The human visual system uses priors to convert an ill-posed inverse problem of 3D shape recovery into a well-posed one. In previous studies, we have demonstrated the use of priors like symmetry, compactness and minimal surface in the perception of 3D symmetric shapes. We also showed that binocular perception of symmetric shapes can be well modeled by the above-mentioned priors and binocular depth order information. In this study, which used a shape-matching task, we show that these priors can also be used to model perception of near-symmetrical shapes. Our near-symmetrical shapes are asymmetrical shapes obtained from affine distortions of symmetrical shapes. We found that the perception of symmetrical shapes is closer to veridical than the perception of asymmetrical shapes is. We introduce a metric to measure asymmetry of abstract polyhedral shapes, and a similar metric to measure shape dissimilarity between two polyhedral shapes. We report some key observations obtained by analyzing the data from the experiment. A website was developed with all the shapes used in the experiment, along with the shapes recovered by the subject and the shapes recovered by the model. This website provides a qualitative analysis of the effectiveness of the model and also helps demonstrate the goodness of the shape metric.
Abstract. We present an approach to figure/ground organization using mirror symmetry as a general purpose and biologically motivated prior. Psychophysical evidence suggests that the human visual system makes use of symmetry in producing three-dimensional (3-D) percepts of objects. 3-D symmetry aids in scene organization because (i) almost all objects exhibit symmetry, and (ii) configurations of objects are not likely to be symmetric unless they share some additional relationship. No general purpose approach is known for solving 3-D symmetry correspondence in two-dimensional (2-D) camera images, because few invariants exist. Therefore, we present a general purpose method for finding 3-D symmetry correspondence by pairing the problem with the two-view geometry of the binocular correspondence problem. Mirror symmetry is a spatially global property that is not likely to be lost in the spatially local noise of binocular depth maps. We tested our approach on a corpus of 180 images collected indoors with a stereo camera system. K -means clustering was used as a baseline for comparison. The informative nature of the symmetry prior makes it possible to cluster data without a priori knowledge of which objects may appear in the scene, and without knowing how many objects there are in the scene. IntroductionAccording to most studies of human vision, the first step in visual perception is determining whether there are objects in front of the observer: where they are and how many there are. This step (visual function) is called figure-ground organization (FGO). 1 The computer vision community refers to this problem as object discovery. As with all natural visual functions of human observers, FGO operates in three-dimensional (3-D) space, as opposed to the two-dimensional (2-D) retinal image. It follows that it is natural to think about visual mechanisms underlying FGO as based on 3-D operations. However, the fact that the input to the visual system is one or more 2-D retinal images encouraged previous researchers to look for a theory of FGO based on 2-D operations. This is how the human vision community studied FGO. Consider the prototypical example of Edgar Rubin's vase-faces stimulus.2 In this 2-D stimulus, there are two possible interpretations depending on which region is perceived as a "figure" as opposed to the "ground." Similar bistable stimuli have been used during the last several dozen years of FGO research in human vision.3,4 This research provided a large body of results, but few theories and computational models. Furthermore, the proposed models are usually not suitable for real retinal or camera images representing 3-D scenes. This paper breaks with this tradition and looks for 3-D operations that can establish the correct 3-D FGO.
For this study a ground-based sky imaging system was developed that, unlike most other such systems, consists of a low-cost sun-tracking camera fitted with a fish-eye lens. The application of interest is short-term solar power forecasting, so cloud detection is an important step. The hybrid thresholding algorithm proposed by Li et al. for cloud detection is employed. Most cloud detection algorithms make use of the red and blue components in a color image. Though these features perform well for many images, they do not produce good results for the images in this study due to the insufficient contrast between cloud and sky pixels when using ratios between red and blue. To overcome this issue, a new feature, the normalized saturation/value (NSV) ratio, is proposed that is computed in the hue-saturation-value (HSV) color space. This study shows that the NSV ratio produces good contrast between cloud and sky pixels not only for the images in this study but also for general sky images acquired using different camera systems. The reasoning behind the choice of the new ratio is described, and quantitative and qualitative results are presented.
We present a new algorithm for 3D shape reconstruction from stereo image pairs that uses mirror symmetry as a biologically inspired prior. 3D reconstruction requires some form of prior because it is an ill-posed inverse problem. Psychophysical research shows that mirror-symmetry is a key prior for 3D shape perception in humans, suggesting that a general purpose solution to this problem will have many applications. An approach is developed for finding objects that fit a given shape definition. The algorithm is developed for shapes with two orthogonal planes of symmetry, thus allowing for straightforward recovery of occluded portions of the objects. Two simulations were run to test: (1) the accuracy of 3D recovery, and (2) the ability of the algorithm to find the object in the presence of noise. We then tested the algorithm on the Children's Furniture Corpus, a corpus of stereo image pairs of mirror symmetric furniture objects. Runtimes and 3D reconstruction errors are reported and failure modes described.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.