Method and device for detecting an object
View Patent ↗It is provided a method for detecting an object in a left view image and a right view image, comprising steps of receiving the left view image and the right view image; detecting a coarse region containing the object in one image of the left view image and the right view image; detecting the object within the detected coarse region in the one image; determining a coarse region in the other image of the left view image and the right view image based on the detected coarse region in the one image and offset relationship indicating position relationship of the object in a past left view image and a past right view image; and detecting the object within the determined coarse region in the other image.
1. A method for determining an eye gaze from a pair of eyes of a face in a left view image and a right view image, comprising:
detecting a rectangle coarse region containing the face in one of the left view image and the right view image;
detecting the face within the detected rectangle coarse region in the one of the left view image and the right view image
determining a rectangle coarse region in the other of the left view image and the right view image based on the detected rectangle coarse region in the one of the left view image and the right view image and offset relationship indicating position relationship of the face in a past left view image and a past right view image;
detecting the face within the determined rectangle coarse region in the other of the left view image and the right view image; and
detecting the pair of eyes in the detected face in the other of the left view image and the right view image to determine the eye gaze.
2. The method of the claim 1 , further comprising
determining offset relationship of the face in the left view image and right view image based on the detected face in the left view image and the detected face in the right view image.
3. The method of the claim 1 , wherein the past left view image is a previous left view image and the past right view image is a previous right view image, the method further comprising
determining offset relationship of the face in the left view image and right view image based on the detected face in the left view image and the detected face in the right view image.
4. A device for determining an eye gaze from a pair of eyes of a face in a left view image and a right view image, comprising:
a storage for storing offset relationship indicating position relationship of the face in a past left view image and a past right view image; and
a processor configured to:
detect a rectangle coarse region containing the face in one of the left view image and the right view image; detecting the face within the detected coarse region in the one of the left view image and the right view image;
determine a rectangle coarse region in the other of the left view image and the right view image based on the detected rectangle coarse region in the one of the left view image and the right view image and offset relationship indicating position relationship of the object in a past left view image and a past right view image;
detect the face within the determined rectangle coarse region in the other of the left view image and the right view image; and
detect the pair of eyes in the detected face in the other of the left view image and the right view image to determine the eye gaze.
5. The device of the claim 4 , further comprising a 3D camera for capturing and outputting the left view image and the right view image.
6. The device of the claim 4 , wherein the processor is further configured to determine offset relationship of the face in the left view image and right view image based on the detected face in the left view image and the detected face in the right view image.
7. The device of the claim 4 , wherein the past left view image is a previous left view image and the past right view image is a previous right view image, the processor is further configured to determine offset relationship of the face in the left view image and right view image based on the detected face in the left view image and the detected face in the right view image.