scispace - formally typeset
Search or ask a question

Showing papers on "Distance transform published in 2022"


Journal ArticleDOI
TL;DR: Li et al. as mentioned in this paper proposed a novel Focal Inverse Distance Transform (FIDT) map for the crowd localization task, which accurately describes the persons' locations without overlapping in dense regions.
Abstract: In this paper, we focus on the crowd localization task, a crucial topic of crowd analysis. Most regression-based methods utilize convolution neural networks (CNN) to regress a density map, which can not accurately locate the instance in the extremely dense scene, attributed to two crucial reasons: 1) the density map consists of a series of blurry Gaussian blobs, 2) severe overlaps exist in the dense region of the density map. To tackle this issue, we propose a novel Focal Inverse Distance Transform (FIDT) map for the crowd localization task. Compared with the density maps, the FIDT maps accurately describe the persons' locations without overlapping in dense regions. Based on the FIDT maps, a Local-Maxima-Detection-Strategy (LMDS) is derived to effectively extract the center point for each individual. Furthermore, we introduce an Independent SSIM (I-SSIM) loss to make the model tend to learn the local structural information, better recognizing local maxima. Extensive experiments demonstrate that the proposed method reports state-of-the-art localization performance on six crowd datasets and one vehicle dataset. Additionally, we find that the proposed method shows superior robustness on the negative and extremely dense scenes, which further verifies the effectiveness of the FIDT maps. The code and model will be available at https://github.com/dk-liang/FIDTM.

17 citations


Journal ArticleDOI
TL;DR: In this paper, a convolutional neural network is used to parameterize the mapping from a set of lamination parameters on a coarse mesh to a one-scale design on a fine mesh to avoid solving the least square problems associated with traditional dehomogenization approaches and save time correspondingly.

8 citations


Journal ArticleDOI
01 Jan 2022
TL;DR: In this paper , Chamfer Distance Algorithm is used to find the shortest path between any two points when the distance is computed, which reduces the overall processing time of the SIFT.
Abstract: Scale-Invariant Feature Transform is an image matching algorithm used to match objects of two images by extracting the feature points of target objects in each image. Scale-Invariant Feature Transform suffers from long processing time due to embedded calculations which reduces the overall speed of the technique. This research aims to enhance SIFT processing time by imbedding Chamfer Distance Algorithm to find the distance between image descriptors instead of using Euclidian Distance Algorithm used in SIFT. Chamfer Distance Algorithm requires less computational time than Euclidian Distance Algorithm because it selects the shortest path between any two points when the distance is computed. To validate and evaluate the enhanced algorithm, A data set with (412) images including: (100) images with different degrees of rotation, (100) images with different intensity levels, (112) images with different measurement levels and (100) distorted images to different degrees were used; these images were applied according to four different criteria. The simulation results showed that the enhanced SIFT outperforms the ORB and the original Scale-Invariant Feature Transform in term of the processing time, and it reduces the overall processing time of the classical SIFT by (41%).

2 citations



Journal ArticleDOI
TL;DR: In this paper , a distance transform algorithm for Discrete Global Grid Systems (DGGS) is proposed, which heavily exploits the hierarchy of a DGGS and its mathematical properties.
Abstract: Geospatial data analysis often requires the computing of a distance transform for a given vector feature. For instance, in wildfire management, it is helpful to find the distance of all points in an area from the wildfire’s boundary. Computing a distance transform on traditional Geographic Information Systems (GIS) is usually adopted from image processing methods, albeit prone to distortion resulting from flat maps. Discrete Global Grid Systems (DGGS) are relatively new low-distortion globe-based GIS that discretize the Earth into highly regular cells using multiresolution grids. In this paper, we introduce an efficient distance transform algorithm for DGGS. Our novel algorithm heavily exploits the hierarchy of a DGGS and its mathematical properties and applies to many different DGGSs. We evaluate our method by comparing its speed and distortion with the distance transform methods used in traditional GIS and general 3D meshes. We demonstrate that our method is efficient and has minimal distortion.

1 citations


Book ChapterDOI
01 Jan 2022
TL;DR: Kulkarni et al. as discussed by the authors proposed the Directed Ray Distance Function (DRDF) to handle complex topologies and large spaces for 3D scene reconstruction from a single image.
Abstract: We present an approach for full 3D scene reconstruction from a single unseen image. We trained on dataset of realistic non-watertight scans of scenes. Our approach uses a predicted distance function, since these have shown promise in handling complex topologies and large spaces. We identify and analyze two key challenges for predicting such image conditioned distance functions that have prevented their success on real 3D scene data. First, we show that predicting a conventional scene distance from an image requires reasoning over a large receptive field. Second, we analytically show that the optimal output of the network trained to predict these distance functions does not obey all the distance function properties. We propose an alternate distance function, the Directed Ray Distance Function (DRDF), that tackles both challenges. We show that a deep network trained to predict DRDFs outperforms all other methods quantitatively and qualitatively on 3D reconstruction from single image on Matterport3D, 3DFront, and ScanNet. (Project Page: https://nileshkulkarni.github.io/scene_drdf )

1 citations


Book ChapterDOI
01 Jan 2022
TL;DR: In this article , the authors examined the validity of the two raster sequences distance transform algorithm, originally given by Rosenfeld and Pfaltz for the distance $$d_4$$ , then extended to the weighted distances by Montanari and Borgefors.
Abstract: This paper examines the validity of the two raster sequences distance transform algorithm, originally given by Rosenfeld and Pfaltz for the distance $$d_4$$ , then extended to the weighted distances by Montanari and Borgefors. We show that the convergence in two passes does not hold for all chamfer masks, and we prove that the chamfer norm condition is a sufficient condition of validity for the algorithm.

Journal ArticleDOI
TL;DR: In this paper , the authors combine the Dahu pseudo-distance with edge information in a graph-cut optimization framework and leverage the complementary strengths of the two distance transform algorithms to improve the segmentation performance.

Posted ContentDOI
30 Jun 2022
TL;DR: In this paper , the authors introduce two new abstract morphs for two $2$-dimensional shapes and give an experimental analysis that includes the two new morphs and a recently introduced abstract morph that is also based on the Hausdorff distance.
Abstract: This paper introduces two new abstract morphs for two $2$-dimensional shapes. The intermediate shapes gradually reduce the Hausdorff distance to the goal shape and increase the Hausdorff distance to the initial shape. The morphs are conceptually simple and apply to shapes with multiple components and/or holes. We prove some basic properties relating to continuity, containment, and area. Then we give an experimental analysis that includes the two new morphs and a recently introduced abstract morph that is also based on the Hausdorff distance (Van Kreveld et al. Between shapes, using the Hausdorff distance. Computational Geometry 100:101817, 2022). We show results on the area and perimeter development throughout the morph, and also the number of components and holes. A visual comparison shows that one of the new morphs appears most attractive.


Journal ArticleDOI
TL;DR: This paper presents an approach for interactive editing of signed distance functions, derived from RGB-D data in the form of regular voxel grids, that enables the manual refinement and enhancement of reconstructed 3D geometry.
Abstract: Signed distance functions computed in discrete form from given RGB-D data as regular voxel grids can represent manifold shapes as the zero crossing of a trivariate function; the corresponding meshes can be derived by the Marching Cubes algorithm. However, 3D models automatically reconstructed in this way often contain irrelevant objects or artifacts, such as holes or noise, due to erroneous scan data and error-prone reconstruction processes. This paper presents an approach for interactive editing of signed distance functions, derived from RGB-D data in the form of regular voxel grids, that enables the manual refinement and enhancement of reconstructed 3D geometry. To this end, we combine concepts known from constructive solid geometry, where complex models are created from simple base shapes, with the voxel-based representation of geometry reconstructed from real-world scans. Our approach can be implemented entirely on GPU to enable real-time interaction. Further, we present how to implement high-level operators, such as copy, move, and unification.

Journal ArticleDOI
TL;DR: In this paper , a hybrid graphics processing unit (GPU)-accelerated marching wavefront method for computing distance transforms of models composed of trimmed non-uniform rational B-splines (NURBS) surfaces with theoretical bounds is presented.
Abstract: Abstract Distance field representation of objects in 3D space has several applications such as shape manipulation, graphics rendering, path planning, etc. Distance transforms (DTs) are discrete representations of distance fields in a regular voxel grid. The two main limitations of using distance transforms are that they are compute-intensive, and there are errors introduced while representing the object using DTs. In this work, we develop a hybrid graphics processing unit (GPU)-accelerated marching wavefront method for computing DTs of models composed of trimmed non-uniform rational B-splines (NURBS) surfaces with theoretical bounds. Our hybrid marching approach eliminates the error due to calculating approximate distances by marching. We also calculate the bounds on the error introduced due to the tessellation of the trimmed NURBS surfaces and calculate the propagation of these bounds in computing the DT. Finally, we present computation times for both 2D and 3D GPU DTs of test objects. We show that our GPU-accelerated approach is significantly faster than existing CPU-based methods.

Journal ArticleDOI
TL;DR: In this article , a unified morphological method was proposed to detect and segment clusters of erythrocytes in microscopy images, and the best alternative to split the clusters into their constituent individual cells after evaluating three algorithms based on H-maxima, weighted external distance and marker controlled watershed.
Abstract: Segmentation of clusters of erythrocytes into their constituent single cells is a procedure needed in various biomedical applications related to microscopy images. This task is part of the general problem of splitting clumps of objects in images which continues being an open research topic in the Image Processing field. This work presents a unified morphological method to detect and segment clusters of erythrocytes in microscopy images, and proposes two main contributions. The first one is to formulate and evaluate a method to detect clusters as connected components in binary images, obtained from a previous coarse segmentation, which is not capable of further dividing a cluster into its constituent cells. Secondly, to propose the best alternative to split the clusters into their constituent individual cells after evaluating three algorithms based in the combination of the transforms: H-maxima, weighted external distance and marker-controlled watershed. Evaluation of the proposed cluster detection methods was made in terms of standard measures of effectiveness. Segmentation accuracy was evaluated comparing the segmented objects obtained to a manually segmented ground truth, by means of the Jaccard index. Then the Friedman test allowed validating the advantages of the proposed method in comparison to the other alternatives studied here.

Journal ArticleDOI
TL;DR: In this article, the radial distance has been used as a tool to compare the shape of simple surfacic objects, and its theoretical properties have been derived under which conditions it satisfies the distance properties.
Abstract: Abstract In this paper, we examine the properties of the radial distance which has been used as a tool to compare the shape of simple surfacic objects. We give a rigorous definition of the radial distance and derive its theoretical properties, and in particular under which conditions it satisfies the distance properties. We show how the computation of the radial distance can be implemented in practice and made faster by the use of an analytical formula and a Fast Fourier Transform. Finally, we conduct experiments to measure how the radial distance is impacted by perturbation and generalization and we give abacuses and thresholds to deduce when buildings are likely to be homologous or non-homologous given their radial distance.

Journal ArticleDOI
01 Feb 2022-Optik
TL;DR: In this paper , a dualmode light field display with viewing distance detecting is proposed by changing the pixel clustering of the elemental image array and re-locating the center of the element image accordingly, the width of the viewing zone at target viewing distance is maximized and the viewing distance range of the light field displays is enhanced.


Journal ArticleDOI
TL;DR: An accurate edge detector using a distance field-based convolutional neural network (DF-CNN) that combines a feature extraction backbone that can fully exploit the multiscale and multilevel information of the edge with the supervised training of the distance field branch to realize the accurate end-to-end object edge detection.
Abstract: In this paper, we first propose an accurate edge detector using a distance field-based convolutional neural network (DF-CNN). In recent years, CNNs have been proved to be effective in image processing and computer vision. As edge detection is a fundamental problem among them, we try to improve the accuracy of edge detection based on the deep learning framework. The proposed network combines a feature extraction backbone that can fully exploit the multiscale and multilevel information of the edge with the supervised training of the distance field branch to realize the accurate end-to-end object edge detection. The distance field branch is applied to predict the Euclidean distance from nonedge points to the nearest edge point in the feature maps. And the distance information embedded in the predicted distance field map can effectively improve the accuracy of edge detection. The network is trained to minimize the weighted sum of the distance field branch loss and the cross-entropy loss. Our experimental results show that the proposed edge detector achieves better performance than previous approaches and the effectiveness of the proposed distance field branch.