SIMULTANEOUS LOCALIZATION AND MAPPING INITIALIZATION

• US 20170069096A1
• Filed: 04/30/2014
• Published: 03/09/2017
• Est. Priority Date: 04/30/2014
• Status: Active Grant

• Current Assignee: Longsand Limited (Open Text Corporation)
• Original Assignee: Longsand Limited (Open Text Corporation)
• Inventors: Cameron, Pashmina, Saklatvala, George
• Granted Patent: US 10,242,453 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/32 using correlation-based methods
• CPC Class Codes: G06T 7/337 involving reference images or patches
• CPC Class Codes: G06T 7/579 from motion

Abstract

A pair of video frames may be used for simultaneous localization and mapping (SLAM) initialization. The pair of frames may be determined according to a translation threshold. Whether the translation threshold is met may be determined by obtaining the pair of video frames and estimating the translation between the frames.

Claims

1. A method, comprising:

obtaining a pair of video frames;

estimating a translation between the two video frames;

using the pair of video frames for initialization of a simultaneous localization and mapping (SLAM) method if the translation exceeds a translation threshold.

2. The method of claim 1, further comprising:

obtaining a set of corresponding feature pairs from a pair of video frames, each corresponding feature pair including a feature from each of the pair of video frames;

estimating a translation between the features of the pairs;

using the pair of frames for initialization of a simultaneous localization and mapping (SLAM) method if the translation and the size of the set of corresponding features meet a joint condition.

3. The method of claim 2, wherein the joint condition comprises the translation threshold and a correspondence threshold.

4. The method of claim 2, further comprising determining the set of corresponding feature pairs by:

extracting features in a first video frame of the pair of video frames;

extracting features in a second video frame of the pair of video frames; and

identifying corresponding features from the extracted features of the first and second video frames.

5. The method of claim 2, further comprising estimating the translation between the pair of frames by estimating a two-dimensional transformation from the first feature set to the second feature set.

6. The method of claim 5;

further comprising estimating the two-dimensional transformation by;

centering the first feature set by subtracting a first centroid from the first feature set;

centering the feature set by subtracting a second centroid from the second feature set;

calculating a correlation matrix from the centered first feature set and the centered second feature set;

calculating a rotation from the centered first feature set to the centered second feature set; and

calculating the translation by a vector joining the rotated first centroid and the second centroid.

7. The method of claim 2, further comprising:

if the translation and the size of the set of corresponding feature pairs do not meet the joint condition;

obtaining a third video frame;

obtaining a second set of corresponding feature pairs from the first video frame and a third video frame;

estimating a second translation between the first video frame and the third video frame; and

using the first video frame and the third video frame as initial frames in the simultaneous localization and mapping (SLAM) method if the second translation and the size of the second set of corresponding feature pairs meet the joint condition.

8. A system;

comprising;

a video input to obtain video frames;

a feature extractor to detect a first set of rays from a first video frame and a corresponding set of rays from a second video frame, each ray from the first set and corresponding ray from the second set representing a common feature in the first video frame and the second video frame;

a transformation estimator to estimate a transformation from the first set of rays to the second set of rays, the transformation including a translation; and

a frame evaluator to determine if the first video frame and the second video frame are suitable as initial frames for simultaneous localization and mapping (SLAM) using a joint condition on the translation and the number of corresponding pairs.

9. The system of claim 8, further comprising:

a SLAM module to perform SLAM initialization using the first video frame and second video frame as initial frames.

10. The system of claim 8, wherein the transformation is a two dimensional transformation comprising a rotation and a translation.

11. A non-transitory computer readable medium storing instructions executable by a processor to:

obtain a first video frame and a second video frame;

extract a first feature set from the first video frame;

extract a second feature set from the second video frame, elements of the first and second feature set forming corresponding pairs of features;

estimate a translation between the first feature set and the second feature set;

if the translation and the number of the corresponding pairs meets a joint condition, use the first video and the second video frame for simultaneous localization and mapping (SLAM) initialization.

12. The non-transitory computer readable medium of claim 11, storing further instructions executable by the processor to:

if the translation and the number of the corresponding pairs do not meet the joint condition, compare subsequent video frames with the first video frame until the joint condition on the translation and the number of corresponding pairs is met, and

use the subsequent video frame and first video frame meeting the joint condition on the translation and the number of corresponding pairs for SLAM initialization.

13. The non-transitory computer readable medium of claim 12, storing further instructions executable by the processor to extract the first feature set and the second feature set by:

extracting features of the first video frame;

extracting features of the second video frame; and

identifying corresponding features from the extracted features of the first and second video frames.

14. The non-transitory computer readable medium of claim 12, storing further instructions executable by the processor to estimate the translation between the first feature set and the second feature set by estimating a two-dimensional transformation from the first feature set to the second feature set.

15. The non-transitory computer readable medium of claim 13, storing further instructions executable by the processor to estimate the two-dimensional transformation by;

centering the first feature set by subtracting a first centroid from the first feature set;

centering the feature set by subtracting a second centroid from the second feature set;

calculating a correlation matrix from the centered first feature set and the centered second feature set;

calculating a rotation from the centered first feature set to the centered second feature set; and

calculating the translation as a vector joining the rotated first centroid and the second centroid.