Dense semantic labeling is significant in high-resolution remote sensing imagery research and it has been widely used in land-use analysis and environment protection. With the recent success of fully convolutional networks (FCN), various types of network architectures have largely improved performance. Among them, atrous spatial pyramid pooling (ASPP) and encoder-decoder are two successful ones. The former structure is able to extract multi-scale contextual information and multiple effective field-of-view, while the latter structure can recover the spatial information to obtain sharper object boundaries. In this study, we propose a more efficient fully convolutional network by combining the advantages from both structures. Our model utilizes the deep residual network (ResNet) followed by ASPP as the encoder and combines two scales of high-level features with corresponding low-level features as the decoder at the upsampling stage. We further develop a multi-scale loss function to enhance the learning procedure. In the postprocessing, a novel superpixel-based dense conditional random field is employed to refine the predictions. We evaluate the proposed method on the Potsdam and Vaihingen datasets and the experimental results demonstrate that our method performs better than other machine learning or deep learning methods. Compared with the state-of-the-art DeepLab_v3+ our model gains 0.4% and 0.6% improvements in overall accuracy on these two datasets respectively.

In this paper, we propose an articulated and generalized Gaussian kernel correlation (GKC)-based framework for human pose estimation. We first derive a unified GKC representation that generalizes the previous sum of Gaussians (SoG)-based methods for the similarity measure between a template and an observation both of which are represented by various SoG variants. Then, we develop an articulated GKC (AGKC) by integrating a kinematic skeleton in a multivariate SoG template that supports subject-specific shape modeling and articulated pose estimation for both the full body and the hands. We further propose a sequential (body/hand) pose tracking algorithm by incorporating three regularization terms in the AGKC function, including visibility, intersection penalty, and pose continuity. Our tracking algorithm is simple yet effective and computationally efficient. We evaluate our algorithm on two benchmark depth data sets. The experimental results are promising and competitive when compared with the state-of-the-art algorithms.

Efficient and accurate semantic segmentation is the key technique for automatic remote sensing image analysis. While there have been many segmentation methods based on traditional hand-craft feature extractors, it is still challenging to process high-resolution and large-scale remote sensing images. In this work, a novel patch-wise semantic segmentation method with a new training strategy based on fully convolutional networks is presented to segment common land resources. First, to handle the high-resolution image, the images are split as local patches and then a patch-wise network is built. Second, training data is preprocessed in several ways to meet the specific characteristics of remote sensing images, i.e., color imbalance, object rotation variations and lens distortion. Third, a multi-scale training strategy is developed to solve the severe scale variation problem. In addition, the impact of conditional random field (CRF) is studied to improve the precision. The proposed method was evaluated on a dataset collected from a capital city in West China with the Gaofen-2 satellite. The dataset contains ten common land resources (Grassland, Road, etc.). The experimental results show that the proposed algorithm achieves 54.96% in terms of mean intersection over union (MIoU) and outperforms other state-of-the-art methods in remote sensing image segmentation.

We present new multilayer joint gait-pose manifolds (multilayer JGPMs) for complex human gait motion modeling, where three latent variables are defined jointly in a low-dimensional manifold to represent a variety of body configurations. Specifically, the pose variable (along the pose manifold) denotes a specific stage in a walking cycle; the gait variable (along the gait manifold) represents different walking styles; and the linear scale variable characterizes the maximum stride in a walking cycle. We discuss two kinds of topological priors for coupling the pose and gait manifolds, i.e., cylindrical and toroidal, to examine their effectiveness and suitability for motion modeling. We resort to a topologically-constrained Gaussian process (GP) latent variable model to learn the multilayer JGPMs where two new techniques are introduced to facilitate model learning under limited training data. First is training data diversification that creates a set of simulated motion data with different strides. Second is the topology-aware local learning to speed up model learning by taking advantage of the local topological structure. The experimental results on the Carnegie Mellon University motion capture data demonstrate the advantages of our proposed multilayer models over several existing GP-based motion models in terms of the overall performance of human gait motion modeling.

We propose a new point set registration method, Global-Local Topology Preservation (GLTP), which can cope with complex non-rigid transformations including highly articulated deformation. The registration is formulated as a Maximum Likelihood (ML) estimation problem with two topologically complementary constraints. The first is the previous Coherent Point Drift (CPD) that encodes a global topology constraint by moving one point set coherently to align with the second set. The second, which is inspired by the idea of Local Linear Embedding (LLE), is introduced to handle highly articulated non-rigid deformation while sustaining the local structure. Without any pre-segmentation, the newly introduced LLE constraint is particularly useful and effective when there are multiple non-coherent and nonrigid local deformations (i.e, the CPD assumption may be violated). We have derived the EM algorithm for the ML optimization constrained with both CPD and LLE terms, leading to the new GLTP algorithm. Experimental results on 2D and 3D examples show its accuracy and robustness in the presence of outliers and noise, especially in the case of highly-articulated non-rigid transformation.

Objective . Magnetic resonance imaging (MRI) has been widely used for the analysis and diagnosis of brain diseases. Accurate and automatic brain tumor segmentation is of paramount importance for radiation treatment. However, low tissue contrast in tumor regions makes it a challenging task. Approach . We propose a novel segmentation network named Category Guided Attention U-Net (CGA U-Net). In this model, we design a Supervised Attention Module (SAM) based on the attention mechanism, which can capture more accurate and stable long-range dependency in feature maps without introducing much computational cost. Moreover, we propose an intra-class update approach to reconstruct feature maps by aggregating pixels of the same category. Main results . Experimental results on the BraTS 2019 datasets show that the proposed method outperformers the state-of-the-art algorithms in both segmentation performance and computational complexity. Significance . The CGA U-Net can effectively capture the global semantic information in the MRI image by using the SAM module, while significantly reducing the computational cost. Code is available at https://github.com/delugewalker/CGA-U-Net .