Search Results - "Ying, Xianghua"
-
1
Deep Unsupervised Domain Adaptation with Time Series Sensor Data: A Survey
Published in Sensors (Basel, Switzerland) (23-07-2022)“…Sensors are devices that output signals for sensing physical phenomena and are widely used in all aspects of our social production activities. The continuous…”
Get full text
Journal Article -
2
Geometric Interpretations of the Relation between the Image of the Absolute Conic and Sphere Images
Published in IEEE transactions on pattern analysis and machine intelligence (01-12-2006)“…A spherical object has been introduced into camera calibration for several years through utilizing the properties of an image conic, which is the projection of…”
Get full text
Journal Article -
3
Vanishing point detection using cascaded 1D Hough Transform from single images
Published in Pattern recognition letters (2012)“…► We used 1D histogram to detect vanishing points. ► We proposed new constraints for vanishing points in “Manhattan world”. ► Vanishing point detection in…”
Get full text
Journal Article -
4
Catadioptric camera calibration using geometric invariants
Published in IEEE transactions on pattern analysis and machine intelligence (01-10-2004)“…Central catadioptric cameras are imaging devices that use mirrors to enhance the field of view while preserving a single effective viewpoint. In this paper, we…”
Get full text
Journal Article -
5
Self-Calibration of Catadioptric Camera with Two Planar Mirrors from Silhouettes
Published in IEEE transactions on pattern analysis and machine intelligence (01-05-2013)“…If an object is interreflected between two planar mirrors, we may take an image containing both the object and its multiple reflections, i.e., simultaneously…”
Get full text
Journal Article -
6
Identical Projective Geometric Properties of Central Catadioptric Line Images and Sphere Images with Applications to Calibration
Published in International journal of computer vision (01-06-2008)“…Central catadioptric cameras are imaging devices that use mirrors to enhance the field of view while preserving a single effective viewpoint. Lines and spheres…”
Get full text
Journal Article -
7
A Fast Algorithm for Multidimensional Ellipsoid-Specific Fitting by Minimizing a New Defined Vector Norm of Residuals Using Semidefinite Programming
Published in IEEE transactions on pattern analysis and machine intelligence (01-09-2012)“…A quadratic surface in n-dimensional space is defined as the locus of zeros of a quadratic polynomial. The quadratic polynomial may be compactly written in…”
Get full text
Journal Article -
8
Camera Calibration from Periodic Motion of a Pedestrian
Published in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2016)“…Camera calibration directly from image sequences of a pedestrian without using any calibration object is a really challenging task and should be well solved in…”
Get full text
Conference Proceeding -
9
Radial distortion correction from a single image of a planar calibration pattern using convex optimization
Published in 2014 IEEE International Conference on Image Processing (ICIP) (01-10-2014)“…In Hartley-Kang's paper [7], they directly treated a planar calibration pattern as an image to construct an image pair together with a radial distorted image…”
Get full text
Conference Proceeding -
10
Radial lens distortion correction using cascaded one-parameter division model
Published in 2015 IEEE International Conference on Image Processing (ICIP) (01-09-2015)“…Radial lens distortion is the most significant lens distortion in current cameras, and many models are proposed to describe it. Fitzgibbon presented the…”
Get full text
Conference Proceeding -
11
Ellipse-specific fitting by relaxing the 3L constraints with semidefinite programming
Published in 2015 IEEE International Conference on Image Processing (ICIP) (01-09-2015)“…This paper presents a new efficient method to increase the accuracy and the robustness of ellipse fitting, by utilizing the 3L algorithm and semidefinite…”
Get full text
Conference Proceeding -
12
FPSMix: data augmentation strategy for point cloud classification
Published in Frontiers of Computer Science (01-02-2025)“…Data augmentation is a widely used regularization strategy in deep neural networks to mitigate overfitting and enhance generalization. In the context of point…”
Get full text
Journal Article -
13
The Perspective-3-Point Problem When Using a Planar Mirror
Published in 2014 22nd International Conference on Pattern Recognition (01-08-2014)“…The Perspective-3-Point problem (P3P) is a classical and fundamental problem in computer vision. All possible solution sets for the P3P problem are from 1 to 4…”
Get full text
Conference Proceeding -
14
Canonicalized central absolute moment for edge-based color constancy
Published in 2013 IEEE International Conference on Image Processing (01-09-2013)“…In the recent paper by Weijer et al. [9], the authors proposed the Grey-Edge hypothesis, which assumes that the average edge difference in the scene is…”
Get full text
Conference Proceeding -
15
Rectifying self-training with neighborhood consistency and proximity for source-free domain adaptation
Published in Neurocomputing (Amsterdam) (14-11-2024)“…Source-free domain adaptation (SFDA) seeks to transfer knowledge from the source domain to the target domain by leveraging only unlabeled target data and…”
Get full text
Journal Article -
16
Geometric properties of multiple reflections in catadioptric camera with two planar mirrors
Published in 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (01-06-2010)“…A catadioptric system consisting of a pinhole camera and two planar mirrors is deeply investigated in this paper. The two mirrors combine to form a corner and…”
Get full text
Conference Proceeding -
17
Direct least square fitting of ellipsoids
Published in Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012) (01-11-2012)“…Least square fitting of quadratic surfaces is a fundamental problem in pattern recognition, computer vision, graphics, and medical imaging analysis. This paper…”
Get full text
Conference Proceeding -
18
Exploiting Temporal Correlations for 3D Human Pose Estimation
Published in IEEE transactions on multimedia (2024)“…Exploiting the rich temporal information in human pose sequences to facilitate 3D pose estimation has garnered particular attention. While various learning…”
Get full text
Journal Article -
19
An Efficient Method for the Detection of Projected Concentric Circles
Published in 2007 IEEE International Conference on Image Processing (01-09-2007)“…Concentric circles are often used as calibration features since they possess good geometric properties. This paper presents an efficient method for the…”
Get full text
Conference Proceeding -
20
Unsupervised Domain Adaptation for Semantic Segmentation of Urban Street Scenes Reflected by Convex Mirrors
Published in IEEE transactions on intelligent transportation systems (01-12-2022)“…Reflective convex mirrors are often used on street corners or as passenger-side mirrors on cars to obtain scene information by reflecting blind spots in the…”
Get full text
Journal Article