabilitation in an innovative way. Poorly performed exercises could aggravate muscle imbalances and worsen health. The way we sit, stand and walk has a long-term effect on the musculoskeletal system [7-9]. Poor posture can simply be a result of the adoption of bad movement habits over many years. When a joint works in an abnormal pattern, the ligaments can be stretched and the efficiency of the joint will be reduced. As the surfaces of the joint are not aligned correctly, this produces abnormal load- bearing on both joint and ligaments. The rehabilitation-associated improvements may also be capable of detecting incorrect movements/postures and provide sensorial and/or visual feedback to the patient and/or physiotherapist. In this project, we intend to address the following points: • To maintain the whole amplitude of the movement of joints and soft tissues, and to teach the patient and/or the relatives adequate tightening procedures to prevent contractures. • To make treatment techniques a part of everyday life, relating them with appropriate daily activities, ensuring maintenance of all the improvement obtained in this manner. • To analyze and evaluate in real-time the position of patients during the workout session to avoid unsatisfactory practices that may result in more severe muscle imbalances and worsen their health. The paper is organized as follows: first of all, the materials and methods section gives details of the experiment. System Design section describes the technological solution and the findings of the study are then presented in experiment results section, followed by a conclusion explanation. 2. MATERIALS AND METHODS 2.1 Materials EM (Multiple Sclerosis Basque Foundation Eugenia Epalza) created a set of exercises to perform the pilot test. These materials include pictures, both static and animated (n=70, approx. 63 MB) and videos (n=110, approx. 850 MB) focused on two main areas: Physiotherapy and Rehabilitation. Videos and images are used to teach the patients in how to perform their rehabilitation through exercises (n=166) developed by EM. Along with this, we developed a system (alpha version) which tracked the movement of patients and detected their position, in particular, the verticality of the patients’ trunk with a time-of-flight (ToF) camera. This system uses image processing algorithms, taking advantage of the depths images provided by the camera sensors. In order to achieve Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Conference’10, Month 1–2, 2010, City, State, Country. Copyright 2010 ACM 1-58113-000-0/00/0010 …$15.00. 3HUPLVVLRQ WR PDNH GLJLWDO RU KDUG FRSLHV RI DOO RU SDUW RI WKLV ZRUN IRU SHUVRQDO RU FODVVURRP XVH LV JUDQWHG ZLWKRXW IHH SURYLGHG WKDW FRSLHV DUH QRW PDGH RU GLVWULEXWHG IRU SURILW RU FRPPHUFLDO DGYDQWDJH DQG WKDW FRSLHV EHDU WKLV QRWLFH DQG WKH IXOO FLWDWLRQ RQ WKH ILUVW SDJH 7R FRS\ RWKHUZLVH WR UHSXEOLVK WR SRVW RQ VHUYHUV RU WR UHGLVWULEXWH WR OLVWV UHTXLUHV SULRU VSHFLILF SHUPLVVLRQ DQGRU D IHH 5(+$% 0D\ 2OGHQEXUJ *HUPDQ\ &RS\ULJKW k ,&67 '2, LFVWSHUYDVLYHKHDOWK