SlideShare ist ein Scribd-Unternehmen logo
1 von 10
Human Arm Tracking
TRAINING A CRS ROBOTIC ARM USING HUMAN ARM
IMITATION THROUGH KINECT
MICROSO         It consists of:

   FT           • RGB Camera.
                • Two Infrared sensors which act as a depth sensor.
 KINECT         • Four element microphone array.
SENSOR
                In default range mode, Kinect can see people standing between
                0.8 meters and 4.0 meters away.
                Users will have to be able to use their arms at that distance,
                which narrows down to a practical range of 1.2 to 3.5 meters.
                In the near mode, Kinect has a practical range of 0.8 to 2.5
                meters.



          [1]
The robotic arm has 6 degree of freedoms:

  CRS
ROBOTIC
  ARM

                                                              [3]

                We wouldn’t be using JOINT 6 as the human arm doesn’t has this
                degree of freedom.



          [2]
D-H Parameters
The Denavit–Hartenberg parameters (also called DH parameters) are the four parameters associated with
a particular convention for attaching reference frames to the links of a spatial kinematic chain.
θi - the angle between the axes, Xi-1 and Xi,
about the axis Zi .
di - the distance between Xi-1 and Xi along Zi.
ai - the distance between the common normals
to axes Zi and Zi + 1 along Xi.
αi - the angle between the axes, Zi and Zi + 1, about
the axis Xi.
                                                                                                    [4]

Using the above 4 parameters we could define a reference for each link of our robotic arm.
Kinect Skeletal API
Microsoft Kinect sensor provides us with the API to track a human body. The Kinect
keeps track of the joints of our arm.
We are using this to provide us with the 3D coordinate of the joints which we
would be further using to calculate the joint angles using the known D-H
parameters of the arm.




                                                                                     [5]
Calculating Joint Angles
• We obtain the upper extremity joint position measurement from the kinect sensor, ex., [x y z].
• To calculate joint angles at the 6-DOFs robot manipulator given the end-effector position
  measurement, we apply the iterative Newton method for solving the inverse kinematics
  problem.
• The algorithm can be described by
Transmitting Data To The
                   Robot
• This will be one of the major challenges.
• The robot is currently controlled by either
  a manual controller or using a windows
  application RobCoMM (the OS of the
  robot)
• The Robot was discontinued in around
  1995
• We do not have much info on how to
  control the bot in realtime by sending
  commands through the serial port
• The data is transmitted to the robot
  through Serial Communication
                                                [6]
Local Optimization and
                 Application
Each of the configuration of the robotic arm is a point in a 5-dimensional space.
While we operate the robotic arm using our hand, it is possible that we might have not taken
the optimal path from start to end configuration .
So we could remove some redundant states from our path to optimize our path.
Algorithm: We would connect each state with it’s k nearest neighbors. Then in the new graph
we would find the shortest path between the start and the end state using the Dijkastra’s
Algorithm. After that we would only keep the states found on the above path and discard the
other states.
Thus we can now use the robot to efficiently perform the task any number of times.
References
• [1] http://gamesforkinect.org/kinect-information/how-does-the-kinect-sensors-work/
• [2] http://cmp.felk.cvut.cz/cmp/hardware/A465/A465.html
• [3] http://cmp.felk.cvut.cz/cmp/courses/ROB/labsmaterial/CRS/CRS-uvod.htm
• [4] Figure 3.4, Page 66 Introduction to Robotics By John J. Craig.
• [5] http://msdn.microsoft.com/en-us/library/hh973074.aspx
• [6] http://www.doom9.org/index.html?/DigiTV/dbox-howto.htm
• Real-Time Human Pose Recognition in Parts from Single Depth Images
 http://research.microsoft.com/pubs/145347/BodyPartRecognition.pdf
• Introduction to Robotics By John J. Craig.
Thank You
AYUSH VARSHNEY
RITESH GAUTAM

Weitere ähnliche Inhalte

Ähnlich wie Human arm tracking

Geasture Control Robotic Arm
Geasture Control Robotic ArmGeasture Control Robotic Arm
Geasture Control Robotic ArmSree Harsha
 
Robotics_EC368_Module_1.pptx
Robotics_EC368_Module_1.pptxRobotics_EC368_Module_1.pptx
Robotics_EC368_Module_1.pptxneenajoseph18
 
Control Buggy using Leap Sensor Camera in Data Mining Domain
Control Buggy using Leap Sensor Camera in Data Mining DomainControl Buggy using Leap Sensor Camera in Data Mining Domain
Control Buggy using Leap Sensor Camera in Data Mining DomainIRJET Journal
 
HCI for Real world Applications
HCI for Real world ApplicationsHCI for Real world Applications
HCI for Real world ApplicationsIOSR Journals
 
Complex Weld Seam Detection Using Computer Vision Linked In
Complex Weld Seam Detection Using Computer Vision Linked InComplex Weld Seam Detection Using Computer Vision Linked In
Complex Weld Seam Detection Using Computer Vision Linked Inglenn_silvers
 
All About Robotics (pdf)
All About Robotics (pdf)All About Robotics (pdf)
All About Robotics (pdf)Priyanshu
 
Robots one day presentation
Robots one day presentationRobots one day presentation
Robots one day presentationGanesh Murugan
 
ROBOTOR AN AUTONOMOUS VEHICLE FOR TARGET DETECTION AND SHOOTING
ROBOTOR AN AUTONOMOUS VEHICLE FOR TARGET DETECTION AND SHOOTINGROBOTOR AN AUTONOMOUS VEHICLE FOR TARGET DETECTION AND SHOOTING
ROBOTOR AN AUTONOMOUS VEHICLE FOR TARGET DETECTION AND SHOOTINGIAEME Publication
 
UNIT 6 Robotics01.ppt
UNIT 6 Robotics01.pptUNIT 6 Robotics01.ppt
UNIT 6 Robotics01.pptnachiketkale5
 
Robotics corporate-training-in-mumbai
Robotics corporate-training-in-mumbaiRobotics corporate-training-in-mumbai
Robotics corporate-training-in-mumbaiUnmesh Baile
 

Ähnlich wie Human arm tracking (20)

Geasture Control Robotic Arm
Geasture Control Robotic ArmGeasture Control Robotic Arm
Geasture Control Robotic Arm
 
Robotics ppt.pptx
Robotics ppt.pptxRobotics ppt.pptx
Robotics ppt.pptx
 
30120140506012 2
30120140506012 230120140506012 2
30120140506012 2
 
30120140506012 2
30120140506012 230120140506012 2
30120140506012 2
 
Robotics_EC368_Module_1.pptx
Robotics_EC368_Module_1.pptxRobotics_EC368_Module_1.pptx
Robotics_EC368_Module_1.pptx
 
Control Buggy using Leap Sensor Camera in Data Mining Domain
Control Buggy using Leap Sensor Camera in Data Mining DomainControl Buggy using Leap Sensor Camera in Data Mining Domain
Control Buggy using Leap Sensor Camera in Data Mining Domain
 
ROBOTICS - Introduction to Robotics
ROBOTICS -  Introduction to RoboticsROBOTICS -  Introduction to Robotics
ROBOTICS - Introduction to Robotics
 
Robocup2006
Robocup2006Robocup2006
Robocup2006
 
L01117074
L01117074L01117074
L01117074
 
HCI for Real world Applications
HCI for Real world ApplicationsHCI for Real world Applications
HCI for Real world Applications
 
Complex Weld Seam Detection Using Computer Vision Linked In
Complex Weld Seam Detection Using Computer Vision Linked InComplex Weld Seam Detection Using Computer Vision Linked In
Complex Weld Seam Detection Using Computer Vision Linked In
 
Project Report
Project ReportProject Report
Project Report
 
All About Robotics (pdf)
All About Robotics (pdf)All About Robotics (pdf)
All About Robotics (pdf)
 
Robots one day presentation
Robots one day presentationRobots one day presentation
Robots one day presentation
 
ROBOTOR AN AUTONOMOUS VEHICLE FOR TARGET DETECTION AND SHOOTING
ROBOTOR AN AUTONOMOUS VEHICLE FOR TARGET DETECTION AND SHOOTINGROBOTOR AN AUTONOMOUS VEHICLE FOR TARGET DETECTION AND SHOOTING
ROBOTOR AN AUTONOMOUS VEHICLE FOR TARGET DETECTION AND SHOOTING
 
UNIT 6 Robotics01.ppt
UNIT 6 Robotics01.pptUNIT 6 Robotics01.ppt
UNIT 6 Robotics01.ppt
 
Kinect sensor
Kinect sensorKinect sensor
Kinect sensor
 
Robotics corporate-training-in-mumbai
Robotics corporate-training-in-mumbaiRobotics corporate-training-in-mumbai
Robotics corporate-training-in-mumbai
 
Robotics ppt
Robotics pptRobotics ppt
Robotics ppt
 
Chapter 1
Chapter 1Chapter 1
Chapter 1
 

Kürzlich hochgeladen

How to setup Pycharm environment for Odoo 17.pptx
How to setup Pycharm environment for Odoo 17.pptxHow to setup Pycharm environment for Odoo 17.pptx
How to setup Pycharm environment for Odoo 17.pptxCeline George
 
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...Nguyen Thanh Tu Collection
 
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdfUGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdfNirmal Dwivedi
 
Interdisciplinary_Insights_Data_Collection_Methods.pptx
Interdisciplinary_Insights_Data_Collection_Methods.pptxInterdisciplinary_Insights_Data_Collection_Methods.pptx
Interdisciplinary_Insights_Data_Collection_Methods.pptxPooja Bhuva
 
ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.MaryamAhmad92
 
On National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsOn National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsMebane Rash
 
Fostering Friendships - Enhancing Social Bonds in the Classroom
Fostering Friendships - Enhancing Social Bonds  in the ClassroomFostering Friendships - Enhancing Social Bonds  in the Classroom
Fostering Friendships - Enhancing Social Bonds in the ClassroomPooky Knightsmith
 
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...Nguyen Thanh Tu Collection
 
The basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxThe basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxheathfieldcps1
 
Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)Jisc
 
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...ZurliaSoop
 
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...Pooja Bhuva
 
On_Translating_a_Tamil_Poem_by_A_K_Ramanujan.pptx
On_Translating_a_Tamil_Poem_by_A_K_Ramanujan.pptxOn_Translating_a_Tamil_Poem_by_A_K_Ramanujan.pptx
On_Translating_a_Tamil_Poem_by_A_K_Ramanujan.pptxPooja Bhuva
 
Micro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdfMicro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdfPoh-Sun Goh
 
Application orientated numerical on hev.ppt
Application orientated numerical on hev.pptApplication orientated numerical on hev.ppt
Application orientated numerical on hev.pptRamjanShidvankar
 
Understanding Accommodations and Modifications
Understanding  Accommodations and ModificationsUnderstanding  Accommodations and Modifications
Understanding Accommodations and ModificationsMJDuyan
 
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdf
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdfUnit 3 Emotional Intelligence and Spiritual Intelligence.pdf
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdfDr Vijay Vishwakarma
 
Holdier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfHoldier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfagholdier
 
Wellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptxWellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptxJisc
 
FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024Elizabeth Walsh
 

Kürzlich hochgeladen (20)

How to setup Pycharm environment for Odoo 17.pptx
How to setup Pycharm environment for Odoo 17.pptxHow to setup Pycharm environment for Odoo 17.pptx
How to setup Pycharm environment for Odoo 17.pptx
 
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...
 
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdfUGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
 
Interdisciplinary_Insights_Data_Collection_Methods.pptx
Interdisciplinary_Insights_Data_Collection_Methods.pptxInterdisciplinary_Insights_Data_Collection_Methods.pptx
Interdisciplinary_Insights_Data_Collection_Methods.pptx
 
ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.
 
On National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsOn National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan Fellows
 
Fostering Friendships - Enhancing Social Bonds in the Classroom
Fostering Friendships - Enhancing Social Bonds  in the ClassroomFostering Friendships - Enhancing Social Bonds  in the Classroom
Fostering Friendships - Enhancing Social Bonds in the Classroom
 
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
 
The basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxThe basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptx
 
Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)
 
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
 
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
 
On_Translating_a_Tamil_Poem_by_A_K_Ramanujan.pptx
On_Translating_a_Tamil_Poem_by_A_K_Ramanujan.pptxOn_Translating_a_Tamil_Poem_by_A_K_Ramanujan.pptx
On_Translating_a_Tamil_Poem_by_A_K_Ramanujan.pptx
 
Micro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdfMicro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdf
 
Application orientated numerical on hev.ppt
Application orientated numerical on hev.pptApplication orientated numerical on hev.ppt
Application orientated numerical on hev.ppt
 
Understanding Accommodations and Modifications
Understanding  Accommodations and ModificationsUnderstanding  Accommodations and Modifications
Understanding Accommodations and Modifications
 
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdf
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdfUnit 3 Emotional Intelligence and Spiritual Intelligence.pdf
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdf
 
Holdier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfHoldier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdf
 
Wellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptxWellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptx
 
FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024
 

Human arm tracking

  • 1. Human Arm Tracking TRAINING A CRS ROBOTIC ARM USING HUMAN ARM IMITATION THROUGH KINECT
  • 2. MICROSO It consists of: FT • RGB Camera. • Two Infrared sensors which act as a depth sensor. KINECT • Four element microphone array. SENSOR In default range mode, Kinect can see people standing between 0.8 meters and 4.0 meters away. Users will have to be able to use their arms at that distance, which narrows down to a practical range of 1.2 to 3.5 meters. In the near mode, Kinect has a practical range of 0.8 to 2.5 meters. [1]
  • 3. The robotic arm has 6 degree of freedoms: CRS ROBOTIC ARM [3] We wouldn’t be using JOINT 6 as the human arm doesn’t has this degree of freedom. [2]
  • 4. D-H Parameters The Denavit–Hartenberg parameters (also called DH parameters) are the four parameters associated with a particular convention for attaching reference frames to the links of a spatial kinematic chain. θi - the angle between the axes, Xi-1 and Xi, about the axis Zi . di - the distance between Xi-1 and Xi along Zi. ai - the distance between the common normals to axes Zi and Zi + 1 along Xi. αi - the angle between the axes, Zi and Zi + 1, about the axis Xi. [4] Using the above 4 parameters we could define a reference for each link of our robotic arm.
  • 5. Kinect Skeletal API Microsoft Kinect sensor provides us with the API to track a human body. The Kinect keeps track of the joints of our arm. We are using this to provide us with the 3D coordinate of the joints which we would be further using to calculate the joint angles using the known D-H parameters of the arm. [5]
  • 6. Calculating Joint Angles • We obtain the upper extremity joint position measurement from the kinect sensor, ex., [x y z]. • To calculate joint angles at the 6-DOFs robot manipulator given the end-effector position measurement, we apply the iterative Newton method for solving the inverse kinematics problem. • The algorithm can be described by
  • 7. Transmitting Data To The Robot • This will be one of the major challenges. • The robot is currently controlled by either a manual controller or using a windows application RobCoMM (the OS of the robot) • The Robot was discontinued in around 1995 • We do not have much info on how to control the bot in realtime by sending commands through the serial port • The data is transmitted to the robot through Serial Communication [6]
  • 8. Local Optimization and Application Each of the configuration of the robotic arm is a point in a 5-dimensional space. While we operate the robotic arm using our hand, it is possible that we might have not taken the optimal path from start to end configuration . So we could remove some redundant states from our path to optimize our path. Algorithm: We would connect each state with it’s k nearest neighbors. Then in the new graph we would find the shortest path between the start and the end state using the Dijkastra’s Algorithm. After that we would only keep the states found on the above path and discard the other states. Thus we can now use the robot to efficiently perform the task any number of times.
  • 9. References • [1] http://gamesforkinect.org/kinect-information/how-does-the-kinect-sensors-work/ • [2] http://cmp.felk.cvut.cz/cmp/hardware/A465/A465.html • [3] http://cmp.felk.cvut.cz/cmp/courses/ROB/labsmaterial/CRS/CRS-uvod.htm • [4] Figure 3.4, Page 66 Introduction to Robotics By John J. Craig. • [5] http://msdn.microsoft.com/en-us/library/hh973074.aspx • [6] http://www.doom9.org/index.html?/DigiTV/dbox-howto.htm • Real-Time Human Pose Recognition in Parts from Single Depth Images http://research.microsoft.com/pubs/145347/BodyPartRecognition.pdf • Introduction to Robotics By John J. Craig.