Search

To meet the requirements of the high-precision operation of intelligent excavator, a dual power source coordinated control strategy of hydraulic-electric hybrid swing system is proposed. In the process of rotation, the servo motor is used as the main drive to control the speed and position of the swing platform. The hydraulic motor and accumulator auxiliary servo motor drive the swing platform to make it run to the desired position accurately and smoothly at the desired speed. Firstly, this paper established the mathematical model of the proposed system and designed the global synovial control algorithm. Then the stability of the proposed system was proved by the Lyapunov method. Then, the multi-body dynamics co-simulation platforms of the original excavator negative flow swing system and the proposed system were established. The operational characteristics of two kinds of swing systems were studied. The results show that compared with the original negative flow swing system, the proposed system can effectively suppress the anti-swing phenomenon, and the operation is more accurate and stable. Compared with PID, the global sliding mode control has higher accuracy and better robustness, and the control accuracy is as high as 99.71%.

Learning-based stereo matching has recently achieved promising results, yet still suffers difficulties in establishing reliable matches in weakly matchable regions that are textureless, non-Lambertian, or occluded. In this paper, we address this challenge by proposing a stereo matching network that considers pixel-wise matchability. Specifically, the network jointly regresses disparity and matchability maps from 3D probability volume through expectation and entropy operations. Next, a learned attenuation is applied as the robust loss function to alleviate the influence of weakly matchable pixels in the training. Finally, a matchability-aware disparity refinement is introduced to improve the depth inference in weakly matchable regions. The proposed deep stereo matchability (DSM) framework can improve the matching result or accelerate the computation while still guaranteeing the quality. Moreover, the DSM framework is portable to many recent stereo networks. Extensive experiments are conducted on Scene Flow and KITTI stereo datasets to demonstrate the effectiveness of the proposed framework over the state-of-the-art learning-based stereo methods., Accepted to ICPR 2020

Establishing correspondences between two images requires both local and global spatial context. Given putative correspondences of feature points in two views, in this paper, we propose Order-Aware Network, which infers the probabilities of correspondences being inliers and regresses the relative pose encoded by the essential matrix. Specifically, this proposed network is built hierarchically and comprises three novel operations. First, to capture the local context of sparse correspondences, the network clusters unordered input correspondences by learning a soft assignment matrix. These clusters are in a canonical order and invariant to input permutations. Next, the clusters are spatially correlated to form the global context of correspondences. After that, the context-encoded clusters are recovered back to the original size through a proposed upsampling operator. We intensively experiment on both outdoor and indoor datasets. The accuracy of the two-view geometry and correspondences are significantly improved over the state-of-the-arts. Code will be available at https://github.com/zjhthu/OANet.git., Comment: Accepted to ICCV 2019, and Winner solution to both tracks of CVPR IMW 2019 Challenge. Code will be available soon at https://github.com/zjhthu/OANet.git

We present a convolutional network architecture for direct feature learning on mesh surfaces through their atlases of texture maps. The texture map encodes the parameterization from 3D to 2D domain, rendering not only RGB values but also rasterized geometric features if necessary. Since the parameterization of texture map is not pre-determined, and depends on the surface topologies, we therefore introduce a novel cross-atlas convolution to recover the original mesh geodesic neighborhood, so as to achieve the invariance property to arbitrary parameterization. The proposed module is integrated into classification and segmentation architectures, which takes the input texture map of a mesh, and infers the output predictions. Our method not only shows competitive performances on classification and segmentation public benchmarks, but also paves the way for the broad mesh surfaces learning.

Accurate relative pose is one of the key components in visual odometry (VO) and simultaneous localization and mapping (SLAM). Recently, the self-supervised learning framework that jointly optimizes the relative pose and target image depth has attracted the attention of the community. Previous works rely on the photometric error generated from depths and poses between adjacent frames, which contains large systematic error under realistic scenes due to reflective surfaces and occlusions. In this paper, we bridge the gap between geometric loss and photometric loss by introducing the matching loss constrained by epipolar geometry in a self-supervised framework. Evaluated on the KITTI dataset, our method outperforms the state-of-the-art unsupervised ego-motion estimation methods by a large margin. The code and data are available at https://github.com/hlzz/DeepMatchVO., Accepted by ICRA 2019

Global Structure-from-Motion (SfM) techniques have demonstrated superior efficiency and accuracy than the conventional incremental approach in many recent studies. This work proposes a divide-and-conquer framework to solve very large global SfM at the scale of millions of images. Specifically, we first divide all images into multiple partitions that preserve strong data association for well-posed and parallel local motion averaging. Then, we solve a global motion averaging that determines cameras at partition boundaries and a similarity transformation per partition to register all cameras in a single coordinate frame. Finally, local and global motion averaging are iterated until convergence. Since local camera poses are fixed during the global motion average, we can avoid caching the whole reconstruction in memory at once. This distributed framework significantly enhances the efficiency and robustness of large-scale motion averaging.

The manifold surface reconstruction in multi-view stereo often fails in retaining thin structures due to incomplete and noisy reconstructed point clouds. In this paper, we address this problem by leveraging spatial curves. The curve representation in nature is advantageous in modeling thin and elongated structures, implying topology and connectivity information of the underlying geometry, which exactly compensates the weakness of scattered point clouds. We present a novel surface reconstruction method using both curves and point clouds. First, we propose a 3D curve reconstruction algorithm based on the initialize-optimize-extend strategy. Then, tetrahedra are constructed from points and curves, where the volumes of thin structures are robustly preserved by the Curve-conformed Delaunay Refinement. Finally, the mesh surface is extracted from tetrahedra by a graph optimization. The method has been intensively evaluated on both synthetic and real-world datasets, showing significant improvements over state-of-the-art methods.

Multi-view stereo (MVS) depends on the pre-determined camera geometry, often from structure from motion (SfM) or simultaneous localization and mapping (SLAM). However, cameras may not be locally optimal for dense stereo matching, especially when it comes from the large scale SfM or the SLAM with multiple sensor fusion. In this paper, we propose a local camera refinement approach for accurate dense reconstruction. Firstly, we refines the relative geometry of independent camera pair using a tailored bundle adjustment. The refinement is also extended to a multi-view version for general MVS reconstructions. Then, the non-rigid dense alignment is formulated as an inverse-distortion problem to transfer point clouds from each local coordinate system to a global coordinate system. The proposed framework has been intensively validated in both SfM and SLAM based dense reconstructions. Results on different datasets show that our method can significantly improve the dense reconstruction quality.

The power of modern image matching approaches is still fundamentally limited by the abrupt scale changes in images. In this paper, we propose a scale-invariant image matching approach to tackling the very large scale variation of views. Drawing inspiration from the scale space theory, we start with encoding the image’s scale space into a compact multi-scale representation. Then, rather than trying to find the exact feature matches all in one step, we propose a progressive two-stage approach. First, we determine the related scale levels in scale space, enclosing the inlier feature correspondences, based on an optimal and exhaustive matching in a limited scale space. Second, we produce both the image similarity measurement and feature correspondences simultaneously after restricting matching between the related scale levels in a robust way. The matching performance has been intensively evaluated on vision tasks including image retrieval, feature matching and Structurefrom- Motion (SfM). The successful integration of the challenging fusion of high aerial and low ground-level views with significant scale differences manifests the superiority of the proposed approach.

To break down the geometry assumptions of traditional motion models (e.g., homography, affine), warping-based motion model recently becomes very popular and is adopted in many latest applications (e.g., image stitching, video stabilization). With high degrees of freedom, the accuracy of model heavily relies on data-terms (keypoint correspondences). In some low-texture environments (e.g., indoor) where keypoint feature is insufficient or unreliable, the warping model is often erroneously estimated. In this paper we propose a simple and effective approach by considering both keypoint and line segment correspondences as data-term. Line segment is a prominent feature in artificial environments and it can supply sufficient geometrical and structural information of scenes, which not only helps guild to a correct warp in low-texture condition, but also prevents the undesired distortion induced by warping. The combination aims to complement each other and benefit for a wider range of scenes. Our method is general and can be ported to many existing applications. Experiments demonstrate that using dual-feature yields more robust and accurate result especially for those low-texture images.

In this paper, we propose a structural segmentation algorithm to partition multi-view stereo reconstructed surfaces of large-scale urban environments into structural segments. Each segment corresponds to a structural component describable by a surface primitive of up to the second order. This segmentation is for use in subsequent urban object modeling, vectorization, and recognition. To overcome the high geometrical and topological noise levels in the 3D reconstructed urban surfaces, we formulate the structural segmentation as a higher-order Conditional Random Field (CRF) labeling problem. It not only incorporates classical lower-order 2D and 3D local cues, but also encodes contextual geometric regularities to disambiguate the noisy local cues. A general higher-order CRF is difficult to solve. We develop a bottom-up progressive approach through a patch-based surface representation, which iteratively evolves from the initial mesh triangles to the final segmentation. Each iteration alternates between performing a prior discovery step, which finds the contextual regularities of the patch-based representation, and an inference step that leverages the regularities as higher-order priors to construct a more stable and regular segmentation. The efficiency and robustness of the proposed method is extensively demonstrated on real reconstruction models, yielding significantly better performance than classical mesh segmentation methods.

In this paper, we propose an optimal decomposition approach to large-scale multi-view stereo from an initial sparse reconstruction. The success of the approach depends on the introduction of surface-segmentation-based camera clustering rather than sparse-point-based camera clustering, which suffers from the problems of non-uniform reconstruction coverage ratio and high redundancy. In details, we introduce three criteria for camera clustering and surface segmentation for reconstruction, and then we formulate these criteria into an energy minimization problem under constraints. To solve this problem, we propose a joint optimization in a hierarchical framework to obtain the final surface segments and corresponding optimal camera clusters. On each level of the hierarchical framework, the camera clustering problem is formulated as a parameter estimation problem of a probability model solved by a General Expectation-Maximization algorithm and the surface segmentation problem is formulated as a Markov Random Field model based on the probability estimated by the previous camera clustering process. The experiments on several Internet datasets and aerial photo datasets demonstrate that the proposed approach method generates more uniform and complete dense reconstruction with less redundancy, resulting in more efficient multi-view stereo algorithm.

We propose a novel method for recognizing irregular patterns in facades. An irregular pattern is an incomplete 2D grid, representing the placements of repetitive structural architectural objects (e.g., windows), which is capable of being generalized to a variety of facade structures. To effectively recognize such a pattern, we jointly model objects and object structures in a unified Marked Point Process framework, where the architectural objects are abstracted as sparsely populated geometric entities and the pairwise spatially interactions are modeled as elliptical repulsion fields. To optimize the proposed model, we introduce a structure-driven Monte Carlo Markov Chain (MCMC) sampler, by which the irregular pattern hypotheses are iteratively constructed in a bottom-up manner and verified in a top-down manner. The solution space is explored more efficiently for fast convergence. Extensive experiments have shown the efficiency and accuracy of our method of parsing a large category of facades.

Conventional hydraulic actuator is controlled by mechanically connected orifices valve. The controllability of this method is poor and the energy consumption is huge especially under the over-running condition. So a novel system configuration of the hydraulic excavator is presented to improve the problem mentioned above, in which boom cylinder, stick cylinder and swing motor are controlled with separate meter in and meter out technology, bucket cylinder and travel motors are controlled with conventional valves. Firstly, the paper provides a comprehensive review on the development of the separate meter in and meter out technology. Then the principles of load sensing system and SMISMO system applied on the excavator are illustrated though two diagram to show the difference of the two systems. And then a virtual prototype based on the real physical structures is established, which consists of the hydraulic excavator mechanical structure with multi-body dynamics and electro-hydraulic system. The model is verified by the statics and dynamics experiments. Then the dynamic, static performances as well as the energy consumption characteristics of the boom, arm and swing actuators are investigated under the condition of load sensing hydraulic system and the proposed system using the virtual prototype. The control strategy of the actuators is formulated according to their load condition and operation characteristics also based on the detailed analysis. After that, the physical prototype based on the proposed configuration system is established and its performance is tested. The experimental results show that the accuracy of the virtual prototype is validated; the proposed configuration system can significantly decreases the pressure losses through the valve and improve the energy efficiency of the machine; the pressure shocks within hydraulic actuators is decreased as well, thus the stationarity of the whole machine is improved accordingly.

Hydraulic switching techniques which have less throttling losses, good repeatability and can be controlled intelligently have been largely developed. The biggest challenge is the hydraulic fluctuation. It is generated in the process of opening and closing the valve. A two-stage digital flow valve operated by Pulse Width Modulation (PWM) signal is studied in this paper. The main stage is cartridge valve based on flow amplifying principle; the pilot stage is high-speed on/off valve. The fluctuation characteristic of the digital flow valve is investigated using theoretical derivation and simulation analysis. The results show that the outlet flow fluctuation is influenced by many parameters such as the frequency and duty ratio of PWM signal, the volume of control chamber, etc. It can be weakened through the proper design of these parameters. Although the fluctuation exists, the mean outlet flow can be proportionally controlled by adjustment of the duty ratio of the control signal.

Cartridge flow valves, widely applied in heavy machine and equipment, have the advantages of low leakage, large flow capacity, and simple structure. However, in the existence technologies, in order to reduce the influence of load variety on valve flow, a pressure differential compensator or a cartridge type flow sensor should be added to proportional throttle valve. This method reduces valve flow capacity and increases system throttling loss. In large flow occasion, flow only can be indirectly controlled by changing valve opening area for the limitation of the structure. So a low energy consumption, high controllable electro-hydraulic proportional valve which is structured by a hydraulic transistor (Valvistor) and a small displacement hydraulic pump driven by a servo motor is introduced. Based on the Valvistor valve flow amplification principle, main valve flow is controlled by pilot pump flow which is controlled by changing rotation speed without the influence of load variety. In the research, it's known from the analysis of the new principle valve steady flow characteristics that feedback throttle slot pre-opening will cause the decrease of the main valve flow as pressure drop increases. Soa method of pressure differential-pilot pump rotation speed compensation is put forward and it can obtain ideal flow characteristic. Then the dynamic mathematical model is established and the main valve stability criterion is derived. The influence of the valve parameters on main valve performance is analyzed and simulated. The results provide a new method for the large flow electro-hydraulic proportional control system.

Absolute value equation is equivalent to a non-differentiable NP-hard problem in its general form. In this paper, an improved harmony search is presented for solving NP-hard absolute value equation with unique solution and multiple solutions. Combining with mutation strategy in differential evolution algorithm, the pitch-adjusted operation in classical harmony search is replaced by difference operator, meanwhile, in order to maintain diversity of population, scaling factor F is generated by chaotic sequence. Numerical results show that the improved harmony search algorithm has strong ability of exploration, and can obtain as many solutions to the absolute value equation as possible.

Absolute value equation is an NP-hard problem in its general form. This paper focused on absolute value equation with 2n solutions. Firstly existent conditions of absolute value equation with 2n solutions was given, then we proposed an improved harmony search algorithm based on multiple population with clustering strategy. Numerical results show that our method has strong ability of exploration, and can obtain as many solutions to the absolute value equation as possible.

In this paper, we study the problem of recognizing man-made objects and present a novel affine-invariant feature, Low-rank SIFT, which exploits the regular appearance property in man-made objects. The proposed feature achieves full affine invariance without needing to simulate over affine parameter space. We rectify local patches by converting them to their low-rank forms to achieve skew invariance, and perform the way similar to conventional SIFT to resolve rotation, translation and scaling ambiguity. The main contributions lie in two-fold: our method seeks to leverage low-rank prior to estimate affine parameters for local patches directly and we propose a fast algorithm to compute such parameters by introducing the Low-rank Integral Map. Besides, we describe a pipeline of constructing a geotagged building database from the ground up. We demonstrate the effectiveness of our approach in the application to place recognition.

In this paper, we propose a real-time object tracking approach. It utilizes generalized part-based appearance model and structure-constrained motion model as auxiliary. The appearance of the target object is modeled by the proposed generalized part-based appearance model, which combines the appearance of different parts of the target object, adaptively updated by an efficient structure learning scheme based on the online Passive-Aggressive algorithm. By integrating the confidence scores of multiple parts, mutual compensation is realized, significantly enhances the robustness of our method against the structure deformation and partial occlusion during the tracking. In addition, we enhance the performance of our tracker by using a motion model. It employs a structure-constrained rule, that is, the change on the structure of the target object between consecutive frames is small. Experiments on public video sequences verify the superior performance of our algorithm.

Global bundle adjustment usually converges to a non-zero residual and produces sub-optimal camera poses for local areas, which leads to loss of details for high- resolution reconstruction. Instead of trying harder to optimize everything globally, we argue that we should live with the non-zero residual and adapt the camera poses to local areas. To this end, we propose a segment-based approach to readjust the camera poses locally and improve the reconstruction for fine geometry details. The key idea is to partition the globally optimized structure from motion points into well-conditioned segments for re-optimization, reconstruct their geometry individually, and fuse everything back into a consistent global model. This significantly reduces severe propagated errors and estimation biases caused by the initial global adjustment. The results on several datasets demonstrate that this approach can significantly improve the reconstruction accuracy, while maintaining the consistency of the 3D structure between segments.

We propose an adaptive sub gradient descent method to efficiently learn the parameters of CRF models for image parsing. To balance the learning efficiency and performance of the learned CRF models, the parameter learning is iteratively carried out by solving a convex optimization problem in each iteration, which integrates a proximal term to preserve the previously learned information and the large margin preference to distinguish bad labeling and the ground truth labeling. A solution of sub gradient descent updating form is derived for the convex optimization problem, with an adaptively determined updating step-size. Besides, to deal with partially labeled training data, we propose a new objective constraint modeling both the labeled and unlabeled parts in the partially labeled training data for the parameter learning of CRF models. The superior learning efficiency of the proposed method is verified by the experiment results on two public datasets. We also demonstrate the powerfulness of our method for handling partially labeled training data.

The binary split grammar is powerful to parse facade in a broad range of types, whose structure is characterized by repetitive patterns with different layouts. We notice that, as far as two labels are concerned, BSG parsing is equivalent to approximating a facade by a matrix with multiple rank-one patterns. Then, we propose an efficient algorithm to decompose an arbitrary matrix into a rank-one matrix and a residual matrix, whose magnitude is small in the sense of l0-norm. Next, we develop a block-wise partition method to parse a more general facade. Our method leverages on the recent breakthroughs in convex optimization that can effectively decompose a matrix into a low-rank and sparse matrix pair. The rank-one block-wise parsing not only leads to the detection of repetitive patterns, but also gives an accurate facade segmentation. Experiments on intensive facade data sets have demonstrated that our method outperforms the state-of-the-art techniques and benchmarks both in robustness and efficiency.

We present a novel method for translational symmetry detection, optimization, and symmetry object segmentation in facade images. Unlike most previous methods, our detection algorithm accumulates pixel-level correspondence in translation space. Thus it does not rely on feature point detection and handles patterns with low repetition counts. To improve the robustness with multiple interfering symmetries, we introduce an image-space global optimization, which resolves multiple per-pixel symmetry lattices. We then propose a learning-based method that generates refined segmentation of foreground symmetry objects of arbitrary shapes, with the aid of the per-pixel symmetry information. Our proposed method is accurate, robust and efficient as demonstrated by an extensive evaluation using a large facade image database.

In this paper, we present a method of detecting translation symmetries from a fronto-parallel image. The proposed method automatically detects unknown multiple repetitive patterns of arbitrary shapes, which are characterized by translation symmetries on a plane. The central idea of our approach is to take advantage of the interesting properties of translation symmetries in both image space and the space of transformation group. We first detect feature points in input image as sampling points. Then for each sampling point, we search for the most probable corresponding lattice structures in the image and transform spaces using scale-space similarity maps. Finally, using a MRF formulation, we optimally partition the graph of all sampling points associated with the estimated lattices into subgraphs of sampling points and lattices belonging to the same symmetry pattern. Our method is robust because of the joint analysis in image and transform spaces, and the MRF optimization. We demonstrate the robustness and effectiveness of our method on a large variety of images.

In this paper we propose a novel nonparametric image parsing method for the image parsing problem in certain environment. A novel and efficient nearest neighbor matching scheme, the ANN bilateral matching scheme, is proposed. Based on the proposed matching scheme, we first retrieve some partially similar images for each given test image from the training image database. The test image can be well explained by these retrieved images, with similar regions existing in the retrieved images for each region in the test image. Then, we match the test image to the retrieved training images with the ANN bilateral matching scheme, and parse the test image by integrating multiple cues in a markov random field. Experiment on three datasets shows our method achieved promising parsing accuracy and outperformed two state-of-the-art nonparametric image parsing methods.

In order to research into changes with time of dynamic characteristics, vibration response of gear driven system of wind turbine was analysed in time-domain. The method of lumped—parameter was adopted to found dynamic model of multi-degree of freedom system for the wind turbine gear driven system. Calculation method of model parameters was introduced. Meshing stiffness, damp coefficient and error excitation were calculated. The numerical simulation of the vibration system in time domain was carried out by the 4-steps Runge-Kutta method with MATLAB. Vibration responses of the system were obtained. It has guiding meaning for system optimization design.

A linear interpolation fuzzy controller with NN compensator is proposed for an electro-hydraulic position servo system. First, to overcome the conventional fuzzy controller’s disadvantage of lower precision caused by discretization, bilinear interpolation 2-D table lookup method is used to replace the exact lookup method. Then, to minimize the steady state error caused by force load, a neural network feed forward compensator is proposed. Finally, to imitate the practical system, co-simulation technique between AMESim and MATLAB/Simulink is adopted. The model of the valve controlled hydraulic cylinder system is constructed in AMESim, which can reflect the nonlinear characteristics of the system. And the controller model is established in Simulink. Lots of simulation experiments are carried out. And the simulating results indicate that with the proposed control scheme good dynamic and static control performance can be achieved. The steady state error caused by discretization can be avoided and that caused by force load can be minimized.

In the permanent magnet synchronous motor servo system, as the motor nonlinearity, strong coupling, parameters variability, and hydraulic systems nonlinear factors such as leaks, Coulomb friction and the uncertainty of the load force, output torque of the motor is interfered with the large random disturbances, and the system suffers from serious dynamic nonlinearity. Adaptive observer is adopted to carry the load torque adaptive control by the estimation error, improve the dynamic performance, and increase disturbance restraint performance. Using Lyapunov stability theory analyses convergence conditions and proves the system stability. The system simulation experiment shows that the control method has strong robustness on parameters variation and random disturbance.

We propose an approach that parses registered images captured at ground level into architectural units for large-scale city modeling. Each parsed unit has a regularized shape, which can be used for further modeling purposes. In our approach, we first parse the environment into buildings, the ground, and the sky using a joint 2D-3D segmentation method. Then, we partition buildings into individual facades. The partition problem is formulated as a dynamic programming optimization for a sequence of natural vertical separating lines. Each facade is regularized by a floor line and a roof line. The floor line is the intersection line of the vertical plane of buildings and the horizontal plane of the ground. The roof line links edge points of roof region. The parsed results provide a first geometric approximation to the city environment, and can be further analyzed if necessary. The approach is demonstrated and validated on several large-scale city datasets.

We present a semi-automatic technique for modeling trees and plants directly from images. Our image-based approach has the distinct advantage that the resulting model inherits the realistic shape and complexity of a real tree or plant. This is possible because the leaves of a tree or a plant all have the same generic shape, and the branches have a natural generative model of self-similarity like a fractal. We designed our modeling system to be interactive, automating the process of shape recovery while relying on the user to provide simple hints on segmentation. Segmentation is performed in both image and 3D spaces, allowing the user to easily visualize its effect immediately. Using the segmented image and 3D data, the geometry of each leaf is then automatically recovered from the multiple views by fitting a deformable leaf model. Our system also allows the user to easily reconstruct branches in a n similar manner. We show realistic reconstructions of a variety of trees and plants. The presentation is based on our work presented in [2,4,5,6], which is based on the quasi-dense structure from motion in [7,8,9,10]. The continuation of the work for other types of objects are also presented in [1,3].

We propose a simple but powerful multi-view semantic segmentation framework for images captured by a camera mounted on a car driving along streets. In our approach, a pair-wise Markov Random Field (MRF) is laid out across multiple views. Both 2D and 3D features are extracted at a super-pixel level to train classifiers for the unary data terms of MRF. For smoothness terms, our approach makes use of color differences in the same image to identify accurate segmentation boundaries, and dense pixel-to-pixel correspondences to enforce consistency across different views. To speed up training and to improve the recognition quality, our approach adaptively selects the most similar training data for each scene from the label pool. Furthermore, we also propose a powerful approach within the same framework to enable large-scale labeling in both the 3D space and 2D images. We demonstrate our approach on more than 10,000 images from Google Maps Street View.

In this paper, we propose a novel graph based clustering approach with satisfactory clustering performance and low computational cost. It consists of two main steps: tree fitting and partitioning. We first introduce a probabilistic method to fit a tree to a data graph under the sense of minimum entropy. Then, we propose a novel tree partitioning method under a normalized cut criterion, called normalized tree partitioning (NTP), in which a fast combinatorial algorithm is designed for exact bipartitioning. Moreover, we extend it to k-way tree partitioning by proposing an efficient best-first recursive bipartitioning scheme. Compared with spectral clustering, NTP produces the exact global optimal bipartition, introduces fewer approximations for k-way partitioning and can intrinsically produce superior performance. Compared with bottom-up aggregation methods, NTP adopts a global criterion and hence performs better. Last, experimental results on image segmentation demonstrate that our approach is more powerful compared with existing graph-based approaches.

This paper presents a robust algorithm to deblur two consecutively captured blurred photos from camera shaking. Previous dual motion deblurring algorithms succeeded in small and simple motion blur and are very sensitive to noise. We develop a robust feedback algorithm to perform iteratively kernel estimation and image deblurring. In kernel estimation, the stability and capability of the algorithm is greatly improved by incorporating a robust cost function and a set of kernel priors. The robust cost function serves to reject outliers and noise, while kernel priors, including sparseness and continuity, remove ambiguity and maintain kernel shape. In deblurring, we propose a novel and robust approach which takes two blurred images as input to infer the clear image. The deblurred image is then used as feedback to refine kernel estimation. Our method can successfully estimate large and complex motion blurs which cannot be handled by previous dual or single image motion deblurring algorithms. The results are shown to be significantly better than those of previous approaches.

A set of images of a Lambertian surface under varying lighting directions defines its shape up to a three-parameter generalized bas-relief (GBR) ambiguity. In this paper, we examine this ambiguity in the context of surfaces having an additive non-Lambertian reflectance component, and we show that the GBR ambiguity is resolved by any non-Lambertian reflectance function that is isotropic and spatially invariant. The key observation is that each point on a curved surface under directional illumination is a member of a family of points that are in isotropic or reciprocal configurations. We show that the GBR can be resolved in closed form by identifying members of these families in two or more images. Based on this idea, we present an algorithm for recovering full Euclidean geometry from a set of uncalibrated photometric stereo images, and we evaluate it empirically on a number of examples.

Aligning a pair of blurred and non-blurred images is a prerequisite for many image and video restoration and graphics applications. The traditional alignment methods such as direct and feature-based approaches cannot be used due to the presence of motion blur in one image of the pair. In this paper, we present an effective and accurate alignment approach for a blurred/non-blurred image pair. We exploit a statistical characteristic of the real blur kernel - the marginal distribution of kernel value is sparse. Using this sparseness prior, we can search the best alignment which produces the sparsest blur kernel. The search is carried out in scale space with a coarse-to-fine strategy for efficiency. Finally, we demonstrate the effectiveness of our algorithm for image deblurring, video restoration, and image matting.