Gesture recognition technology
- 1. SEMINAR (CS-307) Presentation on: Gesture Recognition Technology SUBMITTED TO: Prof. Pragya Jain CS/IT Department SUBMITTED BY: Aishwarya Bharadwaj 0903CS121008 MAHARANA PRATAP COLLEGE OF TECHNOLOGY
- 3. Introduction Gesture recognition is a topic in Computer Science and language technology with the goal of interpreting human gestures via mathematical Algorithms. It can be seen as a way for computers to begin to understand human body language, thus building a richer bridge between machines and humans than primitive text user interfaces or even GUIs , which still limit the majority of input to keyboards and mouse.
- 4. Contents 1. Gesture Types 2. Uses 3. Input Devices 4. Algorithms 5. 3-D Model based algorithms 6. Skeletal based algorithms 7. Appearance based algorithms 8. Disadvantages
- 5. Gesture Types In computer interfaces, two types of gestures are distinguished : Online gestures: We consider online gestures, which can also be regarded as direct manipulation gestures They are used to scale or rotate a tangible object. Offline gestures: Those gestures that are processed after the user interaction with the object. e. g. a circle is drawn to activate a context menu.
- 6. Uses Sign Language Recognition For socially assistive robotics Directional indication through pointing Alternative computer interfaces Immersive Game technology Virtual Controllers Affective Computing Remote control
- 7. Input Devices Wired Gloves: They can detect finger bending with a high degree of accuracy (5-10 degrees).The first hand- tracking device was Data Glove. Uses optical wires. Depth-aware Cameras: One can generate a depth map of what is being seen at a short range. Stereo Cameras: Using two cameras whose relations to one another are known, we can get a 3-D representation Controller-based gestures: These controllers act as an extension of the body so that when gestures are performed, some of their motion can be captured by the software.
- 8. Algorithms
- 9. 3-D Model based Algorithms • A more interesting approach would be to map simple primitive objects to the person’s most important body parts ( for example cylinders for the arms and neck, sphere for the head) and analyse the way these interact with each other. Furthermore, some abstract structures like super- quadrics and generalised cylinders may be even more suitable for approximating the body parts. • A real hand (left) is interpreted as a collection of vertices and lines in the 3D mesh version (right), and the software uses their relative position and interaction in order to infer the gesture.
- 10. Skeletal based Algorithms Instead of using intensive processing of the 3D models and dealing with a lot of parameters, one can just use a simplified version of joint angle parameters along with segment lengths. This is known as a skeletal representation of the body, where a virtual skeleton of the person is computed and parts of the body are mapped to certain segments. The skeletal version (right) is effectively modelling the hand (left). This has fewer parameters than the volumetric version and it's easier to compute, making it suitable for real-time gesture analysis systems
- 11. Appearance- based Algorithms These models don’t use a spatial representation of the body anymore, because they derive the parameters directly from the images or videos using a template database. Some are based on the deformable 2D templates of the human parts of the body, particularly hands. Deformable templates are sets of points on the outline of an object, used as interpolation nodes for the object’s outline approximation. These template-based models are mostly used for hand-tracking, but could also be of use for simple gesture classification. Second approach is image sequences . Parameters for this method are either the images themselves, or certain features derived from these. • These binary silhouette(left) or contour(right) images represent typical input for appearance-based algorithms. They are compared with different hand templates and if they match, the correspondent gesture is inferred.
- 12. Disadvantage There are many challenges associated with the accuracy and usefulness of Gesture Recognition Software. For image-based gesture recognition there are limitations on the equipment used. Items in the background or distinct features of the users may make recognition more difficult. The distance from the camera and camera’s resolution and quality also cause variations in recognition accuracy. Gorilla arm: In periods of prolonged use, users’ arm began to feel discomfort.
- 14. Touchable wind energy GE has been active in Germany for over 100 yrs. For the first time ever the innovative GRT was used to translate the movements of the participants’ arms into moving virtual wind turbines on a multiple HD video wall. The promoters invited travelers at Frankfurt Airport to generate virtual wind energy.
- 15. Interactive Floors and Walls!! GestureFX is one of the world’s most advanced GRT for motion-control interactive displays, signs and surfaces. It’s patented body tracking technology responds to body movement to project dynamic interactive multimedia content, special effects, interactive advertising or games onto any surface.
- 16. Virtual Guitar!! The user’s actions are read by the input device, such as a webcam and passed through gesture recognition. A musical intelligence module interprets these gestures and sends commands to the sound model, which produces final sound
- 17. CONCLUSION Improvements and Future: Gesture recognition algorithm is relatively durable and accurate. Convolution can be slow, so there is tradeoff between speed and accuracy. This computing is not only going to reduce the hardware impact of the system but also it increases the range of usage of physical world object instead of digital objects like keyboards, mouse.
- 18. THANK YOU