Showing papers by "Shai Avidan published in 2015"

Locally Orderless Tracking

Abstract: Locally Orderless Tracking (LOT) is a visual tracking algorithm that automatically estimates the amount of local (dis)order in the target This lets the tracker specialize in both rigid and deformable objects on-line and with no prior assumptions We provide a probabilistic model of the target variations over time We then rigorously show that this model is a special case of the Earth Mover's Distance optimization problem where the ground distance is governed by some underlying noise model This noise model has several parameters that control the cost of moving pixels and changing their color We develop two such noise models and demonstrate how their parameters can be estimated on-line during tracking to account for the amount of local (dis)order in the target We also discuss the significance of this on-line parameter update and demonstrate its contribution to the performance Finally we show LOT's tracking capabilities on challenging video sequences, both commonly used and new, displaying performance comparable to state-of-the-art methods

Best-Buddies Similarity for robust template matching

Abstract: We propose a novel method for template matching in unconstrained environments. Its essence is the Best-Buddies Similarity (BBS), a useful, robust, and parameter-free similarity measure between two sets of points. BBS is based on counting the number of Best-Buddies Pairs (BBPs)—pairs of points in source and target sets, where each point is the nearest neighbor of the other. BBS has several key features that make it robust against complex geometric deformations and high levels of outliers, such as those arising from background clutter and occlusions. We study these properties, provide a statistical analysis that justifies them, and demonstrate the consistent success of BBS on a challenging real-world dataset.

Inverting RANSAC: Global model detection via inlier rate estimation

Abstract: This work presents a novel approach for detecting inliers in a given set of correspondences (matches). It does so without explicitly identifying any consensus set, based on a method for inlier rate estimation (IRE). Given such an estimator for the inlier rate, we also present an algorithm that detects a globally optimal transformation. We provide a theoretical analysis of the IRE method using a stochastic generative model on the continuous spaces of matches and transformations. This model allows rigorous investigation of the limits of our IRE method for the case of 2D-translation, further giving bounds and insights for the more general case. Our theoretical analysis is validated empirically and is shown to hold in practice for the more general case of 2D-affinities. In addition, we show that the combined framework works on challenging cases of 2D-homography estimation, with very few and possibly noisy inliers, where RANSAC generally fails.

Probably Approximately Symmetric: Fast Rigid Symmetry Detection With Global Guarantees

Abstract: We present a fast algorithm for global rigid symmetry detection with approximation guarantees. The algorithm is guaranteed to find the best approximate symmetry of a given shape, to within a user-specified threshold, with very high probability. Our method uses a carefully designed sampling of the transformation space, where each transformation is efficiently evaluated using a sublinear algorithm. We prove that the density of the sampling depends on the total variation of the shape, allowing us to derive formal bounds on the algorithm's complexity and approximation quality. We further investigate different volumetric shape representations in the form of truncated distance transforms, and in such a way control the total variation of the shape and hence the sampling density and the runtime of the algorithm. A comprehensive set of experiments assesses the proposed method, including an evaluation on the eight categories of the COSEG data set. This is the first large-scale evaluation of any symmetry detection technique that we are aware of.

Real-time tracking-with-detection for coping with viewpoint change

Abstract: We consider real-time visual tracking with targets undergoing viewpoint changes. The problem is evaluated on a new and extensive dataset of vehicles undergoing large viewpoint changes. We propose an evaluation method in which tracking accuracy is measured under real-time computational complexity constraints and find that state-of-the-art agnostic trackers, as well as class detectors, are still struggling with this task. We study tracking schemes fusing real-time agnostic trackers with a non-real-time class detector used for template update, with two dominating update strategies emerging. We rigorously analyze the template update latency and demonstrate that such methods significantly outperform stand-alone trackers and class detectors. Results are demonstrated using two different trackers and a state-of-the-art classifier, and at several operating points of algorithm/hardware computational speed.

Peeking Template Matching for Depth Extension

Abstract: We propose a method that extends a given depth image into regions in 3D that are not visible from the point of view of the camera. The algorithm detects repeated 3D structures in the visible scene and suggests a set of 3D extension hypotheses, which are then combined together through a global 3D MRF discrete optimization. The recovered global 3D surface is consistent with both the input depth map and the hypotheses. A key component of this work is a novel 3D template matcher that is used to detect repeated 3D structure in the scene and to suggest the hypotheses. A unique property of this matcher is that it can handle depth uncertainty. This is crucial because the matcher is required to "peek around the corner", as it operates at the boundaries of the visible 3D scene where depth information is missing. The proposed matcher is fast and is guaranteed to find an approximation to the globally optimal solution. We demonstrate on real-world data that our algorithm is capable of completing a full 3D scene from a single depth image and can synthesize a full depth map from a novel viewpoint of the scene. In addition, we report results on an extensive synthetic set of 3D shapes, which allows us to evaluate the method both qualitatively and quantitatively.

Spatially Coherent Random Forests

Abstract: Spatially Coherent Random Forest (SCRF) extends Random Forest to create spatially coherent labeling. Each split function in SCRF is evaluated based on a traditional information gain measure that is regularized by a spatial coherency term. This way, SCRF is encouraged to choose split functions that cluster pixels both in appearance space and in image space. In particular, we use SCRF to detect contours in images, where contours are taken to be the boundaries between different regions. Each tree in the forest produces a segmentation of the image plane and the boundaries of the segmentations of all trees are aggregated to produce a final hierarchical contour map. We show that this modification improves the performance of regular Random Forest by about 10% on the standard Berkeley Segmentation Datasets. We believe that SCRF can be used in other settings as well.