An iterative combination scheme for multimodal visual feature detection

Abstract

We address the problem of multimodal visual feature detection where several individual heterogeneous measures (i.e., feature detectors) are merged into a single saliency value. We survey a number of techniques for the normalization and integration steps used in existing combination methods. A new approach, the iterative combination scheme, is proposed to iteratively learn a classifier that infers a non-linear model to combine different feature detectors. We evaluate and compare the combination strategies presented using an objective methodology, the repeatability criterion, and a dataset with real images of 21 cluttered scenes of 3D objects. Initially, our evaluation tested the performance of individual feature detectors. Considering the overall performance for all 7 scenes in the testing dataset, the Difference of Gaussian detector achieved the best repeatability rate, 54.41%. In our evaluation, we tested the performance of combining all possible sets of feature detectors. Among all possible sets, the triplet composed of Laplacian of Gaussian, Hessian Matrix, and Gradient Magnitude achieved the best performance of 58.93% repeatability. We used this combination of detectors to initialize the iterative combination scheme which was able to improve the performance to 66.62%.