Distance transform

About: Distance transform is a research topic. Over the lifetime, 2886 publications have been published within this topic receiving 59481 citations.

Evolutionary Distance Metric Learning Approach to Semi-supervised Clustering with Neighbor Relations

Abstract: This study proposes a distance metric learning method based on a clustering index with neighbor relation that simultaneously evaluates inter-and intra-clusters. Our proposed method optimizes a distance transform matrix based on the Mahalanobis distance by utilizing a self-adaptive differential evolution (jDE) algorithm. Our approach directly improves various clustering indices and in principle requires less auxiliary information compared to conventional metric learning methods. We experimentally validated the search efficiency of jDE and the generalization performance.

Accurate extrinsic calibration between monocular camera and sparse 3D Lidar points without markers

Abstract: It is of practical interest to automatically calibrate the multiple sensors in autonomous vehicles. In this paper, we deal with an interesting case when used low-resolution Lidar and present a practical approach to extrinsic calibration between monocular camera and Lidar with sparse 3D measurements. We formulate the problem as directly minimizing the feature error evaluated between frames following the way of image warping. To overcome the difficulties in the optimization problem, we propose to use the distance transform and further projection error model to obtain the key approximated edge points that are sensitive to the loss function. Finally, the loss minimization is solved by an efficient random selection algorithm. Experimental results on KITTI dataset show that our proposed method can achieve competitive results and an improvement in translation estimation particularly.

Image capture device and image capture method

Abstract: Disclosed is an image capture device that generates a distance map to a photographic subject from a photographic image, with high precision. Three images are photographed with a sensor drive unit (12) and a sensor drive controller unit (13), which move an image sensor (11) in the optical axis direction: photographic images (A, C) that are respectively focused on the near-end side and the far-end side of the photographic subject, and an image (B) that is photographed while sweeping the image sensor from the near-end side to the far-end side. An omnifocal image (D) is generated by an omnifocal image generator unit (15) from the sweep image (B); a blur quantity in each component region of the image (A) and the image (B) is computed by a blur quantity computation unit (16), carrying out a deconvolution process with an image of a region corresponding to the omnifocal image (D); and the distance from the device to the photographic subject in each image region, i.e., a distance map, is generated by a distance map generator unit (17) from the blur quantity of the regions corresponding to the near-end image (A) and the far-end image (C) and optical coefficients of the image capture device, including the focal length of the lens.

A Neural Model of Distance-Dependent Percept of Object Size Constancy.

Abstract: Size constancy is one of the well-known visual phenomena that demonstrates perceptual stability to account for the effect of viewing distance on retinal image size. Although theories involving distance scaling to achieve size constancy have flourished based on psychophysical studies, its underlying neural mechanisms remain unknown. Single cell recordings show that distance-dependent size tuned cells are common along the ventral stream, originating from V1, V2, and V4 leading to IT. In addition, recent research employing fMRI demonstrates that an object’s perceived size, associated with its perceived egocentric distance, modulates its retinotopic representation in V1. These results suggest that V1 contributes to size constancy, and its activity is possibly regulated by feedback of distance information from other brain areas. Here, we propose a neural model based on these findings. First, we construct an egocentric distance map in LIP by integrating horizontal disparity and vergence through gain-modulated MT neurons. Second, LIP neurons send modulatory feedback of distance information to size tuned cells in V1, resulting in a spread of V1 cortical activity. This process provides V1 with distance-dependent size representations. The model supports that size constancy is preserved by scaling retinal image size to compensate for changes in perceived distance, and suggests a possible neural circuit capable of implementing this process.

Industrial parts recognition and inspection by image morphology

Abstract: Application algorithms for industrial parts and tool recognition and inspection by image morphology techniques are discussed. A recursive adaptive thresholding algorithm transforms a gray-level image into a set of multiple-level regions of objects. This algorithm uses a morphological erosion with a large symmetrical concave structuring element. A distance-transformation algorithm transforms these binary image regions into the minimum distance from each object point to the boundary of the object. This algorithm also uses a morphological erosion. From the distance transform, it is possible to compute a shape number and extract the skeleton, which is useful for generic pattern recognition and feature extraction. Corner angles and the radii of circular holes can be located, identified, and estimated by using morphological openings and erosions. The algorithms allow robust tool and part recognition and inspection. >