Title: MapEnhanced UAV Image Sequence Registration and Synchronization of Multiple Image Sequences
1Map-Enhanced UAV Image Sequence Registration and
Synchronization of Multiple Image Sequences
- Yuping Lin and Gérard Medioni
2Outline
- Introduction
- Method
- Register UAV streams to a global reference image
- Consecutive UAV image registration
- UAV to Map registration
- Interleaving image to image and image to map
- Partial local mosaic
- Synchronization of multiple video streams
- Conclusion
3Introduction
- Input
- Multiple UAV video streams
- Position of moving objects in each video stream
- Goal Synchronize using a common moving object
4Method
- Register UAV streams to a global reference image
(a map), then - Synchronize the streams using the unique path of
a common moving object on the map
5Outline
- Introduction
- Method
- Register UAV streams to a global reference image
- Consecutive UAV image registration
- UAV to Map registration
- Interleaving image to image and image to map
- Partial local mosaic
- Synchronization of multiple video streams
- Conclusion
6Register UAV streams to a global reference image
- Input
- Global reference image (Map)
- UAV stream
- The homography of the first frame of the UAV
stream to the map
7Register UAV streams to a global reference image
- UAV images and the map are different in terms of
viewpoints, sensors and time of capture - Direct matching is difficult
- Given the homography of the first UAV frame to
the map, - Two step registration
- Consecutive UAV image registration, then
- UAV to Map registration
8Outline
- Introduction
- Method
- Register UAV streams to a global reference image
- Consecutive UAV image registration
- UAV to Map registration
- Interleaving image to image and image to map
- Partial local mosaic
- Synchronization of multiple video streams
- Conclusion
9Consecutive UAV Image Registration
- Method
- extract features in each frame
- Establish feature correspondences between
consecutive images - estimate the transformation
10Consecutive UAV Image Registration
- Features should be descriptive for matching and
sufficient to give good transform estimation - Feature matching
- Transform estimation
- SIFT feature extraction
- 128 dimension feature descriptor
- Avg. 2000 features in each image
- Nearest neighbor matching
- Avg. 1000 matches in each pair of images
- RANSAC
- Avg. 600 inliers in each pair of images
11Consecutive UAV Image Registration
12Consecutive UAV Image Registration
13Consecutive UAV Image Registration
14Consecutive UAV Image Registration
15Consecutive UAV Image Registration
16Consecutive UAV Image Registration
- Problem error is accumulated
17Outline
- Introduction
- Method
- Register UAV streams to a global reference image
- Consecutive UAV image registration
- UAV to Map registration
- Interleaving image to image and image to map
- Partial local mosaic
- Synchronization of multiple video streams
- Conclusion
18UAV to Map Registration
- Method
- Perform local search for correspondences between
the UAV image and the map
19UAV to Map Registration
- UAV images are very different from the map, SIFT
features cannot always match
- Sample points in the map
- For each point, locally search for the most
similar image patch in the UAV image - Use Mutual Information as similarity measurement
20UAV to Map Registration
21UAV to Map Registration
22UAV to Map Registration
23UAV to Map Registration
24UAV to Map Registration
25Outline
- Introduction
- Method
- Register UAV streams to a global reference image
- Consecutive UAV image registration
- UAV to Map registration
- Interleaving image to image and image to map
- Partial local mosaic
- Synchronization of multiple video streams
- Conclusion
26Iterative way
- Method
- Perform consecutive UAV image registration and
UAV to Map registration iteratively - Consecutive UAV image registration produce good
initials for UAV to Map registration - Register the partial local mosaic to the map
27Register Partial Local Mosaic
- Correspondences in a single frame are not
enoughRegistration is unstable
- Multiple frames in a time window forms a partial
local mosaic which spans a larger region and
provides more correspondences - More robust
- Smooth transition
28Register Partial Local Mosaic
- Correspondences in a single frame are not
enoughRegistration is unstable
- Multiple frames in a time window forms a partial
local mosaic which spans a larger region and
provides more correspondences - More robust
- Smooth transition
29Register Partial Local Mosaic
Register single frame
Register partial local mosaic
30Iterative way
31Iterative way
32Iterative way
33Iterative way
34Register UAV streams to a global reference image
35Outline
- Introduction
- Method
- Register UAV streams to a global reference image
- Consecutive UAV image registration
- UAV to Map registration
- Interleaving image to image and image to map
- Partial local mosaic
- Synchronization of multiple video streams
- Conclusion
36Synchronization of Multiple Video Streams
- Input UAV image sequences of different views,
different frame rates, but capture the same area
and overlap in time - An moving object on the ground plane which serves
as a clock to synchronize the sequences
37Synchronization of Multiple Video Streams
- The moving object should generate a single path
on the map - Use sequence alignment algorithm to synchronize
the UAV streams
38Synchronization Result
39Conclusion
- Two steps to register an UAV image to the map
- Register each frame to its previous frame to
derive an initial estimate - Register UAV image to the map to derive
- Limitations
- Initial estimate should be given
- Unable to recover from a bad estimate
-