Parametric Image Alignment Using Enhanced Correlation Coefficient Maximization

By Emmanouil Z. Psarakis. 2008

710 citations recorded by the source corpus.

In this work we propose the use of a modified version of the correlation coefficient as a performance criterion for the image alignment problem. The proposed modification has the desirable characteristic of being invariant with respect to photometric distortions. Since the resulting similarity measure is a nonlinear function of the warp parameters, we develop two iterative schemes for its maximization, one based on the forward additive approach and the second on the inverse compositional method. As it is customary in iterative optimization, in each iteration the nonlinear objective function is approximated by an alternative expression for which the corresponding optimization is simple. In our case we propose an efficient approximation that leads to a closed form solution (per iteration) which is of low computational complexity, the latter property being particularly strong in our inverse version. The proposed schemes are tested against the forward additive Lucas-Kanade and the simultaneous inverse compositional algorithm through simulations. Under noisy conditions and photometric distortions our forward version achieves more accurate alignments and exhibits faster convergence whereas our inverse version has similar performance as the simultaneous inverse compositional algorithm but at a lower computational complexity.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Adversarial Diversity and Hard Positive Generation (2016, background): “1 will maximize ECC(ψ(x̃, x), x).”
Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model (2017, methodology): “This section analyzes the performance proﬁle of the Un-supervised, Supervised, SIFT, and ECC methods on our synthetic dataset.”
Real-World Single Image Super-Resolution: A Brief Review (2021, methodology): “For image registration, the Euclidean motion model is applied to describe the relationship between the images with different resolutions and it is optimized by minimizing the enhanced correlation coefﬁcient as in [134].”
BoT-SORT: Robust Associations Multi-Pedestrian Tracking (2022, methodology): “Therefore, many researchers adopted camera motion compensation (CMC) [1, 21, 18, 40, 13] by aligning frames via image registration using the Enhanced Correlation Coefﬁcient (ECC) maximization [15] or matching features such as ORB [36].”
Constraining dense hand surface tracking with elasticity (2020, methodology): “Using this view selection strategy together with enhanced correlation coefficients [Evangelidis and Psarakis 2008] for robust image error, E pho is formulated as where C( X ) is a set of cameras where X is visible in the previous frame and P c is the camera matrix of camera c .”
Tracking Objects as Points (2020, neutral): “As a consequence, Tracktor [1] requires a motion model [5, 6] for low-framerate sequences.”
StrongSORT: Make DeepSORT Great Again (2022, methodology): “For Strong-SORT, the matching distance threshold is 0.45, the warp mode for ECC is MOTION EUCLIDEAN , the momentum term α in EMA is 0.9 and the weight factor for appearance cost λ is 0.98.”
Optimization (2019, methodology): “…image processing techniques adapted to the map alignment problem, namely i) image alignment with Enhanced Correlation Coefﬁcient (ECC) Maximization [14], ii) image registration with Scale-Invariant Feature Transform (SIFT) [17] in combination with Fast Approximate Nearest Neighbors [25] for…”