GAIT RECOGNITION
USING INFRARED
WHAT IS
GAIT ?
 Gait is a behavioral
characteristics of a person.
 Recognition using gait means to
identify a person by the way he
move or walk.
 Human gait recognition works
from the observation that an
individual’s walking style is unique
and can be used for human
identification.
 It is a smart surveillance systems from security-
sensitive areas
Eg :-
 Banks - To alert security officers to a suspicious
individual or unknown individual wandering about
the premises.
 Parking Lots
 Airports
WHERE CANWE
USETHESE
FEATURE?
Other than the individual, that cause variations in gait,
including
 Footwear
 Terrain
 Fatigue
 injury
 Muscle development
 Training
 Personal idiosyncrasies
Injury Footwear
Terrain Fatigue
CHALLENGE
S
 The camera is static and the only motion within
the field of view is that of the moving person
 The subject is monitored by multiple cameras so
that the subject presents a side view to at least
one of the cameras.
ASSUMPTIO
N
Unlike a regular camera which records reflected visible
light, a long wave infrared camera records electromagnetic
radiation emitted by objects in a scene. So, human silhouettes
can be easily extracted from the background regardless of
lighting conditions and colors of the human surfaces and
backgrounds
WHYWE USE
INFRARED?
FIRST PHASE OF GAIT
RECOGNITION SYSTEM
Store feature in
Database
Target
frame
CASIA
images
BACKGROUND
SUBTRACTION
Background Image Original Image Extracted boundary
box
 Mean Intensity
 Height , width
FEATURE
EXTRACTION
Height
Width
Detection of height
and width of a frame
 Area
 Centroid
FEATURE
EXTRACTION
 Diameter
FEATURE
EXTRACTION
CASIA
images
Yes
SECOND PHASE OF
GAIT RECOGNITION
SYSTEM
No
DATA SET
Experiment was performed on different
datasets. This dataset is divided into 2 set, first
contains the video sequences frame feature
and second contains CASIA database frames
features as shown in table.
Each contains the silhouette and extracted
features from different person’s walking
frame. Experiments performed on Matlab.
EXPERIMENT AND
RESULT
Gait recognition is one kind of biometric
technology that can be used to monitor
people without their cooperation.
Controlled environments such as banks,
military installations and even airports
need to be able to quickly detect threats
and provide differing levels of access to
different user groups.
CONCLUSI
ON
 Khan,H. Rathore,y., “Study and Analysis of Human Gait to
Recognize thePerson” ,”India”, vol.2, pp., 2013.
 Liang Wang, Tieniu Tan. Huazhong Ning. and Weiming Hu., “
Silhouette Analysis-Based Gait
Recognition for Human Identification” IEEE Transaction on
PAMI, Vol.25, pp 1505-1518, 2003.
 Shaveta Chauhan et al., “Review On: GAIT RECOGNITION
USING BPNN & SVM”, International Journal of Computer
Application and Technology, pp. 63-67 ,2014.
 Daehee Kim. Seungwon Lee. and Jooki Paik ., “Active Shape
Model-Based Gait Recognition Using Infrared Images”,” Image
Processing and Intelligent Systems Laboratory, Graduate
School of Advanced Imaging Science, Multimedia, and Film,
Chung-Ang University, 221 Heuksuk-Dong, Dongjak-Ku, Seoul
156-756, Korea”, Vol. 2 ,2009.
REFERENC
ES
Gait Recognition Using Infrared
Gait Recognition Using Infrared

Gait Recognition Using Infrared

  • 1.
  • 2.
    WHAT IS GAIT ? Gait is a behavioral characteristics of a person.  Recognition using gait means to identify a person by the way he move or walk.  Human gait recognition works from the observation that an individual’s walking style is unique and can be used for human identification.
  • 3.
     It isa smart surveillance systems from security- sensitive areas Eg :-  Banks - To alert security officers to a suspicious individual or unknown individual wandering about the premises.  Parking Lots  Airports WHERE CANWE USETHESE FEATURE?
  • 4.
    Other than theindividual, that cause variations in gait, including  Footwear  Terrain  Fatigue  injury  Muscle development  Training  Personal idiosyncrasies Injury Footwear Terrain Fatigue CHALLENGE S
  • 5.
     The camerais static and the only motion within the field of view is that of the moving person  The subject is monitored by multiple cameras so that the subject presents a side view to at least one of the cameras. ASSUMPTIO N
  • 6.
    Unlike a regularcamera which records reflected visible light, a long wave infrared camera records electromagnetic radiation emitted by objects in a scene. So, human silhouettes can be easily extracted from the background regardless of lighting conditions and colors of the human surfaces and backgrounds WHYWE USE INFRARED?
  • 7.
    FIRST PHASE OFGAIT RECOGNITION SYSTEM Store feature in Database Target frame CASIA images
  • 8.
  • 9.
     Mean Intensity Height , width FEATURE EXTRACTION Height Width Detection of height and width of a frame
  • 10.
  • 11.
  • 12.
  • 13.
  • 14.
    Experiment was performedon different datasets. This dataset is divided into 2 set, first contains the video sequences frame feature and second contains CASIA database frames features as shown in table. Each contains the silhouette and extracted features from different person’s walking frame. Experiments performed on Matlab. EXPERIMENT AND RESULT
  • 15.
    Gait recognition isone kind of biometric technology that can be used to monitor people without their cooperation. Controlled environments such as banks, military installations and even airports need to be able to quickly detect threats and provide differing levels of access to different user groups. CONCLUSI ON
  • 16.
     Khan,H. Rathore,y.,“Study and Analysis of Human Gait to Recognize thePerson” ,”India”, vol.2, pp., 2013.  Liang Wang, Tieniu Tan. Huazhong Ning. and Weiming Hu., “ Silhouette Analysis-Based Gait Recognition for Human Identification” IEEE Transaction on PAMI, Vol.25, pp 1505-1518, 2003.  Shaveta Chauhan et al., “Review On: GAIT RECOGNITION USING BPNN & SVM”, International Journal of Computer Application and Technology, pp. 63-67 ,2014.  Daehee Kim. Seungwon Lee. and Jooki Paik ., “Active Shape Model-Based Gait Recognition Using Infrared Images”,” Image Processing and Intelligent Systems Laboratory, Graduate School of Advanced Imaging Science, Multimedia, and Film, Chung-Ang University, 221 Heuksuk-Dong, Dongjak-Ku, Seoul 156-756, Korea”, Vol. 2 ,2009. REFERENC ES