Localisation and mapping
First Claim
1. A method of generating a three-dimensional map of a region from successive images of the region captured from different camera poses, the map comprising a set of landmark points each defined by a three dimensional spatial position and image information associated with the three dimensional spatial position, the method comprising:
- capturing successive images of the region using a camera;
detecting, by a processor, feature points within the captured images;
designating, by the processor, a subset of the captured images as a set of keyframes each having respective sets of image position data representing image positions of landmark points detected as feature points in that image;
detecting, by the processor, an angular velocity of the camera between a previous image and a current image of the successive images using at least one of (i) one or more accelerometers, or (ii) one or more gyroscopes;
in respect of a newly captured image, detecting, by the processor, a pose of the camera by detecting the position of landmark points in the newly captured image, the detecting step comprising;
integrating the angular velocity of the camera since the previous image was captured to obtain an estimated rotation; and
predicting the positions of the landmark points in the newly captured image from the estimated rotation and the position of the landmark points in the previous image.
2 Assignments
0 Petitions
Accused Products
Abstract
A method generates a three-dimensional map of a region from successive images of that region captured from different camera poses. The method captures successive images of the region, detects a gravitational vertical direction in respect of each captured image, detects feature points within the captured images and designates a subset of the captured images as a set of keyframes each having respective sets of image position data representing image positions of landmark points detected as feature points in that image. The method also includes, for a captured image (i) deriving a camera pose from detected feature points in the image; (ii) rotating the gravitational vertical direction to the coordinates of a reference keyframe using the camera poses derived for that image and the reference keyframe; and (iii) comparing the rotated direction with the actual gravitational vertical direction for the reference keyframe to detect a quality measure of that image.
-
Citations
19 Claims
-
1. A method of generating a three-dimensional map of a region from successive images of the region captured from different camera poses, the map comprising a set of landmark points each defined by a three dimensional spatial position and image information associated with the three dimensional spatial position, the method comprising:
-
capturing successive images of the region using a camera; detecting, by a processor, feature points within the captured images; designating, by the processor, a subset of the captured images as a set of keyframes each having respective sets of image position data representing image positions of landmark points detected as feature points in that image; detecting, by the processor, an angular velocity of the camera between a previous image and a current image of the successive images using at least one of (i) one or more accelerometers, or (ii) one or more gyroscopes; in respect of a newly captured image, detecting, by the processor, a pose of the camera by detecting the position of landmark points in the newly captured image, the detecting step comprising; integrating the angular velocity of the camera since the previous image was captured to obtain an estimated rotation; and predicting the positions of the landmark points in the newly captured image from the estimated rotation and the position of the landmark points in the previous image. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A non-transitory computer readable medium storing computer instructions thereon, the instructions, when executed by a processor, cause the processor to carry out a method of generating a three-dimensional map of a region from successive images of the region captured from different camera poses, the map comprising a set of landmark points each defined by a three dimensional spatial position and image information associated with the three dimensional spatial position, the method comprising:
-
capturing successive images of the region using a camera; detecting feature points within the captured images; designating a subset of the captured images as a set of keyframes each having respective sets of image position data representing image positions of landmark points detected as feature points in that image; detecting an angular velocity of the camera between a previous image and a current image of the successive images using at least one of (i) one or more accelerometers, or (ii) one or more gyroscopes; in respect of a newly captured image, detecting a pose of the camera by detecting the position of landmark points in the newly captured image, the detecting step comprising; integrating the angular velocity of the camera since the previous image was captured to obtain an estimated rotation; and predicting the positions of the landmark points in the newly captured image from the estimated rotation and the position of the landmark points in the previous image.
-
-
8. An image processing apparatus configured to generate a three-dimensional map of a region from successive images of the region captured from different camera poses, the map comprising a set of landmark points each defined by a three dimensional spatial position and image information associated with the three dimensional position, a subset of the captured images being designated as a set of keyframes each having respective sets of image position data representing image positions of landmark points detected as feature points in that image, wherein the image processing apparatus comprises:
-
a camera configured to capture successive images of the region using, the camera having an associated angular velocity detector configured to detect an angular velocity of the camera between a previous image and a current image of the successive images using at least one of (i) one or more accelerometers, or (ii) one or more gyroscopes; and a camera pose detector configured, in respect of a newly captured image, to detect a pose of the camera according to the position of landmark points in the newly captured image, the camera pose detector being configured to integrate an angular velocity of the camera since the previous image was captured to obtain an estimated rotation, and to predict the position of the landmark points in the newly captured image from the estimated rotation and the position of the landmark points in the previous image. - View Dependent Claims (9, 10, 11, 12, 13)
-
-
14. A computer games apparatus comprising:
an image processing apparatus configured to generate a three-dimensional map of a region from successive images of the region captured from different camera poses, the map comprising a set of landmark points each defined by a three dimensional spatial position and image information associated with the three dimensional position, a subset of the captured images being designated as a set of keyframes each having respective sets of image position data representing image positions of landmark points detected as feature points in that image, wherein the image processing apparatus comprises; a camera configured to capture successive images of the region using a camera, the camera having an associated angular velocity detector configured to detect an angular velocity of the camera between a previous image and a current image of the successive images using at least one of (i) one or more accelerometers, or (ii) one or more gyroscopes; a camera pose detector configured, in respect of a newly captured image, to detect a pose of the camera according to the position of landmark points in the newly captured image, the camera pose detector being configured to integrate an angular velocity of the camera since the previous image was captured to obtain an estimated rotation, and to predict the position of the landmark points in the newly captured image from the estimated rotation and the position of the landmark points in the previous image; and an image renderer configured to render an image for display by combining a captured image with one or more computer-generated image portions generated with respect to map positions associated with feature points of the captured image. - View Dependent Claims (15, 16, 17, 18, 19)
Specification