Publications2011
- Artificial Defocus for Displaying Markers in Microscopy Z-Stacks. IEEE Transactions on Visualization and Computer Graphics (TVCG), to appear, 2011.
@INPRECEEDINGS{author = {A. Giusti et. al.}, title = {Artificial Defocus for Displaying Markers in Microscopy Z-Stacks}, booktitle= { IEEE Transactions on Visualization and Computer Graphics}, year = {2011}} - Automatic laser-based identification for UF6 cylinders. Machine Vision and Applications, to appear, 2011.
@ARTICLE{author = {J. Yao et. al.}, journal= {Machine Vision and Applications}, booktitle= { Machine Vision and Applications}, year = {2011}} - Planar Motion Estimation and Linear Ground Plane Rectification using an Uncalibrated Generic Camera
@ARTICLE{author = {Taddei, Pierluigi and Espuny, Ferran and Caglioti, Vincenzo}, title = {Planar Motion Estimation and Linear Ground Plane Rectification using an Uncalibrated Generic Camera}, journal = {International Journal of Computer Vision}, publisher = {Springer Netherlands}, year = {2011}}
We address and solve the self-calibration of a generic camera that performs planar motion while viewing (part of) a ground plane. Concretely, assuming initial sets of correspondences between several images of the ground plane as known, we are interested in determining both the camera motion and the geometry of the ground plane. The latter is obtained through the rectification of the image of the ground plane, which gives a bijective correspondence between pixels and points on the ground plane.
We initially propose a method to determine the camera motion by using the motion flow between pairs of images. We perform this step with no need of camera calibration. Our solution requires the fixed ground point of the camera motion to be visible on both images.
Once the camera motion is known, either by using our method or by other alternative means (e.g. GPS-based), we show that the rectification of the ground plane can be determined linearly from at least three images up to a scale factor. Experimental results on real images are presented at the end of the paper to validate the proposed methods. - Robust surface registration using N-points approximate congruent sets
@ARTICLE{author ={Jian Yao et al.}, title = {Robust surface registration using N-points approximate congruent sets}, booktitle = {Journal on Advances in Signal Processing}, year = {2011}}
Scans acquired by 3D sensors are typically represented in a local coordinate system. When multiple scans, taken from different locations, represent the same scene these must be registered to a common reference frame. We propose a fast and robust registration approach to automatically align two scans by finding two sets of N-points, that are approximately congruent under rigid transformation and leading to a good estimate of the transformation between their corresponding point clouds. Given two scans, our algorithm randomly searches for the best sets of congruent groups of points using a RANSAC-based approach. To successfully and reliably align two scans when there is only a small overlap, we improve the basic RANSAC random selection step by employing a weight function that approximates the probability of each pair of points in one scan to match one pair in the other. The search time to find pairs of congruent sets of N-points is greatly reduced by employing a fast search Scans acquired by 3D sensors are typically represented in a local coordinate system. When multiple scans, taken from different locations, represent the same scene these must be registered to a common reference frame. We propose a fast and robust registration approach to automatically align two scans by finding two sets of N-points, that are approximately congruent under rigid transformation and leading to a good estimate of the transformation between their corresponding point clouds. Given two scans, our algorithm randomly searches for the best sets of congruent groups of points using a RANSAC-based approach. To successfully and reliably align two scans when there is only a small overlap, we improve the basic RANSAC random selection step by employing a weight function that approximates the probability of each pair of points in one scan to match one pair in the other. The search time to find pairs of congruent sets of N-points is greatly reduced by employing a fast search
- Complex and Photo-realistic Scene Representation Based on Range Planar Segmentation and Model Fusions
@ARTICLE{author ={Jian Yao et al.}, title = {Complex and Photo-realistic Scene Representation Based on Range Planar Segmentation and Model Fusions}, booktitle = {The International Journal of Robotics Research}, year = {2011}}
We present an efficient 3D scene representation method from a set of 3D range scans captured from a large-scale indoor or outdoor scene based on range planar segmentation and model fusion. In our method, range images are partitioned into planar patches and non-planar regions. We firstly partition the range image into a set of rectangle blocks and fit a planar patch to all points of each block. Blocks that are not successfully fitted as planar patches, are iteratively partitioned into sub-blocks until reaching a minimum size. Secondly, we iteratively merge the planar patches and identify unclassified rectangle blocks or points. The segmentation is then refined by relabelling the boundary points of fitted planar patches with respect to the neighbouring planar patches. We further simplify the scene model representation by fusing range scans and welding neighbouring planar patches with clean straight boundaries. An efficient texture mapping approach is proposed to automatically map the reflectance/colour images onto the fused scene model composed of a set of planar patches. Finally we successfully demonstrate the performance of our algorithms on several challenging range data sets.
2010
- Automatic Scan Registration Using 3D Linear and Planar Features
@ARTICLE{author ={Jian Yao et al.}, title = {Automatic Scan Registration Using 3D Linear and Planar Features}, booktitle = {3D Research}, year = {2010}}
We present a common framework for accurate and automatic registration of two geometrically complex 3D range scans by using linear or planar features. The linear features of a range scan are extracted with an efficient split and merge line-fitting algorithm, which refines 2D edges extracted from the associated reflectance image considering the corresponding 3D depth information. The planar features are extracted employing a robust planar segmentation method, which partitions a range image into a set of planar patches. We propose an efficient probabilitybased RANSAC algorithm to automatically register two overlapping range scans. Our algorithm searches for matching pairs of linear (planar) features in the two range scans leading to good alignments. Line orientation (plane normal) angles and line (plane) distances formed by pairs of linear (planar) features are invariant with respect to the rigid transformation and are utilized to find candidate matches. To efficiently seek for candidate pairs and groups of matched features we build a fast search codebook. Given two sets of matched features, the rigid transformation between two scans is computed by using iterative linear optimization algorithms. The efficiency and accuracy of our registration algorithm were evaluated on several challenging range data sets
- Robust Range Image Registration Using 3D Lines
@INPROCEEDINGS{author = {Jian Yao et al.}, title = {Robust Range Image Registration Using 3D Lines}, booktitle = {ICIP}, year = {2010}, month = {September}}
We present an efficient method for accurate automatic registration of two geometrically complex 3D range scans by using 3D lines. We first detect edges from the associated 2D reflectance images and collect 3D edge contours by only taking into account valid foreground points. Then we use an efficient split-and-merge line fitting algorithm to detect 3D lines. Thus, we get a set of 3D lines from each 3D range scan. We build a fast search codebook to efficiently match the two sets of 3D lines. This is done by computing the orientation angle and distance of pairs of 3D lines in each set, both of which are invariant under rigid transformations. Finally we recover the rigid transformation between two scans using an efficient RANSAC algorithm with robust transformation estimation that exploits two sets of corresponding 3D lines. We conclude presenting experimental results that demonstrate efficiency and accuracy of our proposed method.
2009
- Rawseeds ground truth collection systems for indoor self-localization and mapping
@ARTICLE{author = {Simone Ceriani et al.}, title = {Rawseeds ground truth collection systems for indoor self-localization and mapping}, booktitle = {Autonomous Robots}, year = {2009}, month = {November}}
A trustable and accurate ground truth is a key requirement for benchmarking self-localization and mapping algorithms; on the other hand, collection of ground truth is a complex and daunting task, and its validation is a challenging issue. In this paper we propose two techniques for indoor ground truth collection, developed in the framework of the European project Rawseeds, which are mutually independent and also independent on the sensors onboard the robot. These techniques are based, respectively, on a network of fixed cameras, and on a network of fixed laser scanners. We show how these systems are implemented and deployed, and, most importantly, we evaluate their performance; moreover, we investigate the possible fusion of their outputs
2008
- Planar Motion Estimation Using an Uncalibrated General Camera
@INPROCEEDINGS{author = {Vincenzo Caglioti and Pierluigi Taddei}, title = {Planar Motion Estimation Using an Uncalibrated General Camera}, booktitle = {OMNIVIS}, year = {2008}, month = {October}}
Generic camera odometry can be performed using two images of the same plane, such as the ground plane even in the case of non central cameras. It is possible to recover both the angle and rotation center describing a generic planar motion on the ground plane if the center is visible in both images. We present an algorithm to recover these two parameters from an initial set of correspondences and, furthermore, to estimate the motion flow related to any point on the ground plane. In this situation the motion flows are given by a set of “concentric” closed curves around the rotation center. By considering two subsequent ground plane motions and their related motion flows, we show that it is possible to perform a rectification of the plane up to a scale factor. We provide experimental results which validate our approach
- A Manipulable Vision-Based 3D Input Device for Space Curves
@INPROCEEDINGS{author = {Vincenzo Caglioti et al.}, title = {A Manipulable Vision-Based 3D Input Device for Space Curves}, booktitle = {AMDO}, year = {2008}}
This paper presents a novel and user friendly input device for 3D curves. The system is based on a piece of flexible wire and a single off-the-shelf photo camera: the user bends the wire to the desired 3D shape; then, an ad-hoc technique for 3D reconstruction is used to recover its 3D shape (a space curve) from a single image. The result is a simple, unusual input device with many potential applications, ranging from games to 3D modeling. For untrained users, this is a much more intuitive input technique than alternative methods. A disadvantage is that changes to the wire’s shape are not reflected in real time on the recovered representation. We give a detailed description of the system’s structure, briefly recall the reconstruction technique, and describe a prototype in which the input device is seamlessly integrated in the popular Blender 3D modeling software. We finally show simple example applications in which the shape of the wire is used to define the trajectory of moving objects, to deform a 3D object, and to animate a 3D character.
- Template-Based Paper Reconstruction from a Single Image is Well Posed when the Rullings are Parallel
@INPROCEEDINGS{author = {Pierluigi Taddei and Adrien Bartoli}, title = {Template-Based Paper Reconstruction from a Single Image is Well Posed when the Rullings are Parallel}, booktitle = {NORDIA Workshop}, year = {2008}, month = {June}}
We deal with the 3D reconstruction of deformed paperlike surfaces given a template and a single perspective image, for which the internal camera parameters are known. The general problem is ill-posed. We show that when the surface rulings are parallel the problem is well-posed. Given a procedure to recover the rulings direction, this particular problem is equivalent to the reconstruction of a 2D curve seen from a set of 1D camera pairs given a 1D template. Paper can be physically modeled by exploiting local properties. This allows us to formulate the reconstruction problem by non linear variational optimization. We provide experimental results which validate our approach on simulated and real data
2007
- Single-Image Calibration of Off-Axis Catadioptric Cameras Using Lines
@INPROCEEDINGS{author = {Vincenzo Caglioti and Pierluigi Taddei and Giacomo Boracchi and Simone Gasparini and Alessandro Giusti}, title = {Single-Image Calibration of Off-Axis Catadioptric Cameras Using Lines}, booktitle = {OMNIVIS Workshop}, year = {2007}, month = {October}}
We present a novel calibration method for off-axis catadioptric cameras, i.e. standard perspective cameras placed in a generic position w.r.t. an axial-symmetric mirror of unknown shape. The proposed method estimates the intrinsic parameters of the natural perspective camera, the 3D shape of the mirror and its pose w.r.t. the camera. The peculiarity of our approach is that, unlike several other calibration methods, we do not require any cross section of the mirror to be visible in the image. Instead, we require that the catadioptric image contains at least the image of one generic space line. We then derive some constraints that, combined with the harmonic homology relating the apparent contours of the mirror, allow us to calibrate the off-axis camera. We provide experimental results both on synthetic and camera images that prove the validity of the technique.
- Methods for space line localization from single catadioptric images: new proposals and comparisons
@INPROCEEDINGS{author = {Vincenzo Caglioti and Simone Gasparini and Pierluigi Taddei}, title = {Methods for space line localization from single catadioptric images: new proposals and comparisons}, booktitle = {OMNIVIS Workshop}, year = {2007}, month = {October}}
