Menglong Yang

The Reliability of Travel Time Forecasting

Travel time is a fundamental measure in transportation, and accurate travel time forecasting is crucial in intelligent transportation systems (ITSs). Currently, many techniques have been applied to travel time forecasting; however, the reliability of the prediction has not been studied in these approaches. In this paper, we propose an approach using the generalized autoregressive conditional heteroscedasticity (GARCH) model to study the volatility of travel time and supply the information about reliability for travel time forecasting. Three examples on real urban vehicular traffic data show the whole modeling process. In the experiments, we utilize the conditional predicted standard deviation (PSD) to express the reliability of travel time forecasting and screen out the sample points that are thought to be reliable forecasting. The results show that the root-mean-square error (RMSE), mean absolute error (MAE), and mean absolute percent error (MAPE) are all decreasing with an increase in the demand of the reliability. It proves that the model well depicts the reliability of travel time forecasting and that the proposed approach is feasible.

A robust face and ear based multimodal biometric system using sparse representation

If fusion rules cannot adapt to the changes of environment and individual users, multimodal systems may perform worse than unimodal systems when one or more modalities encounter data degeneration. This paper develops a robust face and ear based multimodal biometric system using Sparse Representation (SR), which integrates the face and ear at feature level, and can effectively adjust the fusion rule based on reliability difference between the modalities. We first propose a novel index called Sparse Coding Error Ratio (SCER) to measure the reliability difference between face and ear query samples. Then, SCER is utilized to develop an adaptive feature weighting scheme for dynamically reducing the negative effect of the less reliable modality. In multimodal classification phase, SR-based classification techniques are employed, i.e., Sparse Representation based Classification (SRC) and Robust Sparse Coding (RSC). Finally, we derive a category of SR-based multimodal recognition methods, including Multimodal SRC with feature Weighting (MSRCW) and Multimodal RSC with feature Weighting (MRSCW). Experimental results demonstrate that: (a) MSRCW and MRSCW perform significantly better than the unimodal recognition using either face or ear alone, as well as the known multimodal methods; (b) The effectiveness of adaptive feature weighting is verified. MSRCW and MRSCW are very robust to the image degeneration occurring to one of the modalities. Even when face (ear) query sample suffers from 100% random pixel corruption, they can still get the performance close to the ear (face) unimodal recognition; (c) By integrating the advantages of adaptive feature weighting and sparsity-constrained regression, MRSCW seems excellent in tackling the face and ear based multimodal recognition problem.

Few-view image reconstruction combining total variation and a high-order norm

This work presents a novel computed tomography reconstruction method for few‐view problem based on a compound method. To overcome the disadvantages of total variation (TV) minimization method, we use a high‐order norm coupled within TV and the numerical scheme for our method is given. We use the root mean square error as a referee. The numerical experiments demonstrate that our method achieves better performance than existing reconstruction methods, including filtered back projection, expectation maximization, and TV with projection on convex sets.

Robust Head Pose Estimation Using a 3D Morphable Model

Head pose estimation from single 2D images has been considered as an important and challenging research task in computer vision. This paper presents a novel head pose estimation method which utilizes the shape model of the Basel face model and five fiducial points in faces. It adjusts shape deformation according to Laplace distribution to afford the shape variation across different persons. A new matching method based on PSO (particle swarm optimization) algorithm is applied both to reduce the time cost of shape reconstruction and to achieve higher accuracy than traditional optimization methods. In order to objectively evaluate accuracy, we proposed a new way to compute the pose estimation errors. Experiments on the BFM-synthetic database, the BU-3DFE database, the CUbiC FacePix database, the CMU PIE face database, and the CAS-PEAL-R1 database show that the proposed method is robust, accurate, and computationally efficient.

A homography transform based higher-order MRF model for stereo matching

Stereo matching is one of the most important and fundamental topics in computer vision. It is usually solved by minimizing an energy function, which includes a data term and a smoothness term. The data term consists of the matching cost, and the smoothness term encodes the prior assumption that the surfaces are piecewise smooth. In contrast to the traditional methods, in which the smoothness term is modeled by the pairwise interactions, the smoothness term is modeled with a higher-order model in this paper. With the prior assumption that a tiny piece of a smooth surface is approximately planar, a higher-order potential function based on the homography transformations is presented. Then the energy function defined on a factor graph is proposed, in which the coefficients of the factors depend on the color information of the input images so that the discontinuous edges are preserved. The belief propagation (BP) algorithm is adopted to minimize the energy function, and the experimental results tested on the Middlebury data set show the potential of the proposed method.

Video synchronization based on events alignment

This paper presents a method of synchronizing two video sequences. The changes of kinematic status of feature points are considered as events. The basic idea of this paper is to temporally align these events observed in the two cameras by using an algorithm to score each candidate event correspondence, such that each false correspondence with a lower score could be discarded. Then the recovered event correspondences are obtained and they can be used to coarsely estimate synchronization parameters via the Hough transform. Finally refine these parameters by solving an optimization problem in order to recover synchronization to sub-frame accuracy. The method is evaluated quantitatively using synthetic sequences and demonstrated qualitatively on several real sequences. Experiment results show that the method is applicable to multiple features case, single feature case, different frame rates case and even the case of single feature with the two cameras relative motion.

Real-Time 3D Road Scene Based on Virtual-Real Fusion Method

Road monitoring plays a vital role in emergency disposal, traffic accident liability determination, traffic trend analyzes, and other fields. This paper designs a real-time virtual-real fusion framework for multiview surveillance of large-scale scene, in which 2D panorama, satellite texture, and 3D model are merged. The system is implemented with the following contributions. First, a novel automatic mosaic algorithm for multiview overlapped images is proposed. Feature points between adjacent cameras are detected via comotion statistics map. In addition, transformation model is obtained using random sample consensus algorithm. Second, multiview images are morphed to a same overhead viewpoint. Finally, 2D panoramic road image and 3D scene model are combined based on high-precision ground control points. The proposed framework has been successfully applied to a large road intersection. With the virtual-real fusion approach, observers can freely monitor and ramble in the large-scale 3-D road scene.

Online Multiple Instance Joint Model for Visual Tracking

Although numerous online learning strategies have been proposed to handle the appearance variation in visual tracking, the existing methods just perform well in certain cases since they lack effective appearance learning mechanism. In this paper, a joint model tracker (JMT) is presented, which consists of a generative model based on Multiple Subspaces and a discriminative model based on improved Multiple Instance Boosting (MIBoosting). The generative model utilizes a series of local constructed subspaces to update the Multiple Subspaces model and considers the energy dissipation of dimension reduction in updating step. The discriminative model adopts the Gaussian Mixture Model (GMM) to estimate the posterior probability of the likelihood function. These two parts supervise each other to update in multiple instance way which helps our tracker recover from drift. Extensive experiments on various databases validate the effectiveness of our proposed method over other state-of-the-art trackers.

Stereo matching based on classification of materials

Stereo matching is one of the most important and fundamental topics in computer vision. Encouraging self-similar pixels to be assigned to the same label has been proved to be effective for stereo. A typical way of taking advantage of self-similarity is performing a color segmentation on the image and motivating the pixels within each segment to share an identical label. However, some cases cannot be handled by image segmentation, such as the pixels in disconnected regions. This paper proposes a stereo method based on the assumption, that a 3D scene is a collection of a few smooth surfaces and a few classes of reflective materials, such that the 3D points belonging to an identical material are likely to lie on a small number of surfaces and the 3D points lying on a single surface belong to a few classes of reflective materials. Each material is expected to have specific albedo properties. This paper presents two methods for classifying the albedo properties depending on whether the illumination environment is known, without recovering the albedo parameters. The proposed model is formulated as an energy function incorporating some new priors, that is optimized via fusion move algorithm.

Classification by nearness in complementary subspaces

This study introduces a classifier founded on k-nearest neighbours in the complementary subspaces (NCS). The global space, spanned by all training samples, can be decomposed into the direct sum of two subspaces in terms of one class: the projection vectors of this class into one subspace are nonzero, and that into another subspace are zero. A query sample is projected into the two subspaces for each class, respectively. In each subspace, the distance from the projection vector to the mean of its k-nearest neighbours can be calculated, and the final classification rules are designed in terms of the two distances calculated in the two complementary subspaces, respectively. Allowing for the geometric meaning of Gram determinant and kernel trick, the classifier is naturally implemented in the kernel space. The experimental results on 1 synthetic, 13 IDA binary class, and five UCI multi-class data sets show that NCS compares favourably to the comparing classifiers, which is founded on the k-nearest neighbours or the nearest subspace, on almost all the data sets. The classifier can straightforwardly solve multi-classification problems, and the performance is promising.