Difference between revisions of "EE586L/Projects 2012"
| (26 intermediate revisions by the same user not shown) | |||
| Line 4: | Line 4: | ||
'''Abstract:''' ''Video based American Sign Language Recognition using color detection and motion tracking.'' | '''Abstract:''' ''Video based American Sign Language Recognition using color detection and motion tracking.'' | ||
| − | |||
| − | |||
| − | |||
== AudioSense == | == AudioSense == | ||
| Line 14: | Line 11: | ||
'''Abstract:''' ''A gesture recognition based audio system is implemented. Hand gestures are used to increase/decrease volume, change tracks, mute/unmute the track, play, pause and time seek.'' | '''Abstract:''' ''A gesture recognition based audio system is implemented. Hand gestures are used to increase/decrease volume, change tracks, mute/unmute the track, play, pause and time seek.'' | ||
| − | '''Poster:''' [ Poster] | + | '''Poster:''' [http://biron.usc.edu/~sungwonl/EE586/Submission_2012/Audio_Sense.pdf Poster] |
| + | |||
| + | == Chessboard Game == | ||
| + | |||
| + | '''Authors:''' Ming Qu, [mailto:yuanyang@usc.edu YuanYang], [mailto:huishush@usc.edu Huishu Shi] | ||
| + | |||
| + | '''Abstract:''' ''Our project implements image processing techniques in real time by using the TI c6416 DSP processor and CCS system. | ||
| + | We use a camera, a paper chessboard and two fingerstalls to simulate the process of playing chess between two players. | ||
| + | The project works well in real time.'' | ||
| − | ''' | + | '''PPT:''' [http://biron.usc.edu/~sungwonl/EE586/Submission_2012/ChessBoardGame.pdf PPT] |
| + | '''Video:''' [http://youtu.be/nGApApaR1Mw YouTube Video] | ||
== Digit(al) Calculator == | == Digit(al) Calculator == | ||
| Line 25: | Line 31: | ||
'''Abstract:''' ''Automatic recognition of sign language is an important research problem for communication. Real-time image processing can provide much better experience than using a touch based system. Our project implements a basic calculator using gesture recognition methods. It can be very useful to use this calculator by using gestures for numbers and symbols such as addition, subtraction, multiplication and division, without pressing any buttons or typing anything.'' | '''Abstract:''' ''Automatic recognition of sign language is an important research problem for communication. Real-time image processing can provide much better experience than using a touch based system. Our project implements a basic calculator using gesture recognition methods. It can be very useful to use this calculator by using gestures for numbers and symbols such as addition, subtraction, multiplication and division, without pressing any buttons or typing anything.'' | ||
| − | ''' | + | '''Poster:''' [http://biron.usc.edu/~sungwonl/EE586/Submission_2012/DigitCalculator.pdf Poster] |
| − | |||
== Dodge the Rock == | == Dodge the Rock == | ||
| Line 33: | Line 38: | ||
'''Abstract:''' ''We are doing a interactive game based on gesture recognition.'' | '''Abstract:''' ''We are doing a interactive game based on gesture recognition.'' | ||
| + | |||
| + | '''Poster:''' [http://biron.usc.edu/~sungwonl/EE586/Submission_2012/Dodge_the_Rock.pdf Poster] | ||
'''Video:''' [http://www.youtube.com/watch?v=dlzvKH5jwEY YouTube Video] | '''Video:''' [http://www.youtube.com/watch?v=dlzvKH5jwEY YouTube Video] | ||
| − | |||
== Duck Hunters == | == Duck Hunters == | ||
| Line 43: | Line 49: | ||
'''Abstract:''' ''The name says it all. We all miss the Nintendo games from the 90's, so in an attempt to refresh your memories we re-created the game but this one does not need a zapper gun, you can use a rod to project a point on the screen and we didn't change the rules either.'' | '''Abstract:''' ''The name says it all. We all miss the Nintendo games from the 90's, so in an attempt to refresh your memories we re-created the game but this one does not need a zapper gun, you can use a rod to project a point on the screen and we didn't change the rules either.'' | ||
| − | ''' | + | '''Poster:''' [http://biron.usc.edu/~sungwonl/EE586/Submission_2012/DuckHunters.pdf Poster] |
| + | '''Video:''' [http://www.youtube.com/watch?v=k6nRmgKBqbc YouTube Video] | ||
== EDGR == | == EDGR == | ||
| Line 52: | Line 59: | ||
'''Abstract:''' ''EDGR - Embedded Depth Gesture Recognition. An 8-piece puzzle solved using hand gestures'' | '''Abstract:''' ''EDGR - Embedded Depth Gesture Recognition. An 8-piece puzzle solved using hand gestures'' | ||
| − | ''' | + | '''Poster:''' [http://biron.usc.edu/~sungwonl/EE586/Submission_2012/EDGR.pdf Poster] |
| + | '''Video:''' [http://www.youtube.com/watch?v=CcJajk3dbM4 YouTube Video] | ||
== eMuffler == | == eMuffler == | ||
| Line 61: | Line 69: | ||
'''Abstract:''' ''The objective of the project is to cancel the noise from noisy speech signal using adaptive noise cancellation technique. In this project we use normalized Least Mean Square(NLMS) algorithm to cancel out the noise,which is fed through reference mic, from the noisy speech signal fed through primary mic.'' | '''Abstract:''' ''The objective of the project is to cancel the noise from noisy speech signal using adaptive noise cancellation technique. In this project we use normalized Least Mean Square(NLMS) algorithm to cancel out the noise,which is fed through reference mic, from the noisy speech signal fed through primary mic.'' | ||
| + | '''Poster:''' [http://biron.usc.edu/~sungwonl/EE586/Submission_2012/eMuffler.pdf Poster] | ||
== ExDetect == | == ExDetect == | ||
| Line 68: | Line 77: | ||
'''Abstract:''' ''The human visual system can understand different emotions on face very easily. However, it still needs effort to develop a real-time automated facial expression recognition system with great accuracy and short delay. Here, a real-time facial expression recognition prototype will be developed. The recognition system detect a single face from real-time video sequence and then attempt to recognize a set of emotional expressions including joy, surprise, disgust, anger and neutral. The system is supposed to be response to emotion variation without perceivable delay. First, skin color would be used to trace the face area in video steam and then LBP operator would be performed on divided small blocks of extracted face so that histogram could be computed and cascaded to be a whole feature set. Template matching would be used as classifying method and the outcome would be one of the five predefined emotions.'' | '''Abstract:''' ''The human visual system can understand different emotions on face very easily. However, it still needs effort to develop a real-time automated facial expression recognition system with great accuracy and short delay. Here, a real-time facial expression recognition prototype will be developed. The recognition system detect a single face from real-time video sequence and then attempt to recognize a set of emotional expressions including joy, surprise, disgust, anger and neutral. The system is supposed to be response to emotion variation without perceivable delay. First, skin color would be used to trace the face area in video steam and then LBP operator would be performed on divided small blocks of extracted face so that histogram could be computed and cascaded to be a whole feature set. Template matching would be used as classifying method and the outcome would be one of the five predefined emotions.'' | ||
| − | ''' | + | '''Poster:''' [http://biron.usc.edu/~sungwonl/EE586/Submission_2012/poster_Emotion_Group.pdf Poster] |
| − | |||
== FaceDetc == | == FaceDetc == | ||
| Line 76: | Line 84: | ||
'''Abstract:''' ''real time face detection'' | '''Abstract:''' ''real time face detection'' | ||
| − | |||
| − | |||
| − | |||
== Finger Painting == | == Finger Painting == | ||
| Line 86: | Line 91: | ||
'''Abstract:''' ''With just your fingers you can draw an image and it will apear on an external monitor. By using different hand gestures you can control when to draw, erase or pause and simply track your movements. '' | '''Abstract:''' ''With just your fingers you can draw an image and it will apear on an external monitor. By using different hand gestures you can control when to draw, erase or pause and simply track your movements. '' | ||
| − | ''' | + | '''Poster:''' [http://biron.usc.edu/~sungwonl/EE586/Submission_2012/Finger_Painting.pdf Poster] |
| − | |||
== IRIS(Intelligent Recognition of Individual Signs) == | == IRIS(Intelligent Recognition of Individual Signs) == | ||
| − | '''Authors:''' [mailto:ktadelpal@usc.edu Karthik Tadepalli], [mailto:rameshr@usc.edu Ravishankar Ramesh],[mailto:sudarsha@usc.edu Sharannya | + | '''Authors:''' [mailto:ktadelpal@usc.edu Karthik Tadepalli], [mailto:rameshr@usc.edu Ravishankar Ramesh],[mailto:sudarsha@usc.edu Sharannya Sudarshan] |
'''Abstract:''' ''The project involves detection of the American Sign Language. The 24 static alphabets of the English language are detected using various image processing techniques.'' | '''Abstract:''' ''The project involves detection of the American Sign Language. The 24 static alphabets of the English language are detected using various image processing techniques.'' | ||
| − | ''' | + | '''Poster:''' [http://biron.usc.edu/~sungwonl/EE586/Submission_2012/IRis.pdf Poster] |
| + | '''Video:''' [http://www.youtube.com/watch?v=L9u0uaAl7Wo YouTube Video] | ||
== Magic Face == | == Magic Face == | ||
| Line 104: | Line 109: | ||
'''Abstract:''' ''Our project implements facial expression recognition in real time. Using DSK6416T and camera, human face, eyes and mouth can be tracked and bounding boxes will display on the board. Smile, surprise and neutral expressions can be recognized.'' | '''Abstract:''' ''Our project implements facial expression recognition in real time. Using DSK6416T and camera, human face, eyes and mouth can be tracked and bounding boxes will display on the board. Smile, surprise and neutral expressions can be recognized.'' | ||
| − | ''' | + | '''Poster:''' [http://biron.usc.edu/~sungwonl/EE586/Submission_2012/Magic_Face.pdf Poster] |
| − | |||
== Paper Piano == | == Paper Piano == | ||
| Line 112: | Line 116: | ||
'''Abstract:''' ''The motivation of this project is to implement a virtual piano by using computer vision techniques and TI c6416 DSP processor. Our virtual piano uses a paper keyboard, webcam, and loudspeakers, which can be played as a real piano. The system works for two hands with multiple fingers playing continuously.'' | '''Abstract:''' ''The motivation of this project is to implement a virtual piano by using computer vision techniques and TI c6416 DSP processor. Our virtual piano uses a paper keyboard, webcam, and loudspeakers, which can be played as a real piano. The system works for two hands with multiple fingers playing continuously.'' | ||
| + | |||
| + | '''Poster:''' [http://biron.usc.edu/~sungwonl/EE586/Submission_2012/Pager_Piano.pdf Poster] | ||
'''Video:''' [http://www.youtube.com/watch?v=4SjfzifUMgQ YouTube Video] | '''Video:''' [http://www.youtube.com/watch?v=4SjfzifUMgQ YouTube Video] | ||
| Line 120: | Line 126: | ||
'''Abstract:''' ''This system will give you the best seat in the house, in your house. By using motion tracking to detect performers movements on stage, this system provides the remote viewer with an accurate left/right audio panning to give a full, realistic stereo image of the streaming performance. '' | '''Abstract:''' ''This system will give you the best seat in the house, in your house. By using motion tracking to detect performers movements on stage, this system provides the remote viewer with an accurate left/right audio panning to give a full, realistic stereo image of the streaming performance. '' | ||
| − | |||
| − | |||
| − | |||
== Smart Group == | == Smart Group == | ||
| Line 128: | Line 131: | ||
'''Authors:''' [mailto:lli6@usc.edu Li Li], [mailto:iamxuhao@gmail.com Hao Xu], [mailto:chihocho@usc.edu Chiho Choi] | '''Authors:''' [mailto:lli6@usc.edu Li Li], [mailto:iamxuhao@gmail.com Hao Xu], [mailto:chihocho@usc.edu Chiho Choi] | ||
| − | '''Abstract:''' ''Gaze Tracking. | + | '''Abstract:''' ''Gaze Tracking.'' |
| − | ''' | + | '''Poster:''' [http://biron.usc.edu/~sungwonl/EE586/Submission_2012/Gaze_Tracking.pdf Poster] |
| + | '''Video:''' [http://www.youtube.com/watch?v=xw2-LuFPtuw YouTube Video] | ||
== Theia == | == Theia == | ||
| Line 138: | Line 142: | ||
'''Abstract:''' ''It is a system that tries to extract characters from any surface and convert it into corresponding Braille symbols in an attempt to be a Portable Braille Aid.'' | '''Abstract:''' ''It is a system that tries to extract characters from any surface and convert it into corresponding Braille symbols in an attempt to be a Portable Braille Aid.'' | ||
| − | |||
== Trojan DJs == | == Trojan DJs == | ||
| Line 146: | Line 149: | ||
'''Abstract:''' ''We have developed a gesture based DJ system, which will do audio processing tasks like equalization, stereo panning, cross fading, and pitch variation corresponding to the gestures detected by our system based on Kinect & DM6437 DSP.'' | '''Abstract:''' ''We have developed a gesture based DJ system, which will do audio processing tasks like equalization, stereo panning, cross fading, and pitch variation corresponding to the gestures detected by our system based on Kinect & DM6437 DSP.'' | ||
| − | ''' | + | '''Poster:''' [http://biron.usc.edu/~sungwonl/EE586/Submission_2012/Interactive_DJ.pdf Poster] |
| − | |||
== Video Photoshop == | == Video Photoshop == | ||
| Line 155: | Line 157: | ||
'''Abstract:''' ''Video Photoshop is not only transfering the special function of the software of Photoshop to the DSP board and appling it to input frames. More than that, we are exploring the capability of the DAVINCI and trying to understand and implement video processing under a limited memory and computation power. Our goal is to make the special effects vivid and close to real time as much as possible.'' | '''Abstract:''' ''Video Photoshop is not only transfering the special function of the software of Photoshop to the DSP board and appling it to input frames. More than that, we are exploring the capability of the DAVINCI and trying to understand and implement video processing under a limited memory and computation power. Our goal is to make the special effects vivid and close to real time as much as possible.'' | ||
| − | ''' | + | '''Poster:''' [http://biron.usc.edu/~sungwonl/EE586/Submission_2012/Video_PhotoShop.pdf Poster] |
| − | |||
== Visual Object == | == Visual Object == | ||
| Line 164: | Line 165: | ||
'''Abstract:''' ''Virtual Object inserts a virtual object into the video feed captured by the camera. First, an object of known shape and size is placed in a fixed location in the real scene. Using the POSIT algorithm, our code detects the object feature points and reaches an estimate of the relative camera pose in 3D space. Finally, the Virtual Object is drawn to the output video accordingly.'' | '''Abstract:''' ''Virtual Object inserts a virtual object into the video feed captured by the camera. First, an object of known shape and size is placed in a fixed location in the real scene. Using the POSIT algorithm, our code detects the object feature points and reaches an estimate of the relative camera pose in 3D space. Finally, the Virtual Object is drawn to the output video accordingly.'' | ||
| − | ''' | + | '''Poster:''' [http://biron.usc.edu/~sungwonl/EE586/Submission_2012/VirtualObjectposter.pdf Poster] |
Latest revision as of 00:22, 20 December 2012
Contents
- 1 Arrow In The Knee
- 2 AudioSense
- 3 Chessboard Game
- 4 Digit(al) Calculator
- 5 Dodge the Rock
- 6 Duck Hunters
- 7 EDGR
- 8 eMuffler
- 9 ExDetect
- 10 FaceDetc
- 11 Finger Painting
- 12 IRIS(Intelligent Recognition of Individual Signs)
- 13 Magic Face
- 14 Paper Piano
- 15 Realistic Remote Viewing
- 16 Smart Group
- 17 Theia
- 18 Trojan DJs
- 19 Video Photoshop
- 20 Visual Object
Arrow In The Knee
Authors: Ying Wu, Zhi Tong, Junyuan Shi
Abstract: Video based American Sign Language Recognition using color detection and motion tracking.
AudioSense
Authors: Varun Nasery, Rohit Khaladkar, Gaurav Savadi
Abstract: A gesture recognition based audio system is implemented. Hand gestures are used to increase/decrease volume, change tracks, mute/unmute the track, play, pause and time seek.
Poster: Poster
Chessboard Game
Authors: Ming Qu, YuanYang, Huishu Shi
Abstract: Our project implements image processing techniques in real time by using the TI c6416 DSP processor and CCS system. We use a camera, a paper chessboard and two fingerstalls to simulate the process of playing chess between two players. The project works well in real time.
PPT: PPT
Video: YouTube Video
Digit(al) Calculator
Authors: Anil Sunil,Chetan Bhadrashette,Sarthak Sahu
Abstract: Automatic recognition of sign language is an important research problem for communication. Real-time image processing can provide much better experience than using a touch based system. Our project implements a basic calculator using gesture recognition methods. It can be very useful to use this calculator by using gestures for numbers and symbols such as addition, subtraction, multiplication and division, without pressing any buttons or typing anything.
Poster: Poster
Dodge the Rock
Authors: Peiran Gong, Haowei Tseng, Bo Zhang
Abstract: We are doing a interactive game based on gesture recognition.
Poster: Poster
Video: YouTube Video
Duck Hunters
Authors: Madhur Ahuja, Pushkar Waghulde,Sahil Shrivastava
Abstract: The name says it all. We all miss the Nintendo games from the 90's, so in an attempt to refresh your memories we re-created the game but this one does not need a zapper gun, you can use a rod to project a point on the screen and we didn't change the rules either.
Poster: Poster
Video: YouTube Video
EDGR
Authors: Aditya Tannu, Michael Minkler, Joshua Ramos
Abstract: EDGR - Embedded Depth Gesture Recognition. An 8-piece puzzle solved using hand gestures
Poster: Poster
Video: YouTube Video
eMuffler
Authors: Kiran Nandanan, Rajesh Bisoi
Abstract: The objective of the project is to cancel the noise from noisy speech signal using adaptive noise cancellation technique. In this project we use normalized Least Mean Square(NLMS) algorithm to cancel out the noise,which is fed through reference mic, from the noisy speech signal fed through primary mic.
Poster: Poster
ExDetect
Authors: Yixin Shi, Qinwen Xu,Zhanpeng Yi
Abstract: The human visual system can understand different emotions on face very easily. However, it still needs effort to develop a real-time automated facial expression recognition system with great accuracy and short delay. Here, a real-time facial expression recognition prototype will be developed. The recognition system detect a single face from real-time video sequence and then attempt to recognize a set of emotional expressions including joy, surprise, disgust, anger and neutral. The system is supposed to be response to emotion variation without perceivable delay. First, skin color would be used to trace the face area in video steam and then LBP operator would be performed on divided small blocks of extracted face so that histogram could be computed and cascaded to be a whole feature set. Template matching would be used as classifying method and the outcome would be one of the five predefined emotions.
Poster: Poster
FaceDetc
Authors: Li Cheng,Jinghan Xu,Xin Wei
Abstract: real time face detection
Finger Painting
Authors: Carlos Figueroa, Deniz Kumlu, Bahri Maras
Abstract: With just your fingers you can draw an image and it will apear on an external monitor. By using different hand gestures you can control when to draw, erase or pause and simply track your movements.
Poster: Poster
IRIS(Intelligent Recognition of Individual Signs)
Authors: Karthik Tadepalli, Ravishankar Ramesh,Sharannya Sudarshan
Abstract: The project involves detection of the American Sign Language. The 24 static alphabets of the English language are detected using various image processing techniques.
Poster: Poster
Video: YouTube Video
Magic Face
Authors: Jinkai Wang,Ya Cao,Yao Lin
Abstract: Our project implements facial expression recognition in real time. Using DSK6416T and camera, human face, eyes and mouth can be tracked and bounding boxes will display on the board. Smile, surprise and neutral expressions can be recognized.
Poster: Poster
Paper Piano
Authors: Hang Dong, Dana Morgenstern, Yu Rong
Abstract: The motivation of this project is to implement a virtual piano by using computer vision techniques and TI c6416 DSP processor. Our virtual piano uses a paper keyboard, webcam, and loudspeakers, which can be played as a real piano. The system works for two hands with multiple fingers playing continuously.
Poster: Poster
Video: YouTube Video
Realistic Remote Viewing
Authors: Tim Brochier, Lucas Vollherbst
Abstract: This system will give you the best seat in the house, in your house. By using motion tracking to detect performers movements on stage, this system provides the remote viewer with an accurate left/right audio panning to give a full, realistic stereo image of the streaming performance.
Smart Group
Authors: Li Li, Hao Xu, Chiho Choi
Abstract: Gaze Tracking.
Poster: Poster
Video: YouTube Video
Theia
Authors: Sooyong Ryu,Saranyaraj Rajendran
Abstract: It is a system that tries to extract characters from any surface and convert it into corresponding Braille symbols in an attempt to be a Portable Braille Aid.
Trojan DJs
Authors: Hasan Sayani, Pavankumar Vasu, Nikhil Parab
Abstract: We have developed a gesture based DJ system, which will do audio processing tasks like equalization, stereo panning, cross fading, and pitch variation corresponding to the gestures detected by our system based on Kinect & DM6437 DSP.
Poster: Poster
Video Photoshop
Authors: Xiaqing Pan,Linlin Zhang,Chen Chen
Abstract: Video Photoshop is not only transfering the special function of the software of Photoshop to the DSP board and appling it to input frames. More than that, we are exploring the capability of the DAVINCI and trying to understand and implement video processing under a limited memory and computation power. Our goal is to make the special effects vivid and close to real time as much as possible.
Poster: Poster
Visual Object
Authors: Shira Epstein, Will Chung
Abstract: Virtual Object inserts a virtual object into the video feed captured by the camera. First, an object of known shape and size is placed in a fixed location in the real scene. Using the POSIT algorithm, our code detects the object feature points and reaches an estimate of the relative camera pose in 3D space. Finally, the Virtual Object is drawn to the output video accordingly.
Poster: Poster
