Gesture recognition apparatus and method thereof
First Claim
Patent Images
1. A gesture recognition apparatus comprising:
- a first detector configured to detect a detection area including a portion of a body of an operator in a first image of a motion image captured at a first resolution;
a second detector configured to detect an auxiliary area including an auxiliary portion used for detecting the portion in a second image of the motion image captured at the first resolution when the detection area cannot be detected from the first image of the motion image;
a physical controller configured to control, when the auxiliary area is detected, a capturing unit to capture a third image of the motion image, which is an image in the frame next to the second image and is captured at a second resolution higher than the first resolution, by capturing an area estimated from a predetermined positional relationship between the portion of a body and the auxiliary portion;
a third detector configured to detect the detection area in the third image; and
a gesture recognizer configured to recognize a gesture of the portion based on an entire area of the first image when the detection area is detected from the first image and based on the detection area of the third image when the detection area cannot be detected from the first image.
4 Assignments
0 Petitions
Accused Products
Abstract
A gesture recognition apparatus including a detector, a controller and a gesture recognizer, and is able to detect a portion to be detected using an image captured at a first resolution without reducing the number of images to be entered per unit of time to an object detector by detecting an auxiliary portion instead when the portion to be detected is not detected at a second resolution, estimating the position of the auxiliary portion based on the position of the auxiliary portion, and extracting the periphery thereof from the image captured at the first resolution.
8 Citations
11 Claims
-
1. A gesture recognition apparatus comprising:
-
a first detector configured to detect a detection area including a portion of a body of an operator in a first image of a motion image captured at a first resolution; a second detector configured to detect an auxiliary area including an auxiliary portion used for detecting the portion in a second image of the motion image captured at the first resolution when the detection area cannot be detected from the first image of the motion image; a physical controller configured to control, when the auxiliary area is detected, a capturing unit to capture a third image of the motion image, which is an image in the frame next to the second image and is captured at a second resolution higher than the first resolution, by capturing an area estimated from a predetermined positional relationship between the portion of a body and the auxiliary portion; a third detector configured to detect the detection area in the third image; and a gesture recognizer configured to recognize a gesture of the portion based on an entire area of the first image when the detection area is detected from the first image and based on the detection area of the third image when the detection area cannot be detected from the first image. - View Dependent Claims (2, 3, 4, 5, 6, 9, 10, 11)
-
-
7. A computer-implemented method of recognizing gestures comprising:
-
detecting a detection area including a portion of a body of an operator in a first image of a motion image captured at a first resolution; detecting an auxiliary area including an auxiliary portion used for detecting the portion in a second image of the motion image captured at the first resolution when the detection area cannot be detected from the first image of the motion image; controlling, when the auxiliary area is detected and using a physical controller, a capturing unit to capture a third image of the motion image, which is an image in the frame next to the second image and is captured at a second resolution higher than the first resolution, by capturing an area estimated from a predetermined positional relationship between the portion of the body and the auxiliary portion; detecting the detection area in the third image; and recognizing a gesture of the portion based on an entire area of the first image when the detection area is detected from the first image and based on the detection area of the third image when the detection area cannot be detected from the first image.
-
-
8. A non-transitory computer-readable medium storing a set of instructions that when executed by processor perform a method, the method comprising:
-
detecting a detection area including a portion of a body of an operator in a first image of a motion image captured at a first resolution; detecting an auxiliary area including an auxiliary portion used for detecting the portion in a second image of the motion image captured at the first resolution when the detection area cannot be detected from the first image of the motion image; controlling, when the auxiliary area is detected and using a physical controller, a capturing unit to capture a third image of the motion image, which is an image in the frame next to the second image and is captured at a second resolution higher than the first resolution by capturing an area estimated from a predetermined positional relationship between the portion of the a body and the auxiliary portion; detecting the detection area in the third image; and recognizing a gesture of the portion based on an entire area of the first image when the detection area is detected from the first image and based on the detection area of the third image when the detection area cannot be detected from the first image.
-
Specification