Citation

Elliethy A, Sharma G. IEEE Trans. Image Process. 2016; 25(11): 5304-5315.

Copyright

(Copyright © 2016, IEEE (Institute of Electrical and Electronics Engineers))

DOI

10.1109/TIP.2016.2601265

PMID

27552750

Abstract

To enrich large scale visual analytics applications enabled by aerial wide area motion imagery (WAMI), we propose a novel methodology for accurately registering a geo-referenced vector roadmap to WAMI by using locations of detected vehicles and determining a parametric transform that aligns these locations with the network of roads in the roadmap. Specifically, the problem is formulated in a probabilistic framework, explicitly allowing for spurious detections that do not correspond to onroad vehicles. The registration is estimated via the EM algorithm as the planar homography that minimizes the sum of weighted squared distances between the homography-mapped detection locations and the corresponding closest point on the road network, where the weights are estimated posterior probabilities of detections being on-road vehicles. The weighted distance minimization is efficiently performed using the distance transform with the Levenberg Marquardt (LM) nonlinear least-squares minimization procedure and the fraction of spurious detections is estimated within the EM framework. The proposed method effectively sidesteps the challenges of feature correspondence estimation, applies directly to different imaging modalities, is robust to spurious detections, and is also more appropriate than feature matching for a planar homography.

RESULTS over three WAMI datasets captured by both visual and infra-red sensors indicate the effectiveness of the proposed methodology: both visual comparison and numerical metrics for the registration accuracy are significantly better for the proposed method as compared with existing alternatives.

Language: en