Alexander Zouhar

Anatomically-Aware, Automatic, and Fast Registration of 3D Ear Impression Models

We present a registration framework based on feature points of anatomical, 3D shapes represented in the point cloud domain. Anatomical information is utilized throughout the complete registration process. The surfaces, which in this paper are ear impression models, are considered to be similar in the way that they possess the same anatomical regions but with varying geometry. First, in a shape analysis step, features of important anatomical regions (such as canal, aperture, and concha) are extracted automatically. Next these features are used in ordinary differential equations that update rigid registration parameters between two sets of feature points. For refinement of the results, the GCP algorithm is applied. Through our experiments, we demonstrate our techniques success in surface registration through registration of key anatomical regions of human ear impressions. Furthermore, we show that the proposed method achieves higher accuracy and faster performance than the standard GCP registration algorithm.

3-D shape modeling for hearing aid design [Applications Corner]

Advances in 3-D scanning and fabrication hardware as well as 3-D geometric design software have transformed a once laborintensive manual manufacturing into an efficient digital process for hearing aid design, resulting in higher quality, reduced cost, and better fitting devices. Future work in this field will continue to focus on increasing automation until the process is fully automatic.

Automatic detection of anatomical features on 3D ear impressions for canonical representation

We propose a shape descriptor for 3D ear impressions, derived from a comprehensive set of anatomical features. Motivated by hearing aid (HA) manufacturing, the selection of the anatomical features is carried out according to their uniqueness and importance in HA design. This leads to a canonical ear signature that is highly distinctive and potentially well suited for classification. First, the anatomical features are characterized into generic topological and geometric features, namely concavities, elbows, ridges, peaks, and bumps on the surface of the ear. Fast and robust algorithms are then developed for their detection. This indirect approach ensures the generality of the algorithms with potential applications in biomedicine, biometrics, and reverse engineering.

Layout consistent segmentation of 3-D meshes via conditional random fields and spatial ordering constraints

We address the problem of 3-D Mesh segmentation for categories of objects with known part structure. Part labels are derived from a semantic interpretation of non-overlapping subsurfaces. Our approach models the label distribution using a Conditional Random Field (CRF) that imposes constraints on the relative spatial arrangement of neighboring labels, thereby ensuring semantic consistency. To this end, each label variable is associated with a rich shape descriptor that is intrinsic to the surface. Randomized decision trees and cross validation are employed for learning the model, which is eventually applied using graph cuts. The method is flexible enough for segmenting even geometrically less structured regions and is robust to local and global shape variations.

Freeform shape clustering for customized design automation

Automation can provide significant performance improvements in digital manufacturing systems that customize shapes of implants and prosthetic devices to the anatomy of a patient. The challenge, however, lies in the ability of an automatic solution to adapt to anatomical variations of a given object category. This paper presents a hierarchical framework that generalizes the digital design of anatomical surface models in terms of a small number of prototypes. The latter are derived from the local shape information of constituent parts via shape matching and clustering and then associated with one operation that dictates how a shape undergoes modification. We demonstrate the proposed technique through application to typical hearing aid design operations with promising results.

Performance Evaluation of LiDAR Point Clouds towards Automated FOD Detection on Airport Aprons

Both the current system of airport ground control and the continuous implementation efforts of A-SMGCS and Remote Tower concepts require complete and independent surveillance coverage in real-time. We believe that 3D point clouds generated by an actively scanning LiDAR system available at TU Dresden may satisfy these high standards. Nonetheless, the utilization of LiDAR sensing for airport ground surveillance purposes is extremely challenging due to the unique requirement profile in this domain. This is also the reason why existing solutions in other domains such as autonomous driving and robotics are not directly applicable for airport ground surveillance. In a first step, we developed point cloud object detection and segmentation techniques to present that new data comprehensively to the airport apron controller. In this paper, we focused on the timely detection of dislocated objects (foreign object debris, forgotten equipment etc.) as a serious cause to hazardous situations on airport movement areas. The results are promising for various reference targets. However, the detection of very small objects (e.g. socket wrench) requires more elaborate algorithms to take full advantage of the current LiDAR technology. In the future we will assess the strength of LiDAR-based surveillance in terms of the number of hazardous situations that could be avoided or safely managed by the apron controller.

Joint Shape Classification and Labeling of 3-D Objects Using the Energy Minimization Framework

We propose a combination of multiple Conditional Random Field (CRF) models with a linear classifier. The model is used for the semantic labeling of 3-D surface meshes with large variability in shape. The model employs multiple CRFs of low complexity for surface labeling each of which models the distribution of labelings for a group of surfaces with a similar shape. Given a test surface the classifier exploits the MAP energies of the inferred CRF labelings to determine the shape class. We discuss the associated recognition and learning tasks and demonstrate the capability of the joint shape classification and labeling model on the object category of human outer ears.

Deformable registration of organic shapes via surface intrinsic integrals: application to outer ear surfaces

We propose a method for the deformable registration of organic surfaces. Meaningful correspondences between a source surface and a target surface are established by means of a rich surface descriptor that incorporates three categories of features: (1) local and regional geometry; (2) surface anatomy; and (3) global shape information. First, surface intrinsic, geodesic distance integrals, are exploited to constrain the global geodesic layout. Consequently, the resulting transformation ensures topological consistency. Local geometric features are then introduced to enforce local conformity of various regions. To this end, the extrema of appropriate curvatures -- the extrema of mean curvature, minima of Gauss and minimum principal curvature, and the maxima of maximum principal curvature -- are considered. Regional features are introduced through curvature integrals over various scales. On top of this, explicit anatomical priors are included, thereby resulting in anatomically more consistent registration. The source surface is deformed to the target by minimizing the energy of matching the source features to the target features under a Gaussian propagation model. We validate the proposed method with application to the outer ear surfaces.

Semantic 3-D Labeling of Ear Implants Using a Global Parametric Transition Prior

In this work we consider the problem of sematic part-labeling of 3-D meshesof ear implants. This is a challenging problem and automatic solutions are of high practical relevance, since they help to automate the design of hearing aids. The contribution of this work is a new framework which outperforms existing approaches for this task. To achieve the boost in performance we introduce the new concept of a global parametric transition prior. To our knowledge, this is the first time that such a generic prior is used for 3-D mesh processing, and it may be found useful for a large class of 3-D meshes. To foster more research on the important topic of ear implant labeling, we collected a large data set of 3-D meshes, with associated ground truth labels, which we will make publicly available.