Browsing by Author "Chen, Zen"

Now showing 1 - 8 of 8

3D robust reconstruction using a hand-held digital camera
(2008)
Chen, Zen
;
Wu, Chang-Hao
;
Chen, Wen-Chao
;
資訊工程學系
;
Department of Computer Science
Conventional vision-based reconstruction methods comprise three main steps: feature extraction and matching, estimation of camera matrices, and triangulation method for 3D point computation. Standard factorization algorithms provide an effective means for computing the 3D object shape and camera models simultaneously from the multiple views without going through the process of pairwise reconstructions. Since the numbers of features used in all views must be the same and sufficiently large in these methods, they are not applicable to the cases where not every feature point is visible in all views. On the other hand, the extracted features are often corrupted by image noise. Therefore, there is a need for a reconstruction algorithm that can handle missing feature points and image noise both in order to yield a robust result. We propose a method integrating a multi-view reconstruction and a least-squared-error estimation to produce a robust reconstruction result. Besides, the proposed method utilizes an auto-calibration scheme to convert the projective reconstruction to a Euclidean reconstruction. The method is tested on the synthetic and real data.
A NOVEL 3D DENSE RECONSTRUCTION WITH HIGH ACCURACY AND COMPLETENESS
(2013)
Chen, Zen
;
Chen, Wen-Chao
;
Sung, Ping-Yi
;
資訊工程學系
;
Department of Computer Science
This paper presents a planar patch based method for 3D dense reconstruction. The object surface is represented as a point cloud. For high reconstruction accuracy and completeness, our strategy is to fit the object surface by planar patches at different scales. Furthermore, we apply adaptive weights to defme the photo-consistency measures for view matching. To optimize the view matching, we adopt a derivative-free GLN-PSO stochastic optimization method. Finally, to improve the reconstruction quality we design a patch priority queue for ordering the seed patches for patch expansion. The experimental results indicate the current implementation results are generally superior or comparable in comparison with the top ranked reconstruction methods reported in the Middlebury MVS website.
A Performance Controllable Octree Construction Method
(2008)
Chen, Zen
;
Chou, Hong-Long
;
Chen, Wen-Chao
;
資訊工程學系
;
Department of Computer Science
The conventional octree construction method is implemented iteratively at consecutive subdivision levels. The resultant octree models at different subdivision levels contain quite different octant compositions, so the system performance, in terms of model accuracy, memory space and construction time, changes widely with the subdivision level number. Since the big system performance gap is not desirable for the practical application, new construction methods must have a finer control over the system performance. In the paper a new construction method is proposed using new types of octree octants. Interesting properties and computer simulations of the new method are presented. The performance comparison between the conventional method and the new method is made under the comparable XOR projection error condition. It is shown that under this condition the memory space and construction time required by the conventional method can be reduced significantly by the new method.
A quality controllable multi-view object reconstruction method for 3D imaging systems
(2010-07-01)
Chen, Wen-Chao
;
Chou, Hong-Long
;
Chen, Zen
;
資訊工程學系
;
Department of Computer Science
This paper addresses a novel multi-view visual hull mesh reconstruction for 3D imaging with a system quality control capability. There are numerous 3D imaging methods including multi-view stereo algorithms and various visual hull/octree reconstruction methods known as modeling from silhouettes. The octree based reconstruction methods are conceptually simple to implement, while encountering a conflict between model accuracy and memory size. Since the tree depth is discrete, the system performance measures (in terms of accuracy, memory size, and computation time) are generally varying rapidly with the pre-specified tree depth. This jumping system performance is not suitable for practical applications; a desirable 3D reconstruction method must have a finer control over the system performance. The proposed method aims at the visual quality control along with better management of memory size and computation time. Furthermore, dynamic object modeling is made possible by the new method. Also, progressive transmission of the reconstructed model from coarse to fine is provided. The reconstruction accuracy of the 3D model acquired is measured by the exclusive OR (XOR) projection error between the pairs of binary images: the reconstructed silhouettes and the true silhouettes in the multiple views. Interesting properties of the new method and experimental comparisons with other existing methods are reported. The performance comparisons are made under either a comparable silhouette inconsistency or a similar triangle number of the mesh model. It is shown that under either condition the new method requires less memory size and less computation time. (C) 2010 Published by Elsevier Inc.
A Zernike Moment Phase-Based Descriptor for Local Image Representation and Matching
(2010-01-01)
Chen, Zen
;
Sun, Shu-Kuo
;
資訊工程學系
;
Department of Computer Science
A local image descriptor robust to the common photometric transformations (blur, illumination, noise, and JPEG compression) and geometric transformations ( rotation, scaling, translation, and viewpoint) is crucial to many image understanding and computer vision applications. In this paper, the representation and matching power of region descriptors are to be evaluated. A common set of elliptical interest regions is used to evaluate the performance. The elliptical regions are further normalized to be circular with a fixed size. The normalized circular regions will become affine invariant up to a rotational ambiguity. Here, a new distinctive image descriptor to represent the normalized region is proposed, which primarily comprises the Zernike moment (ZM) phase information. An accurate and robust estimation of the rotation angle between a pair of normalized regions is then described and used to measure the similarity between two matching regions. The discriminative power of the new ZM phase descriptor is compared with five major existing region descriptors ( SIFT, GLOH, PCA-SIFT, complex moments, and steerable filters) based on the precision-recall criterion. The experimental results, involving more than 15 million region pairs, indicate the proposed ZM phase descriptor has, generally speaking, the best performance under the common photometric and geometric transformations. Both quantitative and qualitative analyses on the descriptor performances are given to account for the performance discrepancy. First, the key factor for its striking performance is due to the fact that the ZM phase has accurate estimation accuracy of the rotation angle between two matching regions. Second, the feature dimensionality and feature orthogonality also affect the descriptor performance. Third, the ZM phase is more robust under the nonuniform image intensity fluctuation. Finally, a time complexity analysis is provided.
New efficient octree construction from multiple object silhouettes with construction quality control
(2006)
Chen, Zen
;
Chou, Hong-Long
;
資訊工程學系
;
Department of Computer Science
In this paper, we propose an octree construction method with a new subdivision strategy which is governed by the degree of overlapping between each generated octant and the object. The specification of a maximum level of subdivision required in the conventional method is not needed. We introduce "grey-grey" and "grey-black" nodes based on a construction quality measure. The construction quality is measured by the maximum 2D projection error of the projected octant image with respective to the object silhouette in all views. Only those octants which are "grey-grey" nodes will be subdivided. Furthermore, we present a fast computation of the 2D projection and a new intersection test to reduce the computer processing time. Computer simulations are conducted to show that the new method outperforms the conventional method in terms of memory space and computation time subject to the same level of construction quality.
Robust Logo Recognition for Mobile Phone Applications
(2011-03-01)
Sun, Shu-Kuo
;
Chen, Zen
;
資訊工程學系
;
Department of Computer Science
In the paper, a new recognition method for logos imaged by mobile phone cameras is presented which can be incorporated with mobile phone services for use in enterprise identification, corporate website access, traffic sign reading, security check, content awareness, and the related applications. The main challenge in applying the logo recognition for mobile phone applications is the inevitable photometric and geometric transformations encountered when a handheld mobile phone camera operates at a varying viewpoint under different lighting environments. A new distinctive logo feature vector and an associated similarity measure are proposed for logo recognition using the Zernike moment (ZM) phase information. The discriminative power of the new logo recognition method is compared with three major existing methods. The experimental results indicate that the proposed ZM phase method has the best performance in terms of the precision and recall criterion under the above inevitable imaging variations. An analysis on the performances of the four recognition methods is given to account for the performance discrepancy.
Stochastic Optimization Based 3D Dense Reconstruction from Multiple Views with High Accuracy and Completeness
(2015-01-01)
Chen, Wen-Chao
;
Chen, Zen
;
Sung, Ping-Yi
;
資訊工程學系
;
Department of Computer Science
This paper presents a stochastic optimization based 3D dense reconstruction from multiple views. Accuracy and completeness are two major measure indices for performance evaluation of various multi-view stereo (MVS) algorithms. First, the reconstruction accuracy is highly related to the stereo mismatches over the multiple views. Stereo mismatches occur in the image regions involving the lack of texture, depth discontinuity, or repeated texture patterns. Second, an insufficient number of views or occlusions between objects also lead to the difficulty in matching so that the reconstruction completeness degrades. In pursuit of high accuracy and completeness we present the appropriate techniques to solve the above problems in the reconstruction task. To deal with the various stereo mismatch problems we propose to apply adaptive matching functions and allow partial matching. We shall model the object to be reconstructed by a set of 3D oriented planar patches covering the visible object surface. The adopted multi-view reconstruction is formulated as a patch expansion process under a tree hierarchy. In order to find the optimal patches via multi-view stereo matching we shall employ a PSO (Particle Swarm Optimization) method for the sake of implementation simplicity and avoidance of possible local traps as found in the derivative based optimization methods. The success in the PSO method relies on imposing proper constraints on ranges of the patch parameters including the patch depth and patch normal vector which are involved in the PSO objective function (i.e., the stereo matching function). Furthermore, we use a varying patch size to obtain the reliable patches in the areas containing less texture, repeated texture pattern, or depth discontinuity. To secure a high reconstruction quality we advocate a patch priority queue to select the best patch during the patch expansion. All of the above mentioned techniques are also effective in the situations when the number of views is sparse or the camera baseline width is wide. The proposed method is tested on synthetic and real image data sets. The experimental results indicate that the proposed method is superior or comparable to the top ranked reconstruction methods reported in the public Middlebury MVS evaluation website.