Home 3D-based visual physical activity assessment of children
Article Open Access

3D-based visual physical activity assessment of children

  • S. Maile EMAIL logo , S. Kobel , M. Munz , T. Engleder , J. M. Steinacker and F. Capanni
Published/Copyright: September 12, 2015

Abstract

In the last decades, an alarming rise in prevalence of childhood overweight and obesity has been observed which is partly attributed to a lack in physical activity and has started to become a public health concern. Therefore, the necessity for accurate physical activity assessment has become more and more apparent. Physical activity can be assessed objectively using accelerometers or combined devices. The application of such devices is sometimes complex and wearing the device may influence the behaviour of the test person. Therefore, assessment without any worn device would be an advantage.

A RGB-D camera device captures motion of the test person in a specific measurement area. After reducing the data and subtraction of the voxel distance, an activity level can be calculated.

The calculated activity level is similar to acceleration data of common monitoring devices. The calculated activity level is the sum of the person’s activity. Little activity with small movement can be differentiated from intense activity with large movement and high acceleration as well as no activity. The data can be structured in body-activity and limb-activity. Classifying those categories increases the benefit of this assessment compared to common accelerometers.

With the RGB-D based assessment objective, contextual information of different physical activity levels can be provided. Physical activity assessment without a worn device offers advantages such as the lack of manipulation of the device and its positioning, also the person’s compliance is no issue influencing the assessment. The RGB-D based assessment is similar to acceleration data and can be converted into comparable data and units after calibration. For more specific assessments a validation with accelerometers and the calibration of the derived data is necessary.

1 Introduction

In the last decades, an alarming rise in prevalence of childhood overweight and obesity has been observed which has started to become a public health concern [5]. Obesity often persists into adulthood [3] increasing children’s risk of developing non-communicable diseases such as type 2 diabetes and cardiovascular disease [2]. In recent years, the amount of people suffering from non-communicable diseases has risen continuously leading to the principal cause of death in the world [6]. Since a substantial amount of those diseases are attributed to a lack in physical activity, the necessity for objective and accurate physical activity assessment has become more and more apparent.

Up to now, accelerometers are an often used and well-established instrument for objective assessment of habitual physical activity in large samples under free-living conditions [4]. These devices register the intensity and duration of body acceleration. Hereby, energy expenditure is used as the main parameter to assess physical activity. Conclusions can be drawn based on where the accelerometer is positioned. Main issue – next to compliance and positioning of the device – is that accelerometers only record part of the relevant activities but not all bodily movement [1].

In order to avoid this, an improvement could be achieved by a system which recognises not just bodily movement but also offers contextual information (activity index) allowing a precise calculation of energy expenditure on basis of visual tracking.

1.1 Visual tracking and analysis

The here proposed visual tracking is based on an RGB-D camera device to trace a single person’s movements without any worn device for indoor measurement. The camera system has the ability to track the children’s position and calculate their activity.

During development, first the calculation algorithm is tested in a predefined measurement area, so the action area for each child is strictly limited. The movement in this measurement area is analysed, actions outside this area cannot be analysed (Figure 1).This restriction is necessary to enable a repeatable setup for the testing of the calculation algorithm. In a first test setup the scenario is limited to classroom conditions: indoor, nearly fixed positions, constant lightning and at most 5 persons in one camera filed. In the next steps, the child’s position is tracked and the action area is calculated around the child, so the action area becomes more and more moveable.

Figure 1 Tracking-Scenario in a classroom with children and teacher; here the child at the second desk is tracked and analyzed.
Figure 1

Tracking-Scenario in a classroom with children and teacher; here the child at the second desk is tracked and analyzed.

Figure 2 Activityframe as difference of two sequenced frames; black areas with a lot of activity, white areas with only small changes; activity index coded in gray scale from white to black; top-right – the RGB image of the analyzed person
Figure 2

Activityframe as difference of two sequenced frames; black areas with a lot of activity, white areas with only small changes; activity index coded in gray scale from white to black; top-right – the RGB image of the analyzed person

The analysis is solely based on the depth data of the RGD-D device. The produced depth data is an array of distance values, resulting in a frame of which each point accounts for the distance between the sensor. This can be visualized as a gray coded image (activity frame) where distances are mapped onto different gray levels.

2 Calculation of the activity level

The algorithm enables calculation of the assessed activity in a predefined measurement area, in order to calculate different physical activity levels. The measurement area is a fixed “region of interest” (ROI) and defined as a cuboid around every single child. In a later stage, the ROI will be automatically tracked and fixed to each child.

Largechanges are areas with high velocity or high dynamic. The activityframe (activityframe) is calculated with an element wise subtraction of depth values (Eq. 1).

(1)activityindex=1Ymax*XmaxYYmaxXXmaxactivityframe(x,y)

Calculation of the activity level is currently a postprocessing step. Firstly, the difference of two sequenced frames has to be calculated which leads to activity frames. One activity frame is shown in Figure 2: intense activity or large changes between two frames are then visible as high values (black), static objects become invisible (Figure 2).

2.1 Analyse of calculated activity level

The analysis of motion detection and the classification is based on the sum of all elements in the ROI. The resulting sum vector is the major element of the classification and allows a fast categorisation in three groups (no movement, small movement and intense movement – Figure 3).

Due to the standardisation to the defined measurement area a flexible transfer to other settings and measurement fields is achieved. The activity level is the sum vector of all motions in the measurement field around a centre point. The activity level does not offer any information about the position of the activity in the measurement field. To get the position additional small measurement fields have to be defined around one child.

3 Results

The simple analysis of the RGB-D data allows the classification of sequences without movements, small movements and intense movements. The activity index represents movements with contextual information; with more than one ROI it is possible to locate the movement. Small amplitudes in the activity graph reflect small or slow movements. Fast movements with high dynamic result into high amplitudes in the activity graph.

Figure 3 Sum of the activity in the measurement area; until 1.7 s just noise; after 1.7 s intense activity.
Figure 3

Sum of the activity in the measurement area; until 1.7 s just noise; after 1.7 s intense activity.

In a mixed scenario with phases of intense and small movements the algorithm can detect start and stopping point of the movements (Figure 7).

Figure 4 Scenario with no activity, just noise.
Figure 4

Scenario with no activity, just noise.

Figure 4 represents a situation with no activity; the small amplitudes are just noise from the sensor.

In a scenario with small activity amplitude the activity index is bigger than the noise, resulting in an irregular signal and a low activity (Figure 5).

Higher activity in the scene is shown as a signal with higher amplitudes and higher standard deviation (Figure 6). This makes it easy to differ these three groups of activities.

The developed algorithm can detect activity levels in a scenario (ROI) for one child without a worn device. Fast movements with high dynamic can be differentiated from slow movements.

Figure 5 Scenario with small activity.
Figure 5

Scenario with small activity.

Figure 6 Scenario with intense activity.
Figure 6

Scenario with intense activity.

For more detailed analyses more than one ROI has to be defined. For example, with two ROI a small body-ROI and a greater limb-ROI, the movement of the selected body part and the limbs can be analysed.

Figure 7 Mixedscenario without and with small activity.
Figure 7

Mixedscenario without and with small activity.

4 Conclusion

With the RGB-D based assessment, objective, contextual information of different physical activity levels can be provided. Physical activity assessment without a worn device offers advantages such as the lack of manipulation of the device and its positioning; also the person’s compliance is no issue influencing the assessment.

In further work a validation with accelerometers and the calibration of the derived data is necessary. The RGB-D based assessment seems to be qualitative similar to acceleration data. The acceleration sum data and the RGB-D based assessment have the same curve linearity and can be converted into comparable data and units after calibration.

Funding: The work was supported by the Ulm University of Applied Sciences.

Author’s Statement

  1. Conflict of interest: Authors state no conflict of interest. Material and Methods: Informed consent: Informed consent has been obtained from all individuals included in this study. Ethical approval: The research related to human use has been complied with all the relevant national regulations, institutional policies and in accordance the tenets of the Helsinki Declaration, and has been approved by the authors’ institutional review board or equivalent committee.

References

[1] Gabrys, L., Thiel, C., Tallner, A., Wilms, B., Müller, C., Kahlert, D., et al., Akzelerometrie zur Erfassung körperlicher Aktivität. Sportwissenschaft, 2014, 1-9.10.1007/s12662-014-0349-5Search in Google Scholar

[2] Lobstein, T., Baur, L., Uauy, R..Obesity in children and young people: a crisis in public health. Obesity reviews, 5(s1), 2004, 4-85.10.1111/j.1467-789X.2004.00133.xSearch in Google Scholar PubMed

[3] Singh, A. S., Mulder, C., Twisk, J. W., Van Mechelen, W., & Chinapaw, M. J.,Tracking of childhood overweight into adulthood: a systematic review of the literature. Obesity reviews, 2008, 9(5), 474-488.10.1111/j.1467-789X.2008.00475.xSearch in Google Scholar PubMed

[4] Troiano, R. P., McClain, J. J., Brychta, R. J., & Chen, K. Y. , Evolution of accelerometer methods for physical activity research. British journal of sports medicine, 2014, 48(13), 1019-1023.10.1136/bjsports-2014-093546Search in Google Scholar PubMed PubMed Central

[5] Waters, E., de Silva Sanigorski, A., Hall, B. J., Brown, T., Campbell, K. J., Gao, Y., Summerbell, C. D., Interventions for preventing obesity in children (review). Cochrane collaboration, 2011, (12), 1-212.10.1002/14651858.CD001871.pub3Search in Google Scholar PubMed

[6] WHO, Global status report on noncommunicable diseases 2014, 2014, Geneva (Switzerland)Search in Google Scholar

Published Online: 2015-9-12
Published in Print: 2015-9-1

© 2015 by Walter de Gruyter GmbH, Berlin/Boston

This article is distributed under the terms of the Creative Commons Attribution Non-Commercial License, which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

Articles in the same Issue

  1. Research Article
  2. Development and characterization of superparamagnetic coatings
  3. Research Article
  4. The development of an experimental setup to measure acousto-electric interaction signal
  5. Research Article
  6. Stability analysis of ferrofluids
  7. Research Article
  8. Investigation of endothelial growth using a sensors-integrated microfluidic system to simulate physiological barriers
  9. Research Article
  10. Energy harvesting for active implants: powering a ruminal pH-monitoring system
  11. Research Article
  12. New type of fluxgate magnetometer for the heart’s magnetic fields detection
  13. Research Article
  14. Field mapping of ballistic pressure pulse sources
  15. Research Article
  16. Development of a new homecare sleep monitor using body sounds and motion tracking
  17. Research Article
  18. Noise properties of textile, capacitive EEG electrodes
  19. Research Article
  20. Detecting phase singularities and rotor center trajectories based on the Hilbert transform of intraatrial electrograms in an atrial voxel model
  21. Research Article
  22. Spike sorting: the overlapping spikes challenge
  23. Research Article
  24. Separating the effect of respiration from the heart rate variability for cases of constant harmonic breathing
  25. Research Article
  26. Locating regions of arrhythmogenic substrate by analyzing the duration of triggered atrial activities
  27. Research Article
  28. Combining different ECG derived respiration tracking methods to create an optimal reconstruction of the breathing pattern
  29. Research Article
  30. Atrial and ventricular signal averaging electrocardiography in pacemaker and cardiac resynchronization therapy
  31. Research Article
  32. Estimation of a respiratory signal from a single-lead ECG using the 4th order central moments
  33. Research Article
  34. Compressed sensing of multi-lead ECG signals by compressive multiplexing
  35. Research Article
  36. Heart rate monitoring in ultra-high-field MRI using frequency information obtained from video signals of the human skin compared to electrocardiography and pulse oximetry
  37. Research Article
  38. Synchronization in wireless biomedical-sensor networks with Bluetooth Low Energy
  39. Research Article
  40. Automated classification of stages of anaesthesia by populations of evolutionary optimized fuzzy rules
  41. Research Article
  42. Effects of sampling rate on automated fatigue recognition in surface EMG signals
  43. Research Article
  44. Closed-loop transcranial alternating current stimulation of slow oscillations
  45. Research Article
  46. Cardiac index in atrio- and interventricular delay optimized cardiac resynchronization therapy and cardiac contractility modulation
  47. Research Article
  48. The role of expert evaluation for microsleep detection
  49. Research Article
  50. The impact of baseline wander removal techniques on the ST segment in simulated ischemic 12-lead ECGs
  51. Research Article
  52. Metal artifact reduction by projection replacements and non-local prior image integration
  53. Research Article
  54. A novel coaxial nozzle for in-process adjustment of electrospun scaffolds’ fiber diameter
  55. Research Article
  56. Processing of membranes for oxygenation using the Bellhouse-effect
  57. Research Article
  58. Inkjet printing of viable human dental follicle stem cells
  59. Research Article
  60. The use of an icebindingprotein out of the snowflea Hypogastrura harveyi as a cryoprotectant in the cryopreservation of mesenchymal stem cells
  61. Research Article
  62. New NIR spectroscopy based method to determine ischemia in vivo in liver – a first study on rats
  63. Research Article
  64. QRS and QT ventricular conduction times and permanent pacemaker therapy after transcatheter aortic valve implantation
  65. Research Article
  66. Adopting oculopressure tonometry as a transient in vivo rabbit glaucoma model
  67. Research Article
  68. Next-generation vision testing: the quick CSF
  69. Research Article
  70. Improving tactile sensation in laparoscopic surgery by overcoming size restrictions
  71. Research Article
  72. Design and control of a 3-DOF hydraulic driven surgical instrument
  73. Research Article
  74. Evaluation of endourological tools to improve the diagnosis and therapy of ureteral tumors – from model development to clinical application
  75. Research Article
  76. Frequency based assessment of surgical activities
  77. Research Article
  78. “Hands free for intervention”, a new approach for transoral endoscopic surgery
  79. Research Article
  80. Pseudo-haptic feedback in medical teleoperation
  81. Research Article
  82. Feasibility of interactive gesture control of a robotic microscope
  83. Research Article
  84. Towards structuring contextual information for workflow-driven surgical assistance functionalities
  85. Research Article
  86. Towards a framework for standardized semantic workflow modeling and management in the surgical domain
  87. Research Article
  88. Closed-loop approach for situation awareness of medical devices and operating room infrastructure
  89. Research Article
  90. Kinect based physiotherapy system for home use
  91. Research Article
  92. Evaluating the microsoft kinect skeleton joint tracking as a tool for home-based physiotherapy
  93. Research Article
  94. Integrating multimodal information for intraoperative assistance in neurosurgery
  95. Research Article
  96. Respiratory motion tracking using Microsoft’s Kinect v2 camera
  97. Research Article
  98. Using smart glasses for ultrasound diagnostics
  99. Research Article
  100. Measurement of needle susceptibility artifacts in magnetic resonance images
  101. Research Article
  102. Dimensionality reduction of medical image descriptors for multimodal image registration
  103. Research Article
  104. Experimental evaluation of different weighting schemes in magnetic particle imaging reconstruction
  105. Research Article
  106. Evaluation of CT capability for the detection of thin bone structures
  107. Research Article
  108. Towards contactless optical coherence elastography with acoustic tissue excitation
  109. Research Article
  110. Development and implementation of algorithms for automatic and robust measurement of the 2D:4D digit ratio using image data
  111. Research Article
  112. Automated high-throughput analysis of B cell spreading on immobilized antibodies with whole slide imaging
  113. Research Article
  114. Tissue segmentation from head MRI: a ground truth validation for feature-enhanced tracking
  115. Research Article
  116. Video tracking of swimming rodents on a reflective water surface
  117. Research Article
  118. MR imaging of model drug distribution in simulated vitreous
  119. Research Article
  120. Studying the extracellular contribution to the double wave vector diffusion-weighted signal
  121. Research Article
  122. Artifacts in field free line magnetic particle imaging in the presence of inhomogeneous and nonlinear magnetic fields
  123. Research Article
  124. Introducing a frequency-tunable magnetic particle spectrometer
  125. Research Article
  126. Imaging of aortic valve dynamics in 4D OCT
  127. Research Article
  128. Intravascular optical coherence tomography (OCT) as an additional tool for the assessment of stent structures
  129. Research Article
  130. Simple concept for a wide-field lensless digital holographic microscope using a laser diode
  131. Research Article
  132. Intraoperative identification of somato-sensory brain areas using optical imaging and standard RGB camera equipment – a feasibility study
  133. Research Article
  134. Respiratory surface motion measurement by Microsoft Kinect
  135. Research Article
  136. Improving image quality in EIT imaging by measurement of thorax excursion
  137. Research Article
  138. A clustering based dual model framework for EIT imaging: first experimental results
  139. Research Article
  140. Three-dimensional anisotropic regularization for limited angle tomography
  141. Research Article
  142. GPU-based real-time generation of large ultrasound volumes from freehand 3D sweeps
  143. Research Article
  144. Experimental computer tomograph
  145. Research Article
  146. US-tracked steered FUS in a respiratory ex vivo ovine liver phantom
  147. Research Article
  148. Contribution of brownian rotation and particle assembly polarisation to the particle response in magnetic particle spectrometry
  149. Research Article
  150. Preliminary investigations of magnetic modulated nanoparticles for microwave breast cancer detection
  151. Research Article
  152. Construction of a device for magnetic separation of superparamagnetic iron oxide nanoparticles
  153. Research Article
  154. An IHE-conform telecooperation platform supporting the treatment of dementia patients
  155. Research Article
  156. Automated respiratory therapy system based on the ARDSNet protocol with systemic perfusion control
  157. Research Article
  158. Identification of surgical instruments using UHF-RFID technology
  159. Research Article
  160. A generic concept for the development of model-guided clinical decision support systems
  161. Research Article
  162. Evaluation of local alterations in femoral bone mineral density measured via quantitative CT
  163. Research Article
  164. Creating 3D gelatin phantoms for experimental evaluation in biomedicine
  165. Research Article
  166. Influence of short-term fixation with mixed formalin or ethanol solution on the mechanical properties of human cortical bone
  167. Research Article
  168. Analysis of the release kinetics of surface-bound proteins via laser-induced fluorescence
  169. Research Article
  170. Tomographic particle image velocimetry of a water-jet for low volume harvesting of fat tissue for regenerative medicine
  171. Research Article
  172. Wireless medical sensors – context, robustness and safety
  173. Research Article
  174. Sequences for real-time magnetic particle imaging
  175. Research Article
  176. Speckle-based off-axis holographic detection for non-contact photoacoustic tomography
  177. Research Article
  178. A machine learning approach for planning valve-sparing aortic root reconstruction
  179. Research Article
  180. An in-ear pulse wave velocity measurement system using heart sounds as time reference
  181. Research Article
  182. Measuring different oxygenation levels in a blood perfusion model simulating the human head using NIRS
  183. Research Article
  184. Multisegmental fusion of the lumbar spine a curse or a blessing?
  185. Research Article
  186. Numerical analysis of the biomechanical complications accompanying the total hip replacement with NANOS-Prosthetic: bone remodelling and prosthesis migration
  187. Research Article
  188. A muscle model for hybrid muscle activation
  189. Research Article
  190. Mathematical, numerical and in-vitro investigation of cooling performance of an intra-carotid catheter for selective brain hypothermia
  191. Research Article
  192. An ideally parameterized unscented Kalman filter for the inverse problem of electrocardiography
  193. Research Article
  194. Interactive visualization of cardiac anatomy and atrial excitation for medical diagnosis and research
  195. Research Article
  196. Virtualizing clinical cases of atrial flutter in a fast marching simulation including conduction velocity and ablation scars
  197. Research Article
  198. Mesh structure-independent modeling of patient-specific atrial fiber orientation
  199. Research Article
  200. Accelerating mono-domain cardiac electrophysiology simulations using OpenCL
  201. Research Article
  202. Understanding the cellular mode of action of vernakalant using a computational model: answers and new questions
  203. Research Article
  204. A java based simulator with user interface to simulate ventilated patients
  205. Research Article
  206. Evaluation of an algorithm to choose between competing models of respiratory mechanics
  207. Research Article
  208. Numerical simulation of low-pulsation gerotor pumps for use in the pharmaceutical industry and in biomedicine
  209. Research Article
  210. Numerical and experimental flow analysis in centifluidic systems for rapid allergy screening tests
  211. Research Article
  212. Biomechanical parameter determination of scaffold-free cartilage constructs (SFCCs) with the hyperelastic material models Yeoh, Ogden and Demiray
  213. Research Article
  214. FPGA controlled artificial vascular system
  215. Research Article
  216. Simulation based investigation of source-detector configurations for non-invasive fetal pulse oximetry
  217. Research Article
  218. Test setup for characterizing the efficacy of embolic protection devices
  219. Research Article
  220. Impact of electrode geometry on force generation during functional electrical stimulation
  221. Research Article
  222. 3D-based visual physical activity assessment of children
  223. Research Article
  224. Realtime assessment of foot orientation by Accelerometers and Gyroscopes
  225. Research Article
  226. Image based reconstruction for cystoscopy
  227. Research Article
  228. Image guided surgery innovation with graduate students - a new lecture format
  229. Research Article
  230. Multichannel FES parameterization for controlling foot motion in paretic gait
  231. Research Article
  232. Smartphone supported upper limb prosthesis
  233. Research Article
  234. Use of quantitative tremor evaluation to enhance target selection during deep brain stimulation surgery for essential tremor
  235. Research Article
  236. Evaluation of adhesion promoters for Parylene C on gold metallization
  237. Research Article
  238. The influence of metallic ions from CoCr28Mo6 on the osteogenic differentiation and cytokine release of human osteoblasts
  239. Research Article
  240. Increasing the visibility of thin NITINOL vascular implants
  241. Research Article
  242. Possible reasons for early artificial bone failure in biomechanical tests of ankle arthrodesis systems
  243. Research Article
  244. Development of a bending test procedure for the characterization of flexible ECoG electrode arrays
  245. Research Article
  246. Tubular manipulators: a new concept for intracochlear positioning of an auditory prosthesis
  247. Research Article
  248. Investigation of the dynamic diameter deformation of vascular stents during fatigue testing with radial loading
  249. Research Article
  250. Electrospun vascular grafts with anti-kinking properties
  251. Research Article
  252. Integration of temperature sensors in polyimide-based thin-film electrode arrays
  253. Research Article
  254. Use cases and usability challenges for head-mounted displays in healthcare
  255. Research Article
  256. Device- and service profiles for integrated or systems based on open standards
  257. Research Article
  258. Risk management for medical devices in research projects
  259. Research Article
  260. Simulation of varying femoral attachment sites of medial patellofemoral ligament using a musculoskeletal multi-body model
  261. Research Article
  262. Does enhancing consciousness for strategic planning processes support the effectiveness of problem-based learning concepts in biomedical education?
  263. Research Article
  264. SPIO processing in macrophages for MPI: The breast cancer MPI-SNLB-concept
  265. Research Article
  266. Numerical simulations of airflow in the human pharynx of OSAHS patients
Downloaded on 11.9.2025 from https://www.degruyterbrill.com/document/doi/10.1515/cdbme-2015-0111/html
Scroll to top button