Gesture recognition in vehicles
A method and system for performing gesture recognition of a vehicle occupant employing a time of flight (TOF) sensor and a computing system in a vehicle. An embodiment of the method of the invention includes the steps of receiving one or more raw frames from the TOF sensor, performing clustering to locate one or more body part clusters of the vehicle occupant, calculating the location of the tip of the hand of the vehicle occupant, determining whether the hand has performed a dynamic or a static gesture, retrieving a command corresponding to one of the determined static or dynamic gestures, and executing the command.
1. A method for performing gesture recognition in a vehicle, comprising the steps of:
receiving one or more raw frames from a camera of a vehicle occupant;
performing clustering to determine one or more portions of interest of the vehicle occupant; defining one or more predetermined search spaces in accordance with the location of one
or more of the one or more portions of interest of the vehicle occupant;
defining one or more partition spaces within the one or more search spaces; and
locating one or more of the one or more portions of interest of the vehicle occupant within the partition and search spaces.
2. The method of claim 1 , further comprising the step of cleaning a depth data of each of the one or more raw frames.
3. The method of claim 1 , further comprising the steps of:
observing whether the one or more of the one or more portions of interest of the vehicle occupant has performed a dynamic or a static gesture;
if the one or more of the one or more portions of interest of the vehicle occupant has performed a dynamic gesture, matching the observed gesture with a set of known masks to determine an intended static gesture; and
if the one or more of the one or more portions of interest of the vehicle occupant has performed a dynamic gesture, extracting features from one or more clips of the observed gesture and match with one or more predefined motion streams to determine an intended dynamic gesture.
4. The method of claim 3 , further comprising the steps of:
retrieving a command corresponding to one of the determined static and dynamic gesture; and
executing the command.
5. The method of claim 4 , wherein the command is executed in accordance with a computing system and display within the vehicle.
6. The method of claim 3 , wherein the known masks are determined for a particular individual vehicle occupant.
7. The method of claim 3 , wherein the predefined motion streams are determined for a particular individual vehicle occupant.
8. The method of claim 1 , further comprising the step of selecting the vehicle occupant from among a plurality of individuals in the vehicle.
9. The method of claim 1 , wherein a processor is adapted to determine the vehicle occupant from among two or more individuals in the vehicle.
10. A method for performing gesture recognition of a vehicle occupant employing a camera sensor and a computing system in a vehicle, comprising the steps of:
receiving one or more raw frames from the camera sensor;
performing clustering to locate one or more body part clusters of the vehicle occupant; defining one or more predetermined search spaces in accordance with the location of one
or more of the one or more body part clusters of the vehicle occupant;
defining one or more partition spaces within the one or more search spaces; and
locating one or more of the one or more body part clusters within the partition and search spaces;
determining whether the one or more located body part clusters has performed a dynamic or a static gesture;
retrieving a command corresponding to one of the determined static and dynamic gesture; and
executing the command.
11. A system for performing gesture recognition in
a vehicle, comprising: a camera for providing one or more raw frames of a vehicle occupant; and
a processor for performing clustering to determine one or more objects of interest of the vehicle occupant, calculating a location of one or more portions of the vehicle occupant, defining one or more predetermined search spaces in accordance with the location of the one or more portions of the vehicle occupant, defining one or more partition spaces within the one or more search spaces, and locating the one or more portions of the vehicle occupant within the partition and search spaces.
12. The system of claim 11 , wherein the processor is further adapted to clean a depth data of each of the one or more raw frames.
13. The system of claim 11 , wherein the processor is further adapted to observe whether the one or more portions of the vehicle occupant has performed a dynamic or a static gesture, if the one or more portions of the vehicle occupant has performed a dynamic gesture, match the observed gesture with a set of known masks to determine an intended static gesture, and if the one or more portions of the vehicle occupant has performed a dynamic gesture, extract features from one or more clips of the observed gesture and match with one or more predefined motion streams to determine an intended dynamic gesture.
14. The system of claim 13 , wherein the processor is further adapted to retrieve a command corresponding to one of the determined static and dynamic gesture, and execute the command to perform one or more vehicle actions.
15. The system of claim 14 , further comprising a computing system for implementing the command.
16. The system of claim 15 , wherein the computing system further comprises a display for displaying a response to the command to the vehicle occupant.
17. The system of claim 13 , wherein the processor is adapted to determine the known masks for a particular individual vehicle occupant.
18. The system of claim 13 , wherein the processor is adapted to determine the predefined motion streams for a particular individual vehicle occupant.