Fast directional chamfer matching

By Ming-Yu Liu, Oncel Tuzel, Ashok Narayanan Veeraraghavan, Ramalingam Chellappa. 2010

223 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Pixelwise Instance Segmentation with a Dynamically Instantiated Network (2017, methodology): “Previous approaches to incorporating shape priors in segmentation [22, 7, 43] have involved generating “shape exemplars” from the training dataset and, at inference time, matching these exemplars to object proposals using the Chamfer distance [39, 31].”
3DNN: 3D Nearest Neighbor (2014, methodology): “This is similar to the directional chamfer matching approach introduced by Liu et al. (2010), with the addition of overlapping bins to alleviate the effects of quantization artifacts at the boundaries between buckets.”
Robust 3D visual tracking using particle filtering on the special Euclidean group: A combined approach of keypoint and edge features (2011, background): “However, it is well known that using edge orientation significantly enhances the quality of edge correspondences (Olson and Huttenlocher 2002; Liu et al. 2010).”
Learning to Rank 3D Features (2014, methodology): “Other than the local feature point based methods described in Section 1, there exists a large body of work that models 3D shapes globally such as using 2D/3D contours [3,4], shape templates [10,19], and feature histograms [33,12].”
Voting-based pose estimation for robotic assembly using a 3D sensor (2012, methodology): “Following the seminal paper on chamfer distance [5], there were several useful variants that incorporate edge orientation [6], [7] or employ hierarchical representation [8].”
Human detection from images and videos: A survey (2016, methodology): “Approximating edge pixels in the edge map by segments as proposed in [94] could reduce the number of edge pixels used in template matching and thus may speed up the template matching process.”
Multi-instance object segmentation with occlusion handling (2015, methodology): “A fast CM algorithm [29] is applied to evaluate the distance between the contour of the proposal and the contour of the exemplar template.”
DeepIM: Deep Iterative Matching for 6D Pose Estimation (2018, methodology): “In contrast, template-matching based methods are capable of handling textureless objects (Jurie and Dhome 2001; Liu et al. 2010; Gu and Ren 2010; Hinterstoisser et al. 2012a).”
Real-Time Seamless Single Shot 6D Object Pose Prediction (2017, methodology): “Other related methods include 3D model-based registration [17, 20, 35], Hausdorff matching [9], oriented Chamfer matching for edges [18] and 3D chamfer matching for aligning 3D curve-based models to images [26].”
Segmentation-Driven 6D Object Pose Estimation (2018, background): “Image edges then become the dominant information source [21, 26], and researchers have developed strategies based on different distances, such as the Hausdorff [15] and the Chamfer [25, 13] ones, to match the 3D model against the input image.”