Filippo Bergamasco

A Scale Independent Selection Process for 3D Object Recognition in Cluttered Scenes

During the last years a wide range of algorithms and devices have been made available to easily acquire range images. The increasing abundance of depth data boosts the need for reliable and unsupervised analysis techniques, spanning from part registration to automated segmentation. In this context, we focus on the recognition of known objects in cluttered and incomplete 3D scans. Locating and fitting a model to a scene are very important tasks in many scenarios such as industrial inspection, scene understanding, medical imaging and even gaming. For this reason, these problems have been addressed extensively in the literature. Several of the proposed methods adopt local descriptor-based approaches, while a number of hurdles still hinder the use of global techniques. In this paper we offer a different perspective on the topic: We adopt an evolutionary selection algorithm that seeks global agreement among surface points, while operating at a local level. The approach effectively extends the scope of local descriptors by actively selecting correspondences that satisfy global consistency constraints, allowing us to attack a more challenging scenario where model and scene have different, unknown scales. This leads to a novel and very effective pipeline for 3D object recognition, which is validated with an extensive set of experiments and comparisons with recent techniques at the state of the art.

A game-theoretic approach to deformable shape matching

We consider the problem of minimum distortion intrinsic correspondence between deformable shapes, many useful formulations of which give rise to the NP-hard quadratic assignment problem (QAP). Previous attempts to use the spectral relaxation have had limited success due to the lack of sparsity of the obtained “fuzzy” solution. In this paper, we adopt the recently introduced alternative L1 relaxation of the QAP based on the principles of game theory. We relate it to the Gromov and Lipschitz metrics between metric spaces and demonstrate on state-of-the-art benchmarks that the proposed approach is capable of finding very accurate sparse correspondences between deformable shapes.

RUNE-Tag: A high accuracy fiducial marker with strong occlusion resilience

Over the last decades fiducial markers have provided widely adopted tools to add reliable model-based features into an otherwise general scene. Given their central role in many computer vision tasks, countless different solutions have been proposed in the literature. Some designs are focused on the accuracy of the recovered camera pose with respect to the tag; some other concentrate on reaching high detection speed or on recognizing a large number of distinct markers in the scene. In such a crowded area both the researcher and the practitioner are licensed to wonder if there is any need to introduce yet another approach. Nevertheless, with this paper, we would like to present a general purpose fiducial marker system that can be deemed to add some valuable features to the pack. Specifically, by exploiting the projective properties of a circular set of sizeable dots, we propose a detection algorithm that is highly accurate. Further, applying a dot pattern scheme derived from error-correcting codes, allows for robustness with respect to very large occlusions. In addition, the design of the marker itself is flexible enough to accommodate different requirements in terms of pose accuracy and number of patterns. The overall performance of the marker system is evaluated in an extensive experimental section, where a comparison with a well-known baseline technique is presented.

Pi-Tag: a fast image-space marker design based on projective invariants

Visual marker systems have become an ubiquitous tool to supply a reference frame onto otherwise uncontrolled scenes. Throughout the last decades, a wide range of different approaches have emerged, each with different strengths and limitations. Some tags are optimized to reach a high accuracy in the recovered camera pose, others are based on designs that aim to maximizing the detection speed or minimizing the effect of occlusion on the detection process. Most of them, however, employ a two-step procedure where an initial homography estimation is used to translate the marker from the image plane to an orthonormal world, where it is validated and recognized. In this paper, we present a general purpose fiducial marker system that performs both steps directly in image-space. Specifically, by exploiting projective invariants such as collinearity and cross-ratios, we introduce a detection and recognition algorithm that is fast, accurate and moderately robust to occlusion. The overall performance of the system is evaluated in an extensive experimental section, where a comparison with a well-known baseline technique is presented. Additionally, several real-world applications are proposed, ranging from camera calibration to projector-based augmented reality.

Observation of Extreme Sea Waves in a Space–Time Ensemble

AbstractIn this paper, an observational space–time ensemble of sea surface elevations is investigated in search of the highest waves of the sea state. Wave data were gathered by means of a stereo camera system, which was installed on top of a fixed oceanographic platform located in the Adriatic Sea (Italy). Waves were measured during a mature sea state with an average wind speed of 11 m s−1. By examining the space–time ensemble, the 3D wave groups have been isolated while evolving in the 2D space and grabbed “when and where” they have been close to the apex of their development, thus exhibiting large surface displacements. The authors have selected the groups displaying maximal crest height exceeding the threshold adopted to define rogue waves in a time record, that is, 1.25 times the significant wave height (Hs). The records at the spatial positions where such large crests occurred have been analyzed to derive the empirical distributions of crest and wave heights, which have been compared against standar...

Analysis and Interpretation of Frequency–Wavenumber Spectra of Young Wind Waves

The energy level and its directional distribution are key observations for understanding the energy balance in the wind-wave spectrum between wind-wave generation, nonlinear interactions, and dissipation. Here, properties of gravity waves are investigated from a fixed platform in the Black Sea, equipped with a stereo video system that resolves waves with frequency f up to 1.4 Hz and wavelengths from 0.6 to 11 m. One representative record is analyzed, corresponding to young wind waves with a peak frequency fp = 0.33 Hz and a wind speed of 13 m s−1. These measurements allow for a separation of the linear waves from the bound second-order harmonics. These harmonics are negligible for frequencies f up to 3 times fp but account for most of the energy at higher frequencies. The full spectrum is well described by a combination of linear components and the second-order spectrum. In the range 2fp to 4fp, the full frequency spectrum decays like f−5, which means a steeper decay of the linear spectrum. The directional spectrum exhibits a very pronounced bimodal distribution, with two peaks on either side of the wind direction, separated by 150° at 4fp. This large separation is associated with a significant amount of energy traveling in opposite directions and thus sources of underwater acoustic and seismic noise. The magnitude of these sources can be quantified by the overlap integral I(f), which is found to increase sharply from less than 0.01 at f = 2fp to 0.11 at f = 4fp and possibly up to 0.2 at f = 5fp, close to the 0.5π value proposed in previous studies.

A Non-cooperative Game for 3D Object Recognition in Cluttered Scenes

During the last few years a wide range of algorithms and devices have been made available to easily acquire range images. To this extent, the increasing abundance of depth data boosts the need for reliable and unsupervised analysis techniques, spanning from part registration to automated segmentation. In this context, we focus on the recognition of known objects in cluttered and incomplete 3D scans. Fitting a model to a scene is a very important task in many scenarios such as industrial inspection, scene understanding and even gaming. For this reason, this problem has been extensively tackled in literature. Nevertheless, while many descriptor-based approaches have been proposed, a number of hurdles still hinder the use of global techniques. In this paper we try to offer a different perspective on the topic. Specifically, we adopt an evolutionary selection algorithm in order to extend the scope of local descriptors to satisfy global pair wise constraints. In addition, the very same technique is also used to shift from an initial sparse correspondence to a dense matching. This leads to a novel pipeline for 3D object recognition, which is validated with an extensive set of experiments and comparisons with recent well-known feature-based approaches.

An Accurate and Robust Artificial Marker Based on Cyclic Codes

Artificial markers are successfully adopted to solve several vision tasks, ranging from tracking to calibration. While most designs share the same working principles, many specialized approaches exist to address specific application domains. Some are specially crafted to boost pose recovery accuracy. Others are made robust to occlusion or easy to detect with minimal computational resources. The sheer amount of approaches available in recent literature is indeed a statement to the fact that no silver bullet exists. Furthermore, this is also a hint to the level of scholarly interest that still characterizes this research topic. With this paper we try to add a novel option to the offer, by introducing a general purpose fiducial marker which exhibits many useful properties while being easy to implement and fast to detect. The key ideas underlying our approach are three. The first one is to exploit the projective invariance of conics to jointly find the marker and set a reading frame for it. Moreover, the tag identity is assessed by a redundant cyclic coded sequence implemented using the same circular features used for detection. Finally, the specific design and feature organization of the marker are well suited for several practical tasks, ranging from camera calibration to information payload delivery.

A Robust Multi-camera 3D Ellipse Fitting for Contactless Measurements

Ellipses are a widely used cue in many 2D and 3D object recognition pipelines. In fact, they exhibit a number of useful properties. First, they are naturally occurring in many man-made objects. Second, the projective invariance of the class of ellipses makes them detectable even without any knowledge of the acquisition parameters. Finally, they can be represented by a compact set of parameters that can be easily adopted within optimization tasks. While a large body of work exists in the literature about the localization of ellipses as 2D entities in images, less effort has been put in the direct localization of ellipses in 3D, exploiting images coming from a known camera network. In this paper we propose a novel technique for fitting elliptical shapes in 3D space, by performing an initial 2D guess on each image followed by a multi-camera optimization refining a 3D ellipse simultaneously on all the calibrated views. The proposed method is validated both with synthetic data and by measuring real objects captured by a specially crafted imaging head. Finally, to evaluate the feasibility of the approach within real-time industrial scenarios, we tested the performance of a GPU-based implementation of the algorithm.

A graph-based technique for semi-supervised segmentation of 3D surfaces

A wide range of cheap and simple to use 3D scanning devices has recently been introduced in the market. These tools are no longer addressed to research labs and highly skilled professionals, but rather, they are mostly designed to allow inexperienced users to acquire surfaces and whole objects easily and independently. In this scenario, the demand for automatic or semi-automatic algorithms for 3D data processing is increasing. In this paper we address the task of segmenting the acquired surfaces into perceptually relevant parts. Such a problem is well known to be ill-defined both for 2D images and 3D objects, as even with a perfect understanding of the scene, many different and incompatible semantic or syntactic segmentations can exist together. For this reason recent years have seen a great research effort into semi-supervised approaches, that can make use of small bits of information provided by the user to attain better accuracy. We propose a semi-supervised procedure that exploits an initial set of seeds selected by the user. In our framework segmentation happens by propagating part labels over a weighted graph representation of the surface directly derived from its triangulated mesh. The assignment of each element is driven by a greedy approach that accounts for the curvature between adjacent triangles. The proposed technique does not require to perform edge detection or to fit parametrized surfaces and its implementation is very straightforward. Still, despite its simplicity, tests made on a standard database of scanned 3D objects show its effectiveness even with moderate user supervision.