Yundong Wu

Perspective-SIFT: An efficient tool for low-altitude remote sensing image registration

This paper presents an automated image registration approach that is robust to perspective distortions. State-of-the-art method affine-SIFT uses affine transform to simulate various viewpoints to increase the robustness of registration. However, affine transformation does not follow the process by which real-world images are formed. To solve this problem, we propose a perspective scale invariant feature transform (PSIFT) that uses homographic transformation to simulate perspective distortion. As for ASIFT, PSIFT is based on the scale invariant feature transform (SIFT) and has a two-resolution scheme, namely a low-resolution phase and a high-resolution phase. The low-resolution phase of PSIFT simulates several image views following a perspective transformation by varying two camera axis orientation parameters. Given those simulated images, SIFT is then used to extract features and find matches among them. In the high-resolution phase, the perspective transformations which lead the largest number of matches in the low-resolution stage are selected to generate SIFT features on the original images. Experimental results obtained on three categories of low-altitude remote sensing images and Morel-Yus dataset show that PSIFT outperforms significantly the state-of-the-art ASIFT, SIFT, Random Ferns, Harris-Affine, MSER and Hessian Affine, especially when images suffer severe perspective distortion.

Spectral---spatial co-clustering of hyperspectral image data based on bipartite graph

The high dimensionality of hyperspectral images are usually coupled with limited data available, which degenerates the performances of clustering techniques based only on pixel spectral. To improve the performances of clustering, incorporation of spectral and spatial is needed. As an attempt in this direction, in this paper, we propose an unsupervised co-clustering framework to address both the pixel spectral and spatial constraints, in which the relationship among pixels is formulated using an undirected bipartite graph. The optimal partitions are obtained by spectral clustering on the bipartite graph. Experiments on four hyperspectral data sets are performed to evaluate the effectiveness of the proposed framework. Results also show our method achieves similar or better performance when compared to the other clustering methods.

Novel Graph Cuts Method for Multi-Frame Super-Resolution

In this letter, we propose a new graph cuts multi-frame super resolution method. The method is carried out in 3 steps. First, we project each high-resolution pixel p onto the low-resolution images and select low-resolution pixels which fall within the zone of influence of p. Second, we weigh the contribution of the low-resolution pixels via a soft switching function and add them to construct a virtual low resolution pixel. The high resolution image is then recovered after minimizing a Maximum a posteriori Markov Random Field (MAP-MRF) energy function. This is done by approximating our energy function to make it graph representable and minimize it with a graph cuts α-expansion algorithm. Experimental results show that our approach outperforms state-of-the-art methods.

Spectral-spatial classification of hyperspectral imagery based on Random Forests

The high dimensionality of hyperspectral images are usually coupled with limited reference data available, which degenerates the performances of supervised classification techniques such as random forests (RF). The commonly used pixel-wise classification lacks information about spatial structures of the image. In order to improve the performances of classification, incorporation of spectral and spatial is needed. This paper proposes a novel scheme for accurate spectral-spatial classification of hyperspectral image. It is based on random forests, followed by majority voting within the superpixels obtained by oversegmentation through a graph-based technique. The scheme combines the result of a pixel-wise RF classification and the segmentation map obtained by oversegmentation. Our experimental results on two hyperspectral images show that the proposed framework combining spectral information with spatial context can greatly improve the final result with respect to pixel-wise classification with Random Forests.

A perspective invariant image matching algorithm

To solve the problem of affine transform and discrete sampling in ASIFT(Affine scale invariant feature transform),the PSIFT(Perspective scale invariant feature transform),which is based on particle swarm optimization,is proposed in this paper.The proposed algorithm uses a virtual camera and homographic transform to simulate perspective distortion among multi-view images.Therefore,particle swarm optimization is employed to determine the appropriate homography,which is decomposed into three rotation matrices.Experimental results obtained on three categories of low-altitude remote sensing images show that the proposed method outperforms significantly the state-of-the-art ASIFT,SIFT,Harris-affine and MSER,especially when images suffer severe perspective distortion.

A Robust Transform Estimator Based on Residual Analysis and Its Application on UAV Aerial Images

Estimating the transformation between two images from the same scene is a fundamental step for image registration, image stitching and 3D reconstruction. State-of-the-art methods are mainly based on sorted residual for generating hypotheses. This scheme has acquired encouraging results in many remote sensing applications. Unfortunately, mainstream residual based methods may fail in estimating the transform between Unmanned Aerial Vehicle (UAV) low altitude remote sensing images, due to the fact that UAV images always have repetitive patterns and severe viewpoint changes, which produce lower inlier rate and higher pseudo outlier rate than other tasks. We performed extensive experiments and found the main reason is that these methods compute feature pair similarity within a fixed window, making them sensitive to the size of residual window. To solve this problem, three schemes that based on the distribution of residuals are proposed, which are called Relational Window (RW), Sliding Window (SW), Reverse Residual Order (RRO), respectively. Specially, RW employs a relaxation residual window size to evaluate the highest similarity within a relaxation model length. SW fixes the number of overlap models while varying the length of window size. RRO takes the permutation of residual values into consideration to measure similarity, not only including the number of overlap structures, but also giving penalty to reverse number within the overlap structures. Experimental results conducted on our own built UAV high resolution remote sensing images show that the proposed three strategies all outperform traditional methods in the presence of severe perspective distortion due to viewpoint change.

Cover patches: A general feature extraction strategy for spoofing detection

Face anti‐spoofing has attracted many attentions in security applications, such as mobile payment and entrance guard. Until now, face anti‐spoofing technique is still a challenging task. Mainstream image‐based spoofing algorithms usually use global motion or texture information to distinguish whether an input face is live or fake. However, the performance of these methods are sensitive in light changes, or images acquired from different sensors. The main reason is that spoofed face image always has slight different texture in local areas, such as landmark or salient region of face. To this end, this paper proposes a novel multi‐patches feature extraction strategy to detect spoofing. First, a set of patches with specific combination scheme is selected to cover the face image. Second, features such as hand‐crafted Gray Level Co‐occurrence Matrix (GLCM), Local Binary Patterns (LBP), or deep features are extracted from these patches. Third, all features are combined as the global descriptor of the face image, then fed into an SVM classifier to verify the anti‐spoofing detection. Experimental results show that the proposed strategy can effectively enhance the performance, concerning with the accuracy of spoofed face detection in four widely used anti‐spoofing databases.

Face Alignment Based on Incremental Learning for Bayonet Surveillance

This paper proposed an improved Local Binary Features (LBF) [1] algorithm for bayonet surveillance system. Since LBF is based on shape-regression strategy, which is prone to over-fitting after multi-stage regression, the training model cannot be directly applied to other scenarios. To this end, we employed new data into existing models at the final stage of regression. As a consequent, newly imported data can be embedded to the model. The experimental results conducted on bayonet surveillance videos showed that the proposed method outperforms LBF, ERT and SDM, concerning with mean errors of the regression results.

AN ADAPTIVE FUZZY RULE-BASED COLOR IMAGE SEGMENTATION ALGORITHM

In this paper, we proposed an adaptive fuzzy rule-based color image segmentation algorithm. By using look-up table for designing a FIS (Fuzzy Inference System) to compute similarity percentage of the neighboring pixels and region feature histogram information, then we can use fast-merge for achieving a new color image segmentation algorithm. The experimental results show that our algorithm can produce good results compared to some existing algorithm.