Jiri Matas

On combining classifiers

We develop a common theoretical framework for combining classifiers which use distinct pattern representations and show that many existing schemes can be considered as special cases of compound classification where all the pattern representations are used jointly to make a decision. An experimental comparison of various classifier combination schemes demonstrates that the combination rule developed under the most restrictive assumptions-the sum rule-outperforms other classifier combinations schemes. A sensitivity analysis of the various schemes to estimation errors is carried out to show that this finding can be justified theoretically.

Robust wide-baseline stereo from maximally stable extremal regions

Abstract The wide-baseline stereo problem, i.e. the problem of establishing correspondences between a pair of images taken from different viewpoints is studied. A new set of image elements that are put into correspondence, the so called extremal regions , is introduced. Extremal regions possess highly desirable properties: the set is closed under (1) continuous (and thus projective) transformation of image coordinates and (2) monotonic transformation of image intensities. An efficient (near linear complexity) and practically fast detection algorithm (near frame rate) is presented for an affinely invariant stable subset of extremal regions, the maximally stable extremal regions (MSER). A new robust similarity measure for establishing tentative correspondences is proposed. The robustness ensures that invariants from multiple measurement regions (regions obtained by invariant constructions from extremal regions), some that are significantly larger (and hence discriminative) than the MSERs, may be used to establish tentative correspondences. The high utility of MSERs, multiple measurement regions and the robust metric is demonstrated in wide-baseline experiments on image pairs from both indoor and outdoor scenes. Significant change of scale (3.5×), illumination conditions, out-of-plane rotation, occlusion, locally anisotropic scale change and 3D translation of the viewpoint are all present in the test problems. Good estimates of epipolar geometry (average distance from corresponding points to the epipolar line below 0.09 of the inter-pixel distance) are obtained.

Tracking-Learning-Detection

This paper investigates long-term tracking of unknown objects in a video stream. The object is defined by its location and extent in a single frame. In every frame that follows, the task is to determine the objects location and extent or indicate that the object is not present. We propose a novel tracking framework (TLD) that explicitly decomposes the long-term tracking task into tracking, learning, and detection. The tracker follows the object from frame to frame. The detector localizes all appearances that have been observed so far and corrects the tracker if necessary. The learning estimates the detectors errors and updates it to avoid these errors in the future. We study how to identify the detectors errors and learn from them. We develop a novel learning method (P-N learning) which estimates the errors by a pair of “experts”: (1) P-expert estimates missed detections, and (2) N-expert estimates false alarms. The learning process is modeled as a discrete dynamical system and the conditions under which the learning guarantees improvement are found. We describe our real-time implementation of the TLD framework and the P-N learning. We carry out an extensive quantitative evaluation which shows a significant improvement over state-of-the-art approaches.

P-N learning: Bootstrapping binary classifiers by structural constraints

This paper shows that the performance of a binary classifier can be significantly improved by the processing of structured unlabeled data, i.e. data are structured if knowing the label of one example restricts the labeling of the others. We propose a novel paradigm for training a binary classifier from labeled and unlabeled examples that we call P-N learning. The learning process is guided by positive (P) and negative (N) constraints which restrict the labeling of the unlabeled set. P-N learning evaluates the classifier on the unlabeled data, identifies examples that have been classified in contradiction with structural constraints and augments the training set with the corrected samples in an iterative process. We propose a theory that formulates the conditions under which P-N learning guarantees improvement of the initial classifier and validate it on synthetic and real data. P-N learning is applied to the problem of on-line learning of object detector during tracking. We show that an accurate object detector can be learned from a single example and an unlabeled video sequence where the object may occur. The algorithm is compared with related approaches and state-of-the-art is achieved on a variety of objects (faces, pedestrians, cars, motorbikes and animals).

Robust Wide Baseline Stereo from Maximally Stable Extremal Regions.

The wide-baseline stereo problem, i.e. the problem of establishing correspondences between a pair of images taken from different viewpoints is studied. A new set of image elements that are put into correspondence, the so called extremal regions, is introduced. Extremal regions possess highly desirable properties: the set is closed under 1. continuous (and thus projective) transformation of image coordinates and 2. monotonic transformation of image intensities. An efficient (near linear complexity) and practically fast detection algorithm (near frame rate) is presented for an affinely-invariant stable subset of extremal regions, the maximally stable extremal regions (MSER). A new robust similarity measure for establishing tentative correspondences is proposed. The robustness ensures that invariants from multiple measurement regions (regions obtained by invariant constructions from extremal regions), some that are significantly larger (and hence discriminative) than the MSERs, may be used to establish tentative correspondences. The high utility of MSERs, multiple measurement regions and the robust metric is demonstrated in wide-baseline experiments on image pairs from both indoor and outdoor scenes. Significant change of scale (3.5×), illumination conditions, out-of-plane rotation, occlusion , locally anisotropic scale change and 3D translation of the viewpoint are all present in the test problems. Good estimates of epipolar geometry (average distance from corresponding points to the epipolar line below 0.09 of the inter-pixel distance) are obtained.

Matching with PROSAC - progressive sample consensus

A new robust matching method is proposed. The progressive sample consensus (PROSAC) algorithm exploits the linear ordering defined on the set of correspondences by a similarity function used in establishing tentative correspondences. Unlike RANSAC, which treats all correspondences equally and draws random samples uniformly from the full set, PROSAC samples are drawn from progressively larger sets of top-ranked correspondences. Under the mild assumption that the similarity measure predicts correctness of a match better than random guessing, we show that PROSAC achieves large computational savings. Experiments demonstrate it is often significantly faster (up to more than hundred times) than RANSAC. For the derived size of the sampled set of correspondences as a function of the number of samples already drawn, PROSAC converges towards RANSAC in the worst case. The power of the method is demonstrated on wide-baseline matching problems.

The BANCA database and evaluation protocol

In this paper we describe the acquisition and content of a new large, realistic and challenging multi-modal database intended for training and testing multi-modal verification systems. The BANCA database was captured in four European languages in two modalities (face and voice). For recording, both high and low quality microphones and cameras were used. The subjects were recorded in three different scenarios, controlled, degraded and adverse over a period of three months. In total 208 people were captured, half men and half women. In this paper we also describe a protocol for evaluating verification algorithms on the database. The database will be made available to the research community through http://www.ee.surrey.ac.uk/Research/VSSP/banca.

The Visual Object Tracking VOT2014 Challenge Results

Visual tracking has attracted a significant attention in the last few decades. The recent surge in the number of publications on tracking-related problems have made it almost impossible to follow the developments in the field. One of the reasons is that there is a lack of commonly accepted annotated data-sets and standardized evaluation protocols that would allow objective comparison of different tracking methods. To address this issue, the Visual Object Tracking (VOT) workshop was organized in conjunction with ICCV2013. Researchers from academia as well as industry were invited to participate in the first VOT2013 challenge which aimed at single-object visual trackers that do not apply pre-learned models of object appearance (model-free). Presented here is the VOT2013 benchmark dataset for evaluation of single-object visual trackers as well as the results obtained by the trackers competing in the challenge. In contrast to related attempts in tracker benchmarking, the dataset is labeled per-frame by visual attributes that indicate occlusion, illumination change, motion change, size change and camera motion, offering a more systematic comparison of the trackers. Furthermore, we have designed an automated system for performing and evaluating the experiments. We present the evaluation protocol of the VOT2013 challenge and the results of a comparison of 27 trackers on the benchmark dataset. The dataset, the evaluation tools and the tracker rankings are publicly available from the challenge website (http://votchallenge.net).

Forward-Backward Error: Automatic Detection of Tracking Failures

This paper proposes a novel method for tracking failure detection. The detection is based on the Forward-Backward error, i.e. the tracking is performed forward and backward in time and the discrepancies between these two trajectories are measured. We demonstrate that the proposed error enables reliable detection of tracking failures and selection of reliable trajectories in video sequences. We demonstrate that the approach is complementary to commonly used normalized cross-correlation (NCC). Based on the error, we propose a novel object tracker called Median Flow. State-of-the-art performance is achieved on challenging benchmark video sequences which include non-rigid objects.

Robust Detection of Lines Using the Progressive Probabilistic Hough Transform

In the paper we present the progressive probabilistic Hough transform (PPHT). Unlike the probabilistic HT, where the standard HT is performed on a preselected fraction of input points, the PPHT minimizes the amount of computation needed to detect lines by exploiting the difference in the fraction of votes needed to reliably detect lines with different numbers of supporting points. The fraction of points used for voting need not be specified ad hoc or using a priori knowledge, as in the probabilistic HT; it is a function of the inherent complexity of data. The algorithm is ideally suited for real-time applications with a fixed amount of available processing time, since voting and line detection are interleaved. The most salient features are likely to be detected first. While retaining its robustness, experiments show that the PPHT has, in many circumstances, advantages over the standard HT.