Abstract | ||
---|---|---|
In this work, we present a scalable least-squares solution for computing a seven degree-of-freedom similarity transform. Our method utilizes the generalized camera model to compute relative rotation, translation, and scale from four or more 2D-3D correspondences. In particular, structure and motion estimations from monocular cameras lack scale without specific calibration. As such, our methods have applications in loop closure in visual odometry and registering multiple structure from motion reconstructions where scale must be recovered. We formulate the generalized pose and scale problem as a minimization of a least squares cost function and solve this minimization without iterations or initialization. Additionally, we obtain all minima of the cost function. The order of the polynomial system that we solve is independent of the number of points, allowing our overall approach to scale favorably. We evaluate our method experimentally on synthetic and real datasets and demonstrate that our methods produce higher accuracy similarity transform solutions than existing methods. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1007/978-3-319-10593-2_2 | COMPUTER VISION - ECCV 2014, PT IV |
Keywords | Field | DocType |
Image Noise,Similarity Transformation,Polynomial System,Multiple Camera,Scalable Solution | Structure from motion,Least squares,Computer vision,Matrix similarity,Polynomial,Visual odometry,Computer science,Maxima and minima,Minification,Artificial intelligence,Initialization,Machine learning | Conference |
Volume | ISSN | Citations |
8692 | 0302-9743 | 14 |
PageRank | References | Authors |
0.58 | 28 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chris Sweeney | 1 | 101 | 7.42 |
Victor Fragoso | 2 | 14 | 1.25 |
Tobias Höllerer | 3 | 2666 | 244.50 |
Matthew Turk | 4 | 3724 | 499.42 |