Detecting and tracking objects in images

A computer program product, tangibly embodied in a machine readable medium, the computer program product comprising instructions that, when read by a machine, operate to cause data processing apparatus to:

• detect, using electromagnetic radiation projected proximally to a surface, at least first and second objects adjacent to the surface;
• recognize, using a trained recognition model, the first and second objects, the recognition model being trained to recognize the first and second objects based on an appearance of the first and second objects;
• designate one of the at least first and second objects as a control object based on having recognized the first and second objects;
• and
• generate a user input to a computer application using the control object.

A computer program product, tangibly embodied in a machine readable medium, the computer program product comprising instructions that, when read by a machine, operate to cause data processing apparatus to:

• detect, using electromagnetic radiation projected proximally to a surface, at least first and second objects in the vicinity of the surface;
• recognize, using a trained recognition model, the first and second objects, the recognition model being trained to recognize the first and second objects based on an appearance of the first and second objects;
• and
• generate a user input to a computer application based on the recognized first and second object.

A computer program product, tangibly embodied in a machine readable medium, the computer program product comprising instructions that, when read by a machine, operate to cause data processing apparatus to:

• detect, using electromagnetic radiation projected proximally to a surface, at least first and second objects touching the surface;
• recognize, using a trained recognition model, the at least first and second objects as control objects, the recognition model being trained to identify the control objects based on an appearance of the at least first and second objects;
• and
• generate, using the control objects, a user input to a computer application.

A computer program product, tangibly embodied in a machine readable medium, the computer program product comprising instructions that, when read by a machine, operate to cause data processing apparatus to:

• detect, using electromagnetic radiation projected proximally to a surface, an input object touching the surface;
• compare the input object to a modeled input set of training images of a control object, the input set being modeled as a cone and a tail in an eigenspace;
• determine whether the detected object is the control object based on comparing the input object to the modeled cone or tail;
• and
• generate a user input to a computer application based on the detected object, if it is determined that the detected object is the control object.

A computer program product, tangibly embodied in a machine readable medium, the computer program product comprising instructions that, when read by a machine, operate to cause data processing apparatus to:

• detect, using electromagnetic radiation projected proximally to a surface, an input object touching the surface;
• compare the input object to a modeled input set of training images of a control object, the input set being modeled in an eigenspace using a general equation for a three-dimensional quadratic surface;
• determine whether the detected object is the control object based on comparing the input object to the modeled input set;
• and
• generate a user input to a computer application based on the detected object, if it is determined that the detected object is the control object.

A method comprising:

• detecting, using electromagnetic radiation projected proximally to a surface, an object touching the surface;
• determining whether the detected object is of a predetermined object type using a trained recognition model implemented on a processing device, the recognition model being trained to determine whether the detected object is of the predetermined object type based on an appearance of the detected object;
• and
• generating, using a processing device, a user input to a computer application based on the detected object, if it is determined that the detected object is of the predetermined object type.

A system comprising one or more processing devices configured to:

• detect, using electromagnetic radiation projected proximally to a surface, an object touching the surface;
• determine whether the detected object is of a predetermined object type using a trained recognition model, the recognition model being trained to determine whether the detected object is of the predetermined object type based on an appearance of the detected object;
• and
• generate a user input to a computer application based on the detected object, if it is determined that the detected object is of the predetermined object type.

A method comprising:

• detecting, using electromagnetic radiation projected proximally to a surface, at least first and second objects adjacent to the surface;
• recognizing, using a trained recognition model implemented on a processing device, the first and second objects, the recognition model being trained to recognize the first and second objects based on an appearance of the first and second objects;
• designating, using a processing device, one of the at least first and second objects as a control object based on having recognized the first and second objects;
• and
• generating, using a processing device, a user input to a computer application based on the control object.

A system comprising one or more processing devices configured to:

• detect, using electromagnetic radiation projected proximally to a surface, at least first and second objects adjacent to the surface;
• recognize, using a trained recognition model, the first and second objects, the recognition model being trained to recognize the first and second objects based on an appearance of the first and second objects;
• designate one of the at least first and second objects as a control object based on having recognized the first and second objects;
• and
• generate a user input to a computer application using the control object.

A method comprising:

• detecting, using electromagnetic radiation projected proximally to a surface, at least first and second objects in the vicinity of the surface;
• recognizing, using a trained recognition model implemented on a processing device, the first and second objects, the recognition model being trained to recognize the first and second objects based on an appearance of the first and second objects;
• and
• generating, using a processing device, a user input to a computer application based on the recognized first and second object.

A system comprising one or more processing devices configured to:

• detect, using electromagnetic radiation projected proximally to a surface, at least first and second objects in the vicinity of the surface;
• recognize, using a trained recognition model, the first and second objects, the recognition model being trained to recognize the first and second objects based on an appearance of the first and second objects;
• and
• generate a user input to a computer application based on the recognized first and second object.

A method comprising:

• detecting, using electromagnetic radiation projected proximally to a surface, at least first and second objects touching the surface;
• recognizing, using a trained recognition model implemented on a processing device, the at least first and second objects as control objects, the recognition model being trained to identify the control objects based on an appearance of the at least first and second objects;
• and
• generating, using a processing device, a user input to a computer application based on the control objects.

A system comprising one or more processing devices configured to:

• detect, using electromagnetic radiation projected proximally to a surface, at least first and second objects touching the surface;
• recognize, using a trained recognition model, the at least first and second objects as control objects, the recognition model being trained to identify the control objects based on an appearance of the at least first and second objects;
• and
• generate, using the control objects, a user input to a computer application.

A method comprising:

• detecting, using electromagnetic radiation projected proximally to a surface, an input object touching the surface;
• comparing, using a processing device, the input object to a modeled input set of training images of a control object, the input set being modeled as a cone and a tail in an eigenspace;
• determining, using a processing device, whether the detected object is the control object based on comparing the input object to the modeled cone or tail;
• and
• generating, using a processing device, a user input to a computer application based on the detected object, if it is determined that the detected object is the control object.

A system comprising one or more processing devices configured to:

• detect, using electromagnetic radiation projected proximally to a surface, an input object touching the surface;
• compare the input object to a modeled input set of training images of a control object, the input set being modeled as a cone and a tail in an eigenspace;
• determine whether the detected object is the control object based on comparing the input object to the modeled cone or tail;
• and
• generate a user input to a computer application based on the detected object, if it is determined that the detected object is the control object.

A method comprising:

• detecting, using electromagnetic radiation projected proximally to a surface, an input object touching the surface;
• comparing, using a processing device, the input object to a modeled input set of training images of a control object, the input set being modeled in an eigenspace using a general equation for a three-dimensional quadratic surface;
• determining, using a processing device, whether the detected object is the control object based on comparing the input object to the modeled input set;
• and
• generating, using a processing device, a user input to a computer application based on the detected object, if it is determined that the detected object is the control object.

A system comprising one or more processing devices configured to:

• detect, using electromagnetic radiation projected proximally to a surface, an input object touching the surface;
• compare the input object to a modeled input set of training images of a control object, the input set being modeled in an eigenspace using a general equation for a three-dimensional quadratic surface;
• determine whether the detected object is the control object based on comparing the input object to the modeled input set;
• and
• generate a user input to a computer application based on the detected object, if it is determined that the detected object is the control object.