Feature-based Structure Research Articles

Structure shapes the representation of a novel category.

Concepts contain rich structures that support flexible semantic cognition. These structures can be characterized by patterns of feature covariation: Certain features tend to cluster in the same items (e.g., feathers, wings, can fly). Existing computational models demonstrate how this kind of structure can be leveraged to slowly learn the distinctions between categories, on developmental timescales. However, it is not clear whether and how we leverage feature structure to quickly learn a novel category. We thus investigated how the internal structure of a new category is first extracted from experience, with the prediction that feature-based structure would have a rapid and broad influence on the learned category representation. Across three experiments, novel categories were designed with patterns of feature associations determined by carefully constructed graph structures, with Modular graphs-exhibiting strong clusters of feature covariation-compared against Random and Lattice graphs. In Experiment 1, a feature inference task using verbal stimuli revealed that Modular structure broadly facilitated category learning. Experiment 2 replicated this effect in visual categories. In Experiment 3, a statistical learning paradigm revealed that this Modular benefit relates to high-level structure rather than pairwise feature associations and persists even when category structure is incidental to the task. A neural network model was readily able to account for these effects, suggesting that correlational feature structure may be encoded within rapidly learned, distributed category representations. These findings constrain theories of category representation and link theories of category learning with structure learning more broadly. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Robust 3D reconstruction from uncalibrated small motion clips

Small motion can be induced from burst video clips captured by a handheld camera when the shutter button is pressed. Although uncalibrated burst video clip conveys valuable parallax information, it generally has small baseline between frames, making it difficult to reconstruct 3D scenes. Existing methods usually employ a simplified camera parameterization process with keypoint-based structure from small motion (SFSM), followed by a tailored dense reconstruction. However, such SFSM methods are sensitive to insufficient or unreliable keypoint features, and the subsequent dense reconstruction may fail to recover the detailed surface. In this paper, we propose a robust 3D reconstruction pipeline by leveraging both keypoint and line segment features from video clips to alleviate the uncertainty induced by small baseline. A joint feature-based structure from small motion method is first presented to improve the robustness of the self-calibration with line segment constraints, and then, a noise-aware PatchMatch stereo module is proposed to improve the accuracy of the dense reconstruction. Finally, a confidence weighted fusion process is utilized to further suppress depth noise and mitigate erroneous depth. The proposed method can reduce the failure cases of self-calibration when the keypoints are insufficient, while recovering the detailed 3D surfaces. In comparison with state of the arts, our method achieves more robust and accurate 3D reconstruction results for a variety of challenging scenes.

3-D object modeling from 2-D occluding contour correspondences by opti-acoustic stereo imaging

Utilizing in situ measurements to build 3-D volumetric object models under variety of turbidity conditions is highly desirable for marine sciences. To address the ineffectiveness of feature-based structure from motion and stereo methods under poor visibility, we explore a multi-modal stereo imaging technique that utilizes coincident optical and forward-scan sonar cameras, a so-called opti-acoustic stereo imaging system. The challenges of establishing dense feature correspondences in either opti-acoustic or low-contrast optical stereo images are avoided, by employing 2-D occluding contour correspondences, namely, the images of 3-D object occluding rims. Collecting opti-acoustic stereo pairs while circling an object, matching 2-D apparent contours in optical and sonar views to construct the 3-D occluding rim, and computing the stereo rig trajectory by opti-acoustic bundle adjustment, we generate registered samples of 3-D surface in a reference coordinate system. A surface interpolation gives the 3-D object model.In addition to the key advantage of utilizing range measurements from sonar, the proposed paradigm requires no assumption about local surface curvature as traditionally made in 3-D shape reconstruction from occluding contours. The reconstruction accuracy is improved by computing both the 3-D positions and local surface normals of sampled contours. We also present (1) a simple calibration method to estimate and correct for small discrepancy from the desired relative stereo pose; (2) an analytical analysis of the degenerate configuration that enables special treatment in mapping (tall) elongated objects with dominantly vertical edges. We demonstrate the performance of our method based on the 3-D surface rendering of certain objects, imaged by an underwater opti-acoustic stereo system.

Single camera absolute motion based digital elevation mapping for a next generation planetary lander

Robotic planetary surface exploration missions are becoming much more ambitious in their science goals as they attempt to answer the bigger questions relating to the possibility of life elsewhere in our solar system. Answering these questions will require scientifically rich landing sites. Such sites are unlikely to be located in relatively flat regions that are free from hazards, therefore there is a growing need for next generation entry descent and landing systems to possess highly sophisticated navigation capabilities coupled with active hazard avoidance that can enable a pin-point landing. As a first step towards achieving these goals, a multi-source, multi-rate data fusion algorithm is presented that combines single camera recursive feature-based structure from motion (SfM) estimates with measurements from an inertial measurement unit in order to overcome the scale ambiguity problem by directly estimating the unknown scale factor. This paper focuses on accurate estimation of absolute motion parameters, as well as the estimation of sparse landing site structure to provide a starting point for hazard detection. We assume no prior knowledge of the landing site terrain structure or of the landing craft motion in order to fully assess the capabilities of the proposed algorithm to allow a pin-point landing on distant solar system bodies where accurate knowledge of the desired landing site may be limited. We present results using representative synthetic images of deliberately challenging landing scenarios, which demonstrates that the proposed method has great potential.

A Quantitative Empirical Analysis of the Abstract/Concrete Distinction

This study presents original evidence that abstract and concrete concepts are organized and represented differently in the mind, based on analyses of thousands of concepts in publicly available data sets and computational resources. First, we show that abstract and concrete concepts have differing patterns of association with other concepts. Second, we test recent hypotheses that abstract concepts are organized according to association, whereas concrete concepts are organized according to (semantic) similarity. Third, we present evidence suggesting that concrete representations are more strongly feature-based than abstract concepts. We argue that degree of feature-based structure may fundamentally determine concreteness, and we discuss implications for cognitive and computational models of meaning.

Partial differential equation-based dense 3D structure and motion estimation from monocular image sequences

In this study, the authors propose an approach towards dense depth reconstruction, combining robust feature-based structure from motion with the spatial coherence of dense reconstruction algorithms. To achieve this, a variational framework was set up, minimising the epipolar reprojection error and the image brightness constraint, while preserving discontinuities in the depth field by introducing an anisotropic diffusion term. As initial guess for the iterative solver, a region growing algorithm is proposed which mixes sparse and dense data.

Feature-based spline optimization in CAD

In this paper, an advanced method for CAD-based spline structure optimization is investigated. The method is based on the combination of the commonly known parameter-based spline shape optimization and a recently presented feature-based structure variation concept for commercial CAD tools. The aim is to extend common parameter-based spline shape variation by the additional possibility to automatically add and remove control points or entire splines directly in CAD space. Such advanced spline modification provides a new level of flexibility in general geometry-based structural optimization. Using these splines to build CAD models, entirely new structures may be automatically generated during an optimization run through this newly gained flexibility in spline manipulation. The idea is to roughly define a continuous design space by basic splines and to gradually increase their shape complexity by control point number variation during optimization. Thus, operating on a knowledge-lean initialization—a design space bounded by basic splines and filled with material—this combination further extends the search and solution spaces of CAD-based structural optimization. The paper provides an outlook towards automated geometry-based structure creation combining nowadays commercial CAD software and a dedicated variation and optimization framework for geometry-based structural optimization.

SBA

Bundle adjustment constitutes a large, nonlinear least-squares problem that is often solved as the last step of feature-based structure and motion estimation computer vision algorithms to obtain optimal estimates. Due to the very large number of parameters involved, a general purpose least-squares algorithm incurs high computational and memory storage costs when applied to bundle adjustment. Fortunately, the lack of interaction among certain subgroups of parameters results in the corresponding Jacobian being sparse, a fact that can be exploited to achieve considerable computational savings. This article presents sba, a publicly available C/C++ software package for realizing generic bundle adjustment with high efficiency and flexibility regarding parameterization.

A feature-based topological optimization for structure design

The feature-based modeling technology in computer aided design (CAD) has been widely studied, which greatly facilitates the manufacture of the design. We have incorporated the standard idea into topology optimization, and developed a feature-based structure topology optimization method. The method applies a real valued function to implicitly represent complex material interfaces of a design structure, and employs constructive solid geometry (CSG) to describe the design structure based on a set of simple geometric primitives during the topological optimization process. Meanwhile, the topological derivative analysis is adopted to determine where a simple geometric primitive is inserted in the current structure, and the morphing technology is used to determine which is chosen among the given geometric primitives by combining with the sensitivity analysis. In addition, Boolean operations on the geometric primitives are implemented by R-function method, which guarantees the regularity of the structure representation function, and which meets the need of the structure boundary smoothness for finite element analysis in the fixed Euler meshes. Finally, in order to further simplify the design structure, the shape matching technique is applied to merge the given geometric primitives so that each connected perforation is only constructed by one based geometric primitive.