Yuwei Wu

Vehicle Type Classification Using a Semisupervised Convolutional Neural Network

In this paper, we propose a vehicle type classification method using a semisupervised convolutional neural network from vehicle frontal-view images. In order to capture rich and discriminative information of vehicles, we introduce sparse Laplacian filter learning to obtain the filters of the network with large amounts of unlabeled data. Serving as the output layer of the network, the softmax classifier is trained by multitask learning with small amounts of labeled data. For a given vehicle image, the network can provide the probability of each type to which the vehicle belongs. Unlike traditional methods by using handcrafted visual features, our method is able to automatically learn good features for the classification task. The learned features are discriminative enough to work well in complex scenes. We build the challenging BIT-Vehicle dataset, including 9850 high-resolution vehicle frontal-view images. Experimental results on our own dataset and a public dataset demonstrate the effectiveness of the proposed method.

Metric Learning Based Structural Appearance Model for Robust Visual Tracking

Appearance modeling is a key issue for the success of a visual tracker. Sparse representation based appearance modeling has received an increasing amount of interest in recent years. However, most of existing work utilizes reconstruction errors to compute the observation likelihood under the generative framework, which may give poor performance, especially for significant appearance variations. In this paper, we advocate an approach to visual tracking that seeks an appropriate metric in the feature space of sparse codes and propose a metric learning based structural appearance model for more accurate matching of different appearances. This structural representation is acquired by performing multiscale max pooling on the weighted local sparse codes of image patches. An online multiple instance metric learning algorithm is proposed that learns a discriminative and adaptive metric, thereby better distinguishing the visual object of interest from the background. The multiple instance setting is able to alleviate the drift problem potentially caused by misaligned training examples. Tracking is then carried out within a Bayesian inference framework, in which the learned metric and the structure object representation are used to construct the observation model. Comprehensive experiments on challenging image sequences demonstrate qualitatively and quantitatively that the proposed algorithm outperforms the state-of-the-art methods.

Adaptive diffusion flow active contours for image segmentation

Gradient vector flow (GVF) active contour model shows good performance at concavity convergence and initialization insensitivity, yet it is susceptible to weak edges as well as deep and narrow concavity. This paper proposes a novel external force, called adaptive diffusion flow (ADF), with adaptive diffusion strategies according to the characteristics of an image region in the parametric active contour model framework for image segmentation. We exploit a harmonic hypersurface minimal functional to substitute smoothness energy term in GVF for alleviating the possible leakage. We make use of the p(x) harmonic maps, in which p(x) ranges from 1 to 2, such that the diffusion process of the flow field can be adjusted adaptively according to image characteristics. We also incorporate an infinity laplacian functional to ADF active contour model to drive the active contours onto deep and narrow concave regions of objects. The experimental results demonstrate that ADF active contour model possesses several good properties, including noise robustness, weak edge preserving and concavity convergence.

Segmentation of the left ventricle in cardiac cine MRI using a shape-constrained snake model

Segmentation of the left ventricle (LV) is a hot topic in cardiac magnetic resonance (MR) images analysis. In this paper, we present an automatic LV myocardial boundary segmentation method using the parametric active contour model (or snake model). By convolving the gradient map of an image, a fast external force named gradient vector convolution (GVC) is presented for the snake model. A circle-based energy is incorporated into the GVC snake model to extract the endocardium. With this prior constraint, the snake contour can conquer the unexpected local minimum stemming from artifacts and papillary muscle, etc. After the endocardium is detected, the original edge map around and within the endocardium is directly set to zero. This modified edge map is used to generate a new GVC force filed, which automatically pushes the snake contour directly to the epicardium by employing the endocardium result as initialization. Meanwhile, a novel shape-similarity based energy is proposed to prevent the snake contour from being strapped in faulty edges and to preserve weak boundaries. Both qualitative and quantitative evaluations on our dataset and the publicly available database (e.g. MICCAI 2009) demonstrate the good performance of our algorithm.

Robust Discriminative Tracking via Landmark-Based Label Propagation

The appearance of an object could be continuously changing during tracking, thereby being not independent identically distributed. A good discriminative tracker often needs a large number of training samples to fit the underlying data distribution, which is impractical for visual tracking. In this paper, we present a new discriminative tracker via landmark-based label propagation (LLP) that is nonparametric and makes no specific assumption about the sample distribution. With an undirected graph representation of samples, the LLP locally approximates the soft label of each sample by a linear combination of labels on its nearby landmarks. It is able to effectively propagate a limited amount of initial labels to a large amount of unlabeled samples. To this end, we introduce a local landmarks approximation method to compute the cross-similarity matrix between the whole data and landmarks. Moreover, a soft label prediction function incorporating the graph Laplacian regularizer is used to diffuse the known labels to all the unlabeled vertices in the graph, which explicitly considers the local geometrical structure of all samples. Tracking is then carried out within a Bayesian inference framework, where the soft label prediction value is used to construct the observation model. Both qualitative and quantitative evaluations on the benchmark data set containing 51 challenging image sequences demonstrate that the proposed algorithm outperforms the state-of-the-art methods.

Nonnegative Correlation Coding for Image Classification

Feature coding is one of the most important procedures in the bag-of-features model for image classification. In this paper, we propose a novel feature coding method called nonnegative correlation coding. In order to obtain a discriminative image representation, our method employs two correlations: the correlation between features and visual words, and the correlation between the obtained codes. The first correlation reflects the locality of codes, i.e., the visual words close to the local feature are activated more easily than the ones distant. The second correlation characterizes the similarity of codes, and it means that similar local features are likely to have similar codes. Both correlations are modeled under the nonnegative constraint. Based on the Nesterov’s gradient projection algorithm, we develop an effective numerical solver to optimize the nonnegative correlation coding problem with guaranteed quadratic convergence. Comprehensive experimental results on publicly available datasets demonstrate the effectiveness of our method.创新点本文提出了一种用于图像分类的编码方法,称为“非负关联编码”。为了获得有判别力的图像表示,非负关联编码利用了两种关系:一是待编码的局部特征与视觉单词之间的关系,它反映了编码过程的局部性,即局部特征倾向于利用距离它较近的视觉单词进行表达;二是编码之间的关系,它体现了编码过程的相似性,即相似的局部特征具有相似的编码。这两种关系都在非负约束的条件下建模。另外,本文基于NGP(Nesterov梯度投影)方法提出了一种用于求解非负关联编码的有效算法。公共数据集上的实验结果证明了方法的有效性。

Manifold Kernel Sparse Representation of Symmetric Positive-Definite Matrices and Its Applications

The symmetric positive-definite (SPD) matrix, as a connected Riemannian manifold, has become increasingly popular for encoding image information. Most existing sparse models are still primarily developed in the Euclidean space. They do not consider the non-linear geometrical structure of the data space, and thus are not directly applicable to the Riemannian manifold. In this paper, we propose a novel sparse representation method of SPD matrices in the data-dependent manifold kernel space. The graph Laplacian is incorporated into the kernel space to better reflect the underlying geometry of SPD matrices. Under the proposed framework, we design two different positive definite kernel functions that can be readily transformed to the corresponding manifold kernels. The sparse representation obtained has more discriminating power. Extensive experimental results demonstrate good performance of manifold kernel sparse codes in image classification, face recognition, and visual tracking.

A variational method for contour tracking via covariance matching

This paper presents a novel formulation for contour tracking. We model the second-order statistics of image regions and perform covariance matching under the variational level set framework. Specifically, covariance matrix is adopted as a visual object representation for partial differential equation (PDE) based contour tracking. Log-Euclidean calculus is used as a covariance distance metric instead of Euclidean distance which is unsuitable for measuring the similarities between covariance matrices, because the matrices typically lie on a non-Euclidean manifold. A novel image energy functional is formulated by minimizing the distance metric between the candidate object region and a given template, and maximizing the one between the background region and the template. The corresponding gradient flow is then derived according to a variational approach, enabling partial differential equations (PDEs) based contour tracking. Experiments on several challenging sequences prove the validity of the proposed method.

Learning online structural appearance model for robust object tracking

The main challenge of robust object tracking comes from the difficulty in designing an adaptive appearance model that is able to accommodate appearance variations. Existing tracking algorithms often perform self-updating of the appearance model with examples from recent tracking results to account for appearance changes. However, slight inaccuracy of tracking results can degrade the appearance model. In this paper, we propose a robust tracking method by evaluating an online structural appearance model based on local sparse coding and online metric learning. Our appearance model employs pooling of structural features over the local sparse codes of an object region to obtain a middle-level object representation. Tracking is then formulated by seeking for the most similar candidate within a Bayesian inference framework where the distance metric for similarity measurement is learned in an online manner to match the varying object appearance. Both qualitative and quantitative evaluations on various challenging image sequences demonstrate that the proposed algorithm outperforms the state-of-the-art methods.

Adaptive Diffusion Flow for Parametric Active Contours

This paper proposes a novel external force for active contours, called adaptive diffusion flow (ADF). We reconsider the generative mechanism of gradient vector flow (GVF) diffusion process from the perspective of image restoration, and exploit a harmonic hyper surface minimal function to substitute smoothness energy term of GVF for alleviating the possible leakage problem. Meanwhile, a ∞- laplacian functional is incorporated in the ADF framework to ensure that the vector flow diffuses mainly along normal direction in homogenous regions of an image. Experiments on synthetic and real images demonstrate the good properties of the ADF snake, including noise robustness, weak edge preserving, and concavity convergence.