SlideShare a Scribd company logo
Prince of Songkhla University   Department of Computer Engineering



24th JCAART’09 Conference
     Vision-based Fall Detection and
   Alert System Suitable for the Elderly
          and Disabled Peoples

   Teerasak Kroputaponchai and Dr. Nikom Suvonvorn

     Presented by Assoc. Prof. Dr. Pornchai Phukpattaranont



                        Faculty of Engineering
                Prince of Songkla University, Thailand

    Teerasak Kroputaponchai and Nikom SUVONVORN       August 26-28, 24th JCAART 2009 Conference
Prince of Songkhla University   Department of Computer Engineering


Outline

   •   Problem statement
   •   System Overview
   •   Motion detection and tracking
   •   Features extraction
   •   Fall analysis and detection
   •   Result and discussion
   •   Conclusion and future work



       Teerasak Kroputaponchai and Nikom SUVONVORN       August 26-28, 24th JCAART 2009 Conference
Prince of Songkhla University   Department of Computer Engineering


Problem statement

 • Falls event amongst the elderly are particularly
   serious and often lead to injury or death



 • Automatic monitoring of the activities of daily living
   (ADL) and falls event for the elderly and disabled
   people using image sequences analysis leads to the
   immediate or preventive intervention.


     Teerasak Kroputaponchai and Nikom SUVONVORN       August 26-28, 24th JCAART 2009 Conference
Prince of Songkhla University   Department of Computer Engineering


System overview
Motion detection
                                              Features extraction




                                                                                    Fall detection

                 Motion Tracking
     Teerasak Kroputaponchai and Nikom SUVONVORN       August 26-28, 24th JCAART 2009 Conference
Prince of Songkhla University   Department of Computer Engineering


Motion detection
 • Use background subtraction technique
   – Running Average with selectivity
                      ⎧αFi ( x, y ) + (1 − α ) Bi ( x, y ) if                     Fi ( x, y ) is background
     Bi +1 ( x, y ) = ⎨
                      ⎩                   Bi ( x, y )     else

                      ⎧255 if              Bi ( x, y ) − Fi ( x, y ) < τ
     Oi +1 ( x, y ) = ⎨
                      ⎩                    0 else

 • Morphological operation
   – Opening and Closing
   – Noise suppression

     Teerasak Kroputaponchai and Nikom SUVONVORN       August 26-28, 24th JCAART 2009 Conference
Prince of Songkhla University   Department of Computer Engineering


Motion segmentation
 • Spatial-based region-fusion operation
   – Two regions are the same object if they are overlapped or
     their distance less than a specific threshold




   – Very sensible to light condition : shadow, contrast
     changing and sudden changes of light

     Teerasak Kroputaponchai and Nikom SUVONVORN       August 26-28, 24th JCAART 2009 Conference
Prince of Songkhla University   Department of Computer Engineering


Motion segmentation on tracking
 • Texture-based region-fusion during tracking process
    – the color probability density of object’s texture is
      additionally applied as a similarity measurement between
      regions
    – Mixture motion-texture model can reduce noises and
      increases significantly the effectiveness of algorithm




  (a) Image sequence      (b) motion detection            (c) texture detection     (d) mixture of motion-texture


       Teerasak Kroputaponchai and Nikom SUVONVORN       August 26-28, 24th JCAART 2009 Conference
Prince of Songkhla University   Department of Computer Engineering


Motion tracking by Mean-shift
 • Mean-shift tracking
   – Iterative procedure that shifts pixel’s intensity to the
     average of its neighborhood on the color probability
     density.
 • Multiple-regions tracking
   – Upper body and Lower body parts




     Teerasak Kroputaponchai and Nikom SUVONVORN       August 26-28, 24th JCAART 2009 Conference
Prince of Songkhla University   Department of Computer Engineering


Features extraction
 • Object (Human?) characteristics
   – Width and Height of object region
   – Angle between y-axis and horizontal line
      • Object principle axis is calculated from region moment
   – Speed of the extremity points of y-axis
      • Computed as the ratio of moving distance between frames and
        time


                     θ                                                             H



                                                                           W




     Teerasak Kroputaponchai and Nikom SUVONVORN         August 26-28, 24th JCAART 2009 Conference
Prince of Songkhla University   Department of Computer Engineering


Features extraction
 • Noises suppression
   – Noisy features obtained from non-perfect tracking process
 • Butterworth low-pass filter
   – To consider the fall characteristic factors : the frequency
     cut must higher than the fall frequencies (0.4s-0.8s)
   – Kernel parameters is 1/22 [1/6, 1/2, 1/1.06, 1, 1/1.06, 1/2, 1/6]
   – Apply to the five features…




     Teerasak Kroputaponchai and Nikom SUVONVORN       August 26-28, 24th JCAART 2009 Conference
Prince of Songkhla University   Department of Computer Engineering


Features to fall analysis
                                            (a)                     Fall                           (b)
       Fall                                                                  Lie



                 Lie




        Fall                                (c)

               Lie



                                                        (a) Angle
                                                        (b) Width and Height
                                                        (c) Speed of extremity points
    Teerasak Kroputaponchai and Nikom SUVONVORN        August 26-28, 24th JCAART 2009 Conference
Prince of Songkhla University    Department of Computer Engineering


Fall detection
 • Expert and Rules based decision
           Fall detection

                                                                Yes



                                                                                Yes
                                                      Yes




                                                                             Lie detection

                      H = Height                       W = Width
                       t = Time                         V = Speed
                      delta = Fall angle

    Teerasak Kroputaponchai and Nikom SUVONVORN        August 26-28, 24th JCAART 2009 Conference
Prince of Songkhla University   Department of Computer Engineering


Result and discussion
 • Dataset
   – 15 Fall datasets was done in a indoor situation using
     volunteers
 • Result
               T-Shirt           Pants            Image              Fall           False
                Color            Color          Sequences          Detection       positives

              Orange              Blue                   5            80%               1

               White              Blue                   5            60%               2

               Green             White                   5            80%               1


      • Most false positives is caused by non-perfect motion detection
        and tracking process.

     Teerasak Kroputaponchai and Nikom SUVONVORN         August 26-28, 24th JCAART 2009 Conference
Prince of Songkhla University   Department of Computer Engineering


Result and discussion
 • Demo




    Teerasak Kroputaponchai and Nikom SUVONVORN       August 26-28, 24th JCAART 2009 Conference
Prince of Songkhla University   Department of Computer Engineering


Result and discussion
 • Error




     Teerasak Kroputaponchai and Nikom SUVONVORN       August 26-28, 24th JCAART 2009 Conference
Prince of Songkhla University   Department of Computer Engineering


Future work

 • Improve the motion and tracking method

 • Improve human
   modeling


 • Decision method
   – Decision rules                by          the expert
                  to               by          supervised learning

    Teerasak Kroputaponchai and Nikom SUVONVORN       August 26-28, 24th JCAART 2009 Conference
Prince of Songkhla University   Department of Computer Engineering


References
 •   G. Perolle, P. Fraisse, M. Mavros and I. Etxeberria. , “Automatic Fall Detection and Activity
     Monitoring for Elderly,” In Proceedings of MEDETEL, 2006.
 •   Chia-Wen Lin and Zhi-Hong Ling., “Automatic Fall Incident Detection in Compressed Video for
     Intelligent Homecare,” Computer Communications and Networks 2007, pp.1172 – 1177,2007.
 •   R. C. Gonzalez and R. E. Woods, Digital Image Processing, Prentice Hall, (2nd Edition) 2002.
 •   W. Hu, T. Tan, L. Wang, and S. Maybank, “A survey on visual surveillance of object motion
     and behavior,” IEEE trans. Systems, Man, and Cybernetics- Part C: Applications and Reviews,
     vol. 38, no. 3, pp.334-352, Aug. 2004.
 •    R. Cucchiara, A. Prati and R. Vezzani “A Multi-Camera Vision system for Fall Detection and
     Alarm Generation,” Expert Systems Journal , vol. 5 , Blackwell Publishing. 2007.
 •   J. K. Aggarwai, Q. Cai, “Human Motion Analysis: A review,” Computer Vision and Image
     Understanding, Vol. 73, pp.428-440,1999
 •    M. Piccardi, “Background subtraction techniques: a review”, in Proc. of IEEE SMC 2004
     International Conference on Systems, Man and Cybernetics, The Hague, The Netherlands,
     October 2004.


                                    Thanks you
         Teerasak Kroputaponchai and Nikom SUVONVORN       August 26-28, 24th JCAART 2009 Conference

More Related Content

Viewers also liked

smartphone enabled intelligent surveillance system
smartphone enabled intelligent surveillance systemsmartphone enabled intelligent surveillance system
smartphone enabled intelligent surveillance system
Syam Suresh
 
Fall Prevention AgeTech Call 1 28 10
Fall Prevention AgeTech Call 1 28 10Fall Prevention AgeTech Call 1 28 10
Fall Prevention AgeTech Call 1 28 10
Laura Mitchell
 
Valdovinos presentation sp13_no_video
Valdovinos presentation sp13_no_videoValdovinos presentation sp13_no_video
Valdovinos presentation sp13_no_video
valdo3333
 
Fall detection slideshow
Fall detection slideshowFall detection slideshow
Fall detection slideshow
anilramnanan
 
Fall Detection Technology Verhaert
Fall Detection Technology VerhaertFall Detection Technology Verhaert
Fall Detection Technology Verhaert
Verhaert Masters in Innovation
 
Fall detection
Fall detectionFall detection
Fall detection
Lippo Group Digital
 
SensorBand
SensorBandSensorBand
SensorBand
Fundació TicSalut
 
Fall Detection System for the Elderly based on the Classification of Shimmer ...
Fall Detection System for the Elderly based on the Classification of Shimmer ...Fall Detection System for the Elderly based on the Classification of Shimmer ...
Fall Detection System for the Elderly based on the Classification of Shimmer ...
Moiz Ahmed
 

Viewers also liked (8)

smartphone enabled intelligent surveillance system
smartphone enabled intelligent surveillance systemsmartphone enabled intelligent surveillance system
smartphone enabled intelligent surveillance system
 
Fall Prevention AgeTech Call 1 28 10
Fall Prevention AgeTech Call 1 28 10Fall Prevention AgeTech Call 1 28 10
Fall Prevention AgeTech Call 1 28 10
 
Valdovinos presentation sp13_no_video
Valdovinos presentation sp13_no_videoValdovinos presentation sp13_no_video
Valdovinos presentation sp13_no_video
 
Fall detection slideshow
Fall detection slideshowFall detection slideshow
Fall detection slideshow
 
Fall Detection Technology Verhaert
Fall Detection Technology VerhaertFall Detection Technology Verhaert
Fall Detection Technology Verhaert
 
Fall detection
Fall detectionFall detection
Fall detection
 
SensorBand
SensorBandSensorBand
SensorBand
 
Fall Detection System for the Elderly based on the Classification of Shimmer ...
Fall Detection System for the Elderly based on the Classification of Shimmer ...Fall Detection System for the Elderly based on the Classification of Shimmer ...
Fall Detection System for the Elderly based on the Classification of Shimmer ...
 

Similar to 24th JCAART 2009 Conference

UNIT 4.ppt
UNIT 4.pptUNIT 4.ppt
UNIT 4.ppt
VIJAYAN S N
 
Automatic reading cr39
Automatic reading cr39Automatic reading cr39
Automatic reading cr39
MOAYYAD ALSSABBAGH
 
Computed Radiography and Computed Tomography
Computed Radiography and Computed TomographyComputed Radiography and Computed Tomography
Computed Radiography and Computed Tomography
karthi keyan
 
Plane wave decomposition and beamforming for directional spatial sound locali...
Plane wave decomposition and beamforming for directional spatial sound locali...Plane wave decomposition and beamforming for directional spatial sound locali...
Plane wave decomposition and beamforming for directional spatial sound locali...
Muhammad Imran
 
Computer Based Free Vibration Analysis of Isotropic Thin Rectangular Flat CCC...
Computer Based Free Vibration Analysis of Isotropic Thin Rectangular Flat CCC...Computer Based Free Vibration Analysis of Isotropic Thin Rectangular Flat CCC...
Computer Based Free Vibration Analysis of Isotropic Thin Rectangular Flat CCC...
theijes
 
phase2 FINAL
phase2 FINALphase2 FINAL
phase2 FINAL
Ashok Sharma
 
ncp
ncpncp
Part 1 presentation 1
Part 1 presentation 1Part 1 presentation 1
Part 1 presentation 1
Gaye Aktürk
 
CE 72.32 (January 2016 Semester): Lecture 1b: Analysis and Design of Tall Bui...
CE 72.32 (January 2016 Semester): Lecture 1b: Analysis and Design of Tall Bui...CE 72.32 (January 2016 Semester): Lecture 1b: Analysis and Design of Tall Bui...
CE 72.32 (January 2016 Semester): Lecture 1b: Analysis and Design of Tall Bui...
Fawad Najam
 
RETRIEVAL OF ATMOSPHERIC BOUNDARY LAYER HEIGHT BY CSIR-NLC MOBILE LIDAR, PRET...
RETRIEVAL OF ATMOSPHERIC BOUNDARY LAYER HEIGHT BY CSIR-NLC MOBILE LIDAR, PRET...RETRIEVAL OF ATMOSPHERIC BOUNDARY LAYER HEIGHT BY CSIR-NLC MOBILE LIDAR, PRET...
RETRIEVAL OF ATMOSPHERIC BOUNDARY LAYER HEIGHT BY CSIR-NLC MOBILE LIDAR, PRET...
grssieee
 
Automated Motion Detection from space in sea surveillance
Automated Motion Detection from space in sea surveillanceAutomated Motion Detection from space in sea surveillance
Automated Motion Detection from space in sea surveillance
Liza Charalambous
 
Space Science Technology and Applications at CPUT By Prof Robert van Zyl
Space Science Technology and Applications at CPUT By Prof Robert van ZylSpace Science Technology and Applications at CPUT By Prof Robert van Zyl
Space Science Technology and Applications at CPUT By Prof Robert van Zyl
Polytechnic of Namibia
 
Yanjun Chen_1017_English Version
Yanjun Chen_1017_English VersionYanjun Chen_1017_English Version
Yanjun Chen_1017_English Version
Yanjun Chen
 
All-polymer based fabrication process for an all-polymer flexible and paralle...
All-polymer based fabrication process for an all-polymer flexible and paralle...All-polymer based fabrication process for an all-polymer flexible and paralle...
All-polymer based fabrication process for an all-polymer flexible and paralle...
Jilin Yang
 
Joe Kelleher Presentation (May 27th 2014)
Joe Kelleher Presentation (May 27th 2014)Joe Kelleher Presentation (May 27th 2014)
Joe Kelleher Presentation (May 27th 2014)
Roadshow2014
 
Geospatial Research At UCL
Geospatial Research At UCLGeospatial Research At UCL
Geospatial Research At UCL
Jeremy Morley
 
Approaches of nanoelectronics
Approaches of nanoelectronicsApproaches of nanoelectronics
Approaches of nanoelectronics
Aravinth Dhanasekaran
 
Whispers of Speckles ( Part I: Building Computational Imaging Frameworks for ...
Whispers of Speckles (Part I: Building Computational Imaging Frameworks for ...Whispers of Speckles (Part I: Building Computational Imaging Frameworks for ...
Whispers of Speckles ( Part I: Building Computational Imaging Frameworks for ...
Debdoot Sheet
 
A new Compton scattered tomography modality and its application to material n...
A new Compton scattered tomography modality and its application to material n...A new Compton scattered tomography modality and its application to material n...
A new Compton scattered tomography modality and its application to material n...
irjes
 
Reliable Positioning with Hybrid Antenna Model for Aerial Wireless Sensor and...
Reliable Positioning with Hybrid Antenna Model for Aerial Wireless Sensor and...Reliable Positioning with Hybrid Antenna Model for Aerial Wireless Sensor and...
Reliable Positioning with Hybrid Antenna Model for Aerial Wireless Sensor and...
M. Ilhan Akbas
 

Similar to 24th JCAART 2009 Conference (20)

UNIT 4.ppt
UNIT 4.pptUNIT 4.ppt
UNIT 4.ppt
 
Automatic reading cr39
Automatic reading cr39Automatic reading cr39
Automatic reading cr39
 
Computed Radiography and Computed Tomography
Computed Radiography and Computed TomographyComputed Radiography and Computed Tomography
Computed Radiography and Computed Tomography
 
Plane wave decomposition and beamforming for directional spatial sound locali...
Plane wave decomposition and beamforming for directional spatial sound locali...Plane wave decomposition and beamforming for directional spatial sound locali...
Plane wave decomposition and beamforming for directional spatial sound locali...
 
Computer Based Free Vibration Analysis of Isotropic Thin Rectangular Flat CCC...
Computer Based Free Vibration Analysis of Isotropic Thin Rectangular Flat CCC...Computer Based Free Vibration Analysis of Isotropic Thin Rectangular Flat CCC...
Computer Based Free Vibration Analysis of Isotropic Thin Rectangular Flat CCC...
 
phase2 FINAL
phase2 FINALphase2 FINAL
phase2 FINAL
 
ncp
ncpncp
ncp
 
Part 1 presentation 1
Part 1 presentation 1Part 1 presentation 1
Part 1 presentation 1
 
CE 72.32 (January 2016 Semester): Lecture 1b: Analysis and Design of Tall Bui...
CE 72.32 (January 2016 Semester): Lecture 1b: Analysis and Design of Tall Bui...CE 72.32 (January 2016 Semester): Lecture 1b: Analysis and Design of Tall Bui...
CE 72.32 (January 2016 Semester): Lecture 1b: Analysis and Design of Tall Bui...
 
RETRIEVAL OF ATMOSPHERIC BOUNDARY LAYER HEIGHT BY CSIR-NLC MOBILE LIDAR, PRET...
RETRIEVAL OF ATMOSPHERIC BOUNDARY LAYER HEIGHT BY CSIR-NLC MOBILE LIDAR, PRET...RETRIEVAL OF ATMOSPHERIC BOUNDARY LAYER HEIGHT BY CSIR-NLC MOBILE LIDAR, PRET...
RETRIEVAL OF ATMOSPHERIC BOUNDARY LAYER HEIGHT BY CSIR-NLC MOBILE LIDAR, PRET...
 
Automated Motion Detection from space in sea surveillance
Automated Motion Detection from space in sea surveillanceAutomated Motion Detection from space in sea surveillance
Automated Motion Detection from space in sea surveillance
 
Space Science Technology and Applications at CPUT By Prof Robert van Zyl
Space Science Technology and Applications at CPUT By Prof Robert van ZylSpace Science Technology and Applications at CPUT By Prof Robert van Zyl
Space Science Technology and Applications at CPUT By Prof Robert van Zyl
 
Yanjun Chen_1017_English Version
Yanjun Chen_1017_English VersionYanjun Chen_1017_English Version
Yanjun Chen_1017_English Version
 
All-polymer based fabrication process for an all-polymer flexible and paralle...
All-polymer based fabrication process for an all-polymer flexible and paralle...All-polymer based fabrication process for an all-polymer flexible and paralle...
All-polymer based fabrication process for an all-polymer flexible and paralle...
 
Joe Kelleher Presentation (May 27th 2014)
Joe Kelleher Presentation (May 27th 2014)Joe Kelleher Presentation (May 27th 2014)
Joe Kelleher Presentation (May 27th 2014)
 
Geospatial Research At UCL
Geospatial Research At UCLGeospatial Research At UCL
Geospatial Research At UCL
 
Approaches of nanoelectronics
Approaches of nanoelectronicsApproaches of nanoelectronics
Approaches of nanoelectronics
 
Whispers of Speckles ( Part I: Building Computational Imaging Frameworks for ...
Whispers of Speckles (Part I: Building Computational Imaging Frameworks for ...Whispers of Speckles (Part I: Building Computational Imaging Frameworks for ...
Whispers of Speckles ( Part I: Building Computational Imaging Frameworks for ...
 
A new Compton scattered tomography modality and its application to material n...
A new Compton scattered tomography modality and its application to material n...A new Compton scattered tomography modality and its application to material n...
A new Compton scattered tomography modality and its application to material n...
 
Reliable Positioning with Hybrid Antenna Model for Aerial Wireless Sensor and...
Reliable Positioning with Hybrid Antenna Model for Aerial Wireless Sensor and...Reliable Positioning with Hybrid Antenna Model for Aerial Wireless Sensor and...
Reliable Positioning with Hybrid Antenna Model for Aerial Wireless Sensor and...
 

Recently uploaded

Leveraging Generative AI to Drive Nonprofit Innovation
Leveraging Generative AI to Drive Nonprofit InnovationLeveraging Generative AI to Drive Nonprofit Innovation
Leveraging Generative AI to Drive Nonprofit Innovation
TechSoup
 
RHEOLOGY Physical pharmaceutics-II notes for B.pharm 4th sem students
RHEOLOGY Physical pharmaceutics-II notes for B.pharm 4th sem studentsRHEOLOGY Physical pharmaceutics-II notes for B.pharm 4th sem students
RHEOLOGY Physical pharmaceutics-II notes for B.pharm 4th sem students
Himanshu Rai
 
How to Fix the Import Error in the Odoo 17
How to Fix the Import Error in the Odoo 17How to Fix the Import Error in the Odoo 17
How to Fix the Import Error in the Odoo 17
Celine George
 
The Diamonds of 2023-2024 in the IGRA collection
The Diamonds of 2023-2024 in the IGRA collectionThe Diamonds of 2023-2024 in the IGRA collection
The Diamonds of 2023-2024 in the IGRA collection
Israel Genealogy Research Association
 
How to Manage Your Lost Opportunities in Odoo 17 CRM
How to Manage Your Lost Opportunities in Odoo 17 CRMHow to Manage Your Lost Opportunities in Odoo 17 CRM
How to Manage Your Lost Opportunities in Odoo 17 CRM
Celine George
 
คำศัพท์ คำพื้นฐานการอ่าน ภาษาอังกฤษ ระดับชั้น ม.1
คำศัพท์ คำพื้นฐานการอ่าน ภาษาอังกฤษ ระดับชั้น ม.1คำศัพท์ คำพื้นฐานการอ่าน ภาษาอังกฤษ ระดับชั้น ม.1
คำศัพท์ คำพื้นฐานการอ่าน ภาษาอังกฤษ ระดับชั้น ม.1
สมใจ จันสุกสี
 
Chapter 4 - Islamic Financial Institutions in Malaysia.pptx
Chapter 4 - Islamic Financial Institutions in Malaysia.pptxChapter 4 - Islamic Financial Institutions in Malaysia.pptx
Chapter 4 - Islamic Financial Institutions in Malaysia.pptx
Mohd Adib Abd Muin, Senior Lecturer at Universiti Utara Malaysia
 
Advanced Java[Extra Concepts, Not Difficult].docx
Advanced Java[Extra Concepts, Not Difficult].docxAdvanced Java[Extra Concepts, Not Difficult].docx
Advanced Java[Extra Concepts, Not Difficult].docx
adhitya5119
 
Digital Artefact 1 - Tiny Home Environmental Design
Digital Artefact 1 - Tiny Home Environmental DesignDigital Artefact 1 - Tiny Home Environmental Design
Digital Artefact 1 - Tiny Home Environmental Design
amberjdewit93
 
Film vocab for eal 3 students: Australia the movie
Film vocab for eal 3 students: Australia the movieFilm vocab for eal 3 students: Australia the movie
Film vocab for eal 3 students: Australia the movie
Nicholas Montgomery
 
Cognitive Development Adolescence Psychology
Cognitive Development Adolescence PsychologyCognitive Development Adolescence Psychology
Cognitive Development Adolescence Psychology
paigestewart1632
 
Beyond Degrees - Empowering the Workforce in the Context of Skills-First.pptx
Beyond Degrees - Empowering the Workforce in the Context of Skills-First.pptxBeyond Degrees - Empowering the Workforce in the Context of Skills-First.pptx
Beyond Degrees - Empowering the Workforce in the Context of Skills-First.pptx
EduSkills OECD
 
Pollock and Snow "DEIA in the Scholarly Landscape, Session One: Setting Expec...
Pollock and Snow "DEIA in the Scholarly Landscape, Session One: Setting Expec...Pollock and Snow "DEIA in the Scholarly Landscape, Session One: Setting Expec...
Pollock and Snow "DEIA in the Scholarly Landscape, Session One: Setting Expec...
National Information Standards Organization (NISO)
 
বাংলাদেশ অর্থনৈতিক সমীক্ষা (Economic Review) ২০২৪ UJS App.pdf
বাংলাদেশ অর্থনৈতিক সমীক্ষা (Economic Review) ২০২৪ UJS App.pdfবাংলাদেশ অর্থনৈতিক সমীক্ষা (Economic Review) ২০২৪ UJS App.pdf
বাংলাদেশ অর্থনৈতিক সমীক্ষা (Economic Review) ২০২৪ UJS App.pdf
eBook.com.bd (প্রয়োজনীয় বাংলা বই)
 
A Independência da América Espanhola LAPBOOK.pdf
A Independência da América Espanhola LAPBOOK.pdfA Independência da América Espanhola LAPBOOK.pdf
A Independência da América Espanhola LAPBOOK.pdf
Jean Carlos Nunes Paixão
 
clinical examination of hip joint (1).pdf
clinical examination of hip joint (1).pdfclinical examination of hip joint (1).pdf
clinical examination of hip joint (1).pdf
Priyankaranawat4
 
How to Setup Warehouse & Location in Odoo 17 Inventory
How to Setup Warehouse & Location in Odoo 17 InventoryHow to Setup Warehouse & Location in Odoo 17 Inventory
How to Setup Warehouse & Location in Odoo 17 Inventory
Celine George
 
LAND USE LAND COVER AND NDVI OF MIRZAPUR DISTRICT, UP
LAND USE LAND COVER AND NDVI OF MIRZAPUR DISTRICT, UPLAND USE LAND COVER AND NDVI OF MIRZAPUR DISTRICT, UP
LAND USE LAND COVER AND NDVI OF MIRZAPUR DISTRICT, UP
RAHUL
 
writing about opinions about Australia the movie
writing about opinions about Australia the moviewriting about opinions about Australia the movie
writing about opinions about Australia the movie
Nicholas Montgomery
 
The basics of sentences session 6pptx.pptx
The basics of sentences session 6pptx.pptxThe basics of sentences session 6pptx.pptx
The basics of sentences session 6pptx.pptx
heathfieldcps1
 

Recently uploaded (20)

Leveraging Generative AI to Drive Nonprofit Innovation
Leveraging Generative AI to Drive Nonprofit InnovationLeveraging Generative AI to Drive Nonprofit Innovation
Leveraging Generative AI to Drive Nonprofit Innovation
 
RHEOLOGY Physical pharmaceutics-II notes for B.pharm 4th sem students
RHEOLOGY Physical pharmaceutics-II notes for B.pharm 4th sem studentsRHEOLOGY Physical pharmaceutics-II notes for B.pharm 4th sem students
RHEOLOGY Physical pharmaceutics-II notes for B.pharm 4th sem students
 
How to Fix the Import Error in the Odoo 17
How to Fix the Import Error in the Odoo 17How to Fix the Import Error in the Odoo 17
How to Fix the Import Error in the Odoo 17
 
The Diamonds of 2023-2024 in the IGRA collection
The Diamonds of 2023-2024 in the IGRA collectionThe Diamonds of 2023-2024 in the IGRA collection
The Diamonds of 2023-2024 in the IGRA collection
 
How to Manage Your Lost Opportunities in Odoo 17 CRM
How to Manage Your Lost Opportunities in Odoo 17 CRMHow to Manage Your Lost Opportunities in Odoo 17 CRM
How to Manage Your Lost Opportunities in Odoo 17 CRM
 
คำศัพท์ คำพื้นฐานการอ่าน ภาษาอังกฤษ ระดับชั้น ม.1
คำศัพท์ คำพื้นฐานการอ่าน ภาษาอังกฤษ ระดับชั้น ม.1คำศัพท์ คำพื้นฐานการอ่าน ภาษาอังกฤษ ระดับชั้น ม.1
คำศัพท์ คำพื้นฐานการอ่าน ภาษาอังกฤษ ระดับชั้น ม.1
 
Chapter 4 - Islamic Financial Institutions in Malaysia.pptx
Chapter 4 - Islamic Financial Institutions in Malaysia.pptxChapter 4 - Islamic Financial Institutions in Malaysia.pptx
Chapter 4 - Islamic Financial Institutions in Malaysia.pptx
 
Advanced Java[Extra Concepts, Not Difficult].docx
Advanced Java[Extra Concepts, Not Difficult].docxAdvanced Java[Extra Concepts, Not Difficult].docx
Advanced Java[Extra Concepts, Not Difficult].docx
 
Digital Artefact 1 - Tiny Home Environmental Design
Digital Artefact 1 - Tiny Home Environmental DesignDigital Artefact 1 - Tiny Home Environmental Design
Digital Artefact 1 - Tiny Home Environmental Design
 
Film vocab for eal 3 students: Australia the movie
Film vocab for eal 3 students: Australia the movieFilm vocab for eal 3 students: Australia the movie
Film vocab for eal 3 students: Australia the movie
 
Cognitive Development Adolescence Psychology
Cognitive Development Adolescence PsychologyCognitive Development Adolescence Psychology
Cognitive Development Adolescence Psychology
 
Beyond Degrees - Empowering the Workforce in the Context of Skills-First.pptx
Beyond Degrees - Empowering the Workforce in the Context of Skills-First.pptxBeyond Degrees - Empowering the Workforce in the Context of Skills-First.pptx
Beyond Degrees - Empowering the Workforce in the Context of Skills-First.pptx
 
Pollock and Snow "DEIA in the Scholarly Landscape, Session One: Setting Expec...
Pollock and Snow "DEIA in the Scholarly Landscape, Session One: Setting Expec...Pollock and Snow "DEIA in the Scholarly Landscape, Session One: Setting Expec...
Pollock and Snow "DEIA in the Scholarly Landscape, Session One: Setting Expec...
 
বাংলাদেশ অর্থনৈতিক সমীক্ষা (Economic Review) ২০২৪ UJS App.pdf
বাংলাদেশ অর্থনৈতিক সমীক্ষা (Economic Review) ২০২৪ UJS App.pdfবাংলাদেশ অর্থনৈতিক সমীক্ষা (Economic Review) ২০২৪ UJS App.pdf
বাংলাদেশ অর্থনৈতিক সমীক্ষা (Economic Review) ২০২৪ UJS App.pdf
 
A Independência da América Espanhola LAPBOOK.pdf
A Independência da América Espanhola LAPBOOK.pdfA Independência da América Espanhola LAPBOOK.pdf
A Independência da América Espanhola LAPBOOK.pdf
 
clinical examination of hip joint (1).pdf
clinical examination of hip joint (1).pdfclinical examination of hip joint (1).pdf
clinical examination of hip joint (1).pdf
 
How to Setup Warehouse & Location in Odoo 17 Inventory
How to Setup Warehouse & Location in Odoo 17 InventoryHow to Setup Warehouse & Location in Odoo 17 Inventory
How to Setup Warehouse & Location in Odoo 17 Inventory
 
LAND USE LAND COVER AND NDVI OF MIRZAPUR DISTRICT, UP
LAND USE LAND COVER AND NDVI OF MIRZAPUR DISTRICT, UPLAND USE LAND COVER AND NDVI OF MIRZAPUR DISTRICT, UP
LAND USE LAND COVER AND NDVI OF MIRZAPUR DISTRICT, UP
 
writing about opinions about Australia the movie
writing about opinions about Australia the moviewriting about opinions about Australia the movie
writing about opinions about Australia the movie
 
The basics of sentences session 6pptx.pptx
The basics of sentences session 6pptx.pptxThe basics of sentences session 6pptx.pptx
The basics of sentences session 6pptx.pptx
 

24th JCAART 2009 Conference

  • 1. Prince of Songkhla University Department of Computer Engineering 24th JCAART’09 Conference Vision-based Fall Detection and Alert System Suitable for the Elderly and Disabled Peoples Teerasak Kroputaponchai and Dr. Nikom Suvonvorn Presented by Assoc. Prof. Dr. Pornchai Phukpattaranont Faculty of Engineering Prince of Songkla University, Thailand Teerasak Kroputaponchai and Nikom SUVONVORN August 26-28, 24th JCAART 2009 Conference
  • 2. Prince of Songkhla University Department of Computer Engineering Outline • Problem statement • System Overview • Motion detection and tracking • Features extraction • Fall analysis and detection • Result and discussion • Conclusion and future work Teerasak Kroputaponchai and Nikom SUVONVORN August 26-28, 24th JCAART 2009 Conference
  • 3. Prince of Songkhla University Department of Computer Engineering Problem statement • Falls event amongst the elderly are particularly serious and often lead to injury or death • Automatic monitoring of the activities of daily living (ADL) and falls event for the elderly and disabled people using image sequences analysis leads to the immediate or preventive intervention. Teerasak Kroputaponchai and Nikom SUVONVORN August 26-28, 24th JCAART 2009 Conference
  • 4. Prince of Songkhla University Department of Computer Engineering System overview Motion detection Features extraction Fall detection Motion Tracking Teerasak Kroputaponchai and Nikom SUVONVORN August 26-28, 24th JCAART 2009 Conference
  • 5. Prince of Songkhla University Department of Computer Engineering Motion detection • Use background subtraction technique – Running Average with selectivity ⎧αFi ( x, y ) + (1 − α ) Bi ( x, y ) if Fi ( x, y ) is background Bi +1 ( x, y ) = ⎨ ⎩ Bi ( x, y ) else ⎧255 if Bi ( x, y ) − Fi ( x, y ) < τ Oi +1 ( x, y ) = ⎨ ⎩ 0 else • Morphological operation – Opening and Closing – Noise suppression Teerasak Kroputaponchai and Nikom SUVONVORN August 26-28, 24th JCAART 2009 Conference
  • 6. Prince of Songkhla University Department of Computer Engineering Motion segmentation • Spatial-based region-fusion operation – Two regions are the same object if they are overlapped or their distance less than a specific threshold – Very sensible to light condition : shadow, contrast changing and sudden changes of light Teerasak Kroputaponchai and Nikom SUVONVORN August 26-28, 24th JCAART 2009 Conference
  • 7. Prince of Songkhla University Department of Computer Engineering Motion segmentation on tracking • Texture-based region-fusion during tracking process – the color probability density of object’s texture is additionally applied as a similarity measurement between regions – Mixture motion-texture model can reduce noises and increases significantly the effectiveness of algorithm (a) Image sequence (b) motion detection (c) texture detection (d) mixture of motion-texture Teerasak Kroputaponchai and Nikom SUVONVORN August 26-28, 24th JCAART 2009 Conference
  • 8. Prince of Songkhla University Department of Computer Engineering Motion tracking by Mean-shift • Mean-shift tracking – Iterative procedure that shifts pixel’s intensity to the average of its neighborhood on the color probability density. • Multiple-regions tracking – Upper body and Lower body parts Teerasak Kroputaponchai and Nikom SUVONVORN August 26-28, 24th JCAART 2009 Conference
  • 9. Prince of Songkhla University Department of Computer Engineering Features extraction • Object (Human?) characteristics – Width and Height of object region – Angle between y-axis and horizontal line • Object principle axis is calculated from region moment – Speed of the extremity points of y-axis • Computed as the ratio of moving distance between frames and time θ H W Teerasak Kroputaponchai and Nikom SUVONVORN August 26-28, 24th JCAART 2009 Conference
  • 10. Prince of Songkhla University Department of Computer Engineering Features extraction • Noises suppression – Noisy features obtained from non-perfect tracking process • Butterworth low-pass filter – To consider the fall characteristic factors : the frequency cut must higher than the fall frequencies (0.4s-0.8s) – Kernel parameters is 1/22 [1/6, 1/2, 1/1.06, 1, 1/1.06, 1/2, 1/6] – Apply to the five features… Teerasak Kroputaponchai and Nikom SUVONVORN August 26-28, 24th JCAART 2009 Conference
  • 11. Prince of Songkhla University Department of Computer Engineering Features to fall analysis (a) Fall (b) Fall Lie Lie Fall (c) Lie (a) Angle (b) Width and Height (c) Speed of extremity points Teerasak Kroputaponchai and Nikom SUVONVORN August 26-28, 24th JCAART 2009 Conference
  • 12. Prince of Songkhla University Department of Computer Engineering Fall detection • Expert and Rules based decision Fall detection Yes Yes Yes Lie detection H = Height W = Width t = Time V = Speed delta = Fall angle Teerasak Kroputaponchai and Nikom SUVONVORN August 26-28, 24th JCAART 2009 Conference
  • 13. Prince of Songkhla University Department of Computer Engineering Result and discussion • Dataset – 15 Fall datasets was done in a indoor situation using volunteers • Result T-Shirt Pants Image Fall False Color Color Sequences Detection positives Orange Blue 5 80% 1 White Blue 5 60% 2 Green White 5 80% 1 • Most false positives is caused by non-perfect motion detection and tracking process. Teerasak Kroputaponchai and Nikom SUVONVORN August 26-28, 24th JCAART 2009 Conference
  • 14. Prince of Songkhla University Department of Computer Engineering Result and discussion • Demo Teerasak Kroputaponchai and Nikom SUVONVORN August 26-28, 24th JCAART 2009 Conference
  • 15. Prince of Songkhla University Department of Computer Engineering Result and discussion • Error Teerasak Kroputaponchai and Nikom SUVONVORN August 26-28, 24th JCAART 2009 Conference
  • 16. Prince of Songkhla University Department of Computer Engineering Future work • Improve the motion and tracking method • Improve human modeling • Decision method – Decision rules by the expert to by supervised learning Teerasak Kroputaponchai and Nikom SUVONVORN August 26-28, 24th JCAART 2009 Conference
  • 17. Prince of Songkhla University Department of Computer Engineering References • G. Perolle, P. Fraisse, M. Mavros and I. Etxeberria. , “Automatic Fall Detection and Activity Monitoring for Elderly,” In Proceedings of MEDETEL, 2006. • Chia-Wen Lin and Zhi-Hong Ling., “Automatic Fall Incident Detection in Compressed Video for Intelligent Homecare,” Computer Communications and Networks 2007, pp.1172 – 1177,2007. • R. C. Gonzalez and R. E. Woods, Digital Image Processing, Prentice Hall, (2nd Edition) 2002. • W. Hu, T. Tan, L. Wang, and S. Maybank, “A survey on visual surveillance of object motion and behavior,” IEEE trans. Systems, Man, and Cybernetics- Part C: Applications and Reviews, vol. 38, no. 3, pp.334-352, Aug. 2004. • R. Cucchiara, A. Prati and R. Vezzani “A Multi-Camera Vision system for Fall Detection and Alarm Generation,” Expert Systems Journal , vol. 5 , Blackwell Publishing. 2007. • J. K. Aggarwai, Q. Cai, “Human Motion Analysis: A review,” Computer Vision and Image Understanding, Vol. 73, pp.428-440,1999 • M. Piccardi, “Background subtraction techniques: a review”, in Proc. of IEEE SMC 2004 International Conference on Systems, Man and Cybernetics, The Hague, The Netherlands, October 2004. Thanks you Teerasak Kroputaponchai and Nikom SUVONVORN August 26-28, 24th JCAART 2009 Conference