GUIDED BY

1
2-D Comparative Gait Kinematics Using a Single
Video Camera and EMG Signal Analysis

• GUIDED BY
• Mr. Chaitanya Srinivas L.V. Sujeet Blessing
• Assistant Professor 08MBE026
• SBST VIT University
• VIT University Vellore
• Vellore

2
SUMMARY OF WORK

• Acquisition and Processing of EMG for six
  subjects from nine muscles
• Stride analysis for six subjects
• Kinematics analysis for six subjects
• Marker based automated video-graphic analysis
• Marker-less automated video-graphic analysis

3
EMG ANALYSIS

• EMG acquisition
• EMG processing
• Linear envelope
• Normalization using Maximum Voluntary Contraction
• Wave rectification
• Butterworth low pass filter
• Integrated EMG
• Output from Low pass filter is passed through an
  integrator
• Root mean square

4
µ volts
µ volts
µ volts



Biceps Femoris
Vastus Medialis
Vastus Lateralis



µ volts
µ volts
µ volts

Semi Tendinosus
Rectus Femoris
Medial Gastrocnemius
µ volts
µ volts
µ volts
Lateral Gastrocnemius
Soleus
Tibialis Anterior
Linear envelope of EMG during one gait cycle
Normal
5
µ volts
µ volts
Muscles Medial gastrocnemius Lateral gastrocnemius Rectus femoris Vastus lateralis Vastus medialis Biceps Femoris Semi membranosus Soleus Tibialis Anterior
Average 102.7534 102.4169 69.4962 90.5123 100.0003 76.9286 147.1159 108.0622 163.433
6
STRIDE ANALYSIS

• Stride analysis Paper-Ink Method
• Step length, Stride length, Cadence, Stride
  width, Velocity, Foot progression angle

7
KINEMATIC ANALYSIS

• The motion of objects without consideration of
  the causes leading to the motion
• Determinants of position
• Active EMG
• Passive Force

8
MARKER TECHNIQUE

• Helen Hayes marker set
• Distance from Camera 9 feet
• Camera captures 25 frames/second
• Image processing
• Colour image to binary image
• Blob detection
• Drawing line, connecting respective markers
• Line and angle detection using Houghs transform

Pics
Results
9
MARKER-LESS TECHNIQUE

• Converting into silhouette video
• Extraction of the silhouette
• Segmenting leg into thigh, shin and foot using
  manual measurements
• Finding mid points of these segments, which
  serves as markers
• Correlating these markers with the un-segmented
  body
• Drawing lines connecting these markers
• Detecting lines and angles using Houghs
  transform

Pics
Results
10
Video
MARKER TECHNIQUE
Frame n
Colour image
Binary image
Blob detection
Draw lines
Draw lines
Houghs Transform
Houghs Transform
Hip angle
Knee angle
Video
11
Video (in RGB)
MARKER-LESS TECHNIQUE
Silhouette extraction
Frame n
Swing Phase Algorithm
Stance Phase Algorithm
Segmentation and Detection of Markers
Adjusting Leg Shortening using extraction
Drawing Lines
Segmentation and Detection of Markers
Angle Detection
Drawing Lines
Angle Detection
Video
12
COMPARISON

• Marker-less technique has a wide range of hip
  angle
• Knee flexion angle during heel strike is not
  clearly seen in marker-less technique, however,
  during swing phase, it has a good range

Normal
13
CONCLUSION

• Stride analysis was carried out using paper-ink
  method
• Emg was acquired from nine muscles from six
  subjects, processed and averaged
• Kinematic analysis was done on the same six
  subjects
• Marker and Marker-less automated video-graphic
  techniques were developed and the results were
  compared

14
REFERENCE

• Richard Baker, Gait analysis methods in
  rehabilitation, Journal of NeuroEngineering and
  Rehabilitation, 2006, 34.
• Mary M. Rodgers, Dynamic biomechanics of the
  normal foot and ankle during walking and
  running, Physical Therapy, 1988, 1822-30.
• Michela Goffredo, Imed Bouchrika, John N. Carter
  and Mark S. Nixon, Performance analysis for gait
  in camera networks, Association of Computing
  Machinery, 2008, 73-80.
• Y.P. Ivanenko, R.E. Poppele and F. Lacquaniti,
  Five basic muscle activation patterns account
  for muscle activity during human locomotion,
  American Journal of Physiology, 2004, 267-282.
• M.B.I. Reaz, M.S. Hussain and F. Mohd-Yasin,
  Techniques of EMG signal analysis Detection,
  processing, classification and applications,
  Biological Procedures, 2006, 8(1) 11-35.
• Noraxon EMG and Sensor System, Clinical SEMG
  Electrode Sites. www.noraxon.com.
• Helen Hayes Marker System, www.helenhayeshospital.
  org.

15
Queries???
16
THANK YOU.
17
Back
18
Back
19
MARKER BASED VIDEO-GRAPHIC TECHNIQUE
Back
HIP ANGLE
KNEE ANGLE
MARKER-LESS VIDEO-GRAPHIC TECHNIQUE
Back
HIP ANGLE
KNEE ANGLE
20
MUSCLES

• Lateral gastrocnemius, Medial gastrocnemius,
  Vastus lateralis, Vastus medialis, Rectus
  femoris, Biceps femoris, Semi tendinosus, Soleus,
  Tibialis anterior

Back
21
SOLEUS
LG
MG
TA
VL
RF
Back
VM
µ volts
BF
Stride
ST
Data Taken From Winter (1991)
Normal Hip Angle
Normal Knee Angle
Back
22
From Helen Hayes official website
Back
23

• a one frame of an original video b grey
  image c, d binary image e blob detection
  f for hip angle
• estimation g for knee angle estimation h
  detected lines by Houghs transform for hip
  angle
• i detected lines by Houghs transform for knee
  angle

Back
24
h
i
a Silhouette of a original frame b image
extracted from d negative image e
correlating the manual the hip c extracting
only the subject from the background
measurements with the pixel values f shin g
upper leg h drawing lines connecting the
markers i detected lines using Houghs
transform
BACK