L. Di Stefano

A simple and efficient connected components labeling algorithm

We describe a two-scan algorithm for labeling connected components in binary images in raster format. Unlike the classical two-scan approach, our algorithm processes equivalences during the first scan by merging equivalence classes as soon as a new equivalence is found. We show that this significantly improves the efficiency of the labeling process with respect to the classical approach. The data structure used to support the handling of equivalences is a 1D-array. This renders the more frequent operation of finding class identifiers very fast, while the less-frequent class-merging operation has a relatively high computational cost. Nonetheless, it is possible to reduce significantly the merging cost by two slight modifications to the algorithms basic structure. The idea of merging equivalence classes is present also in Samets general labeling algorithm. However when considering the case of binary images in raster format this algorithm is much more complex than the one we describe in this paper.

Classification and evaluation of cost aggregation methods for stereo correspondence

In the last decades several cost aggregation methods aimed at improving the robustness of stereo correspondence within local and global algorithms have been proposed. Given the recent developments and the lack of an appropriate comparison, in this paper we survey, classify and compare experimentally on a standard data set the main cost aggregation approaches proposed in literature. The experimental evaluation addresses both accuracy and computational requirements, so as to outline the best performing methods under these two criteria.

Adaptive Appearance Modeling for Video Tracking: Survey and Evaluation

Long-term video tracking is of great importance for many applications in real-world scenarios. A key component for achieving long-term tracking is the trackers capability of updating its internal representation of targets (the appearance model) to changing conditions. Given the rapid but fragmented development of this research area, we propose a unified conceptual framework for appearance model adaptation that enables a principled comparison of different approaches. Moreover, we introduce a novel evaluation methodology that enables simultaneous analysis of tracking accuracy and tracking success, without the need of setting application-dependent thresholds. Based on the proposed framework and this novel evaluation methodology, we conduct an extensive experimental comparison of trackers that perform appearance model adaptation. Theoretical and experimental analyses allow us to identify the most effective approaches as well as to highlight design choices that favor resilience to errors during the update process. We conclude the paper with a list of key open research challenges that have been singled out by means of our experimental comparison.

Performance Evaluation of Full Search Equivalent Pattern Matching Algorithms

Pattern matching is widely used in signal processing, computer vision, and image and video processing. Full search equivalent algorithms accelerate the pattern matching process and, in the meantime, yield exactly the same result as the full search. This paper proposes an analysis and comparison of state-of-the-art algorithms for full search equivalent pattern matching. Our intention is that the data sets and tests used in our evaluation will be a benchmark for testing future pattern matching algorithms, and that the analysis concerning state-of-the-art algorithms could inspire new fast algorithms. We also propose extensions of the evaluated algorithms and show that they outperform the original formulations.

Multimodal cue integration through Hypotheses Verification for RGB-D object recognition and 6DOF pose estimation

This paper proposes an effective algorithm for recognizing objects and accurately estimating their 6DOF pose in scenes acquired by a RGB-D sensor. The proposed method is based on a combination of different recognition pipelines, each exploiting the data in a diverse manner and generating object hypotheses that are ultimately fused together in an Hypothesis Verification stage that globally enforces geometrical consistency between model hypotheses and the scene. Such a scheme boosts the overall recognition performance as it enhances the strength of the different recognition pipelines while diminishing the impact of their specific weaknesses. The proposed method outperforms the state-of-the-art on two challenging benchmark datasets for object recognition comprising 35 object models and, respectively, 176 and 353 scenes.

Near real-time stereo based on effective cost aggregation

Recent research activity on stereo matching has proved the efficacy of local approaches based on advanced cost aggregation strategies in accurately retrieving 3D information. However, accuracy is typically achieved at expense of computational efficiency, with best methods being far from meeting real-time requirements. On the other side, basic real-time local algorithms relying on a rectangular correlation window suffer from significant ambiguity along depth borders and untextured areas. This work proposes a novel local approach aimed at maximizing the speed-accuracy trade-off by means of an efficient segmentation-based cost aggregation strategy.

Full-Search-Equivalent Pattern Matching with Incremental Dissimilarity Approximations

This paper proposes a novel method for fast pattern matching based on dissimilarity functions derived from the Lp norm, such as the Sum of Squared Differences (SSD) and the Sum of Absolute Differences (SAD). The proposed method is full-search equivalent, i.e. it yields the same results as the Full Search (FS) algorithm. In order to pursue computational savings the method deploys a succession of increasingly tighter lower bounds of the adopted Lp norm-based dissimilarity function. Such bounding functions allow for establishing a hierarchy of pruning conditions aimed at skipping rapidly those candidates that cannot satisfy the matching criterion. The paper includes an experimental comparison between the proposed method and other full-search equivalent approaches known in literature, which proves the remarkable computational efficiency of our proposal.

An efficient algorithm for exhaustive template matching based on normalized cross correlation

This work proposes a novel technique aimed at improving the performance of exhaustive template matching based on the normalized cross correlation (NCC). An effective sufficient condition, capable of rapidly pruning those match candidates that could not provide a better cross correlation score with respect to the current best candidate, can be obtained exploiting an upper bound of the NCC function. This upper bound relies on partial evaluation of the crosscorrelation and can be computed efficiently, yielding a significant reduction of operations compared to the NCC function and allows for reducing the overall number of operations required to carry out exhaustive searches. However, the bounded partial correlation (BPC) algorithm turns out to be significantly data dependent. In this paper we propose a novel algorithm that improves the overall performance of BPC thanks to the deployment of a more selective sufficient condition which allows for rendering the algorithm significantly less data dependent. Experimental results with real images and actual CPU time are reported.

An effective real-time mosaicing algorithm apt to detect motion through background subtraction using a PTZ camera

Nowadays, many visual surveillance systems exploit pan/tilt/zoom (PTZ) cameras to increase the field of view of a surveyed area. The background subtraction technique is widespread to detect moving objects with a high accuracy using one stationary camera. Extending such algorithms to work with moving cameras requires to have a background mosaic at ones disposal. Many solutions using mosaic background subtraction have been proposed, which offer real time capabilities or high quality of the detected objects. However, most of them rely on prior assumptions which limit the camera motion or the algorithm to work with a depth field of view only. In this work we propose some innovative solutions to achieve a real time mosaic background apt to work with existing background subtraction algorithms to yield excellent foreground object masks. Extensive experiments accomplished on challenging indoor and outdoor scenes permit to assess the quality of the mosaic as well as of the detected moving masks.

Fast stereo matching for the VIDET system using a general purpose processor with multimedia extensions

The ever-increasing speed of current general purpose processors, together with architectural enhancements such as multimedia-oriented instruction set extensions, allow for deploying standard PC-based systems in a number of com-putationally intensive computer vision tasks. This paper de-scribes the PC-based real-time stereo vision system devel-oped within the VIDET project, which is a research project aimed at the development of a mobility aid for the visu-ally impaired. VIDETs approach consists in the conversion of depth data gathered through a stereo vision system into a 3D model perceivable by the user by means of a wire-actuated haptic interface. The developed stereo matching algorithm makes massive use of recursion and multime-dia instructions to achieve the performance figures needed to sustain users real-time interaction with the 3D model through the haptic interface.