移动视觉测量中基于空间交会的匹配方法

移动视觉测量中大量非编码点粘贴在被测物表面。由于图像点在不同站位图像中形状相似,因此无法提供足够多的信息来对其进行分类识别,匹配不同图像间的非编码点是移动视觉测量中的一项重要任务。大量研究证明,极线匹配方法是实现图像点匹配的有效方法。然而移动视觉测量的相机是未经过标定的,在利用极线匹配方法时,图像畸变会使基本矩阵求解精度较低,从而导致大量误匹配情况出现。为了解决该问题,提出一种基于空间交会的非编码点匹配方法。该方法通过不同图像间编码点的自动匹配,结合平差优化算法初步获取各站位的内外参数。然后利用这些参数将二维图像点重投影成对应的三维空间直线,在空间中利用直线间的交会关系确定图像匹配点。大量实验证明,该方法可以比极线匹配方法寻找更多的匹配点,更适合用于移动视觉测量。     

基于局部保持的遥感场景零样本分类算法

目标域遥感图像特征分布的变化,导致遥感场景零样本分类性能下降,针对该问题,提出一种基于局部保持的遥感场景零样本分类算法。首先,为减少冗余信息,采用解析字典学习方法,将源域中的场景图像特征和类别语义词向量嵌入到同一稀疏编码空间,并实现两者稀疏系数的强制对齐,以建立图像特征与词向量之间的关系;然后,通过保留图像特征空间中场景图像间的局部近邻关系,增强场景图像对应稀疏系数的鉴别性,以有助于对稀疏系数进行聚类分析;最后,为适应目标域图像特征分布变化,采用k-means算法对目标域场景图像的稀疏系数进行聚类,并以初始中心的类别标签作为对应的聚类簇中场景的类别标签。实验分别采用GoogLeNet和VGGNet图像特征,以数据集UCM作为源域遥感场景集,对目标域场景集RSSCN7进行零样本分类,获得了最高50.67%和53.29%的总体分类准确度,比现有算法各提升了8.06%和9.70%。实验结果表明:该算法能够适应目标域遥感场景图像特征分布的变化,显著提升遥感场景零样本分类效果,具有一定的优越性。     

基于稀疏编码和卷积神经网络的地貌图像分类

提出了一种基于稀疏编码和卷积神经网络的地貌场景图像分类算法;利用非下采样Contourlet变换对训练样本进行多尺度分解;在训练样本中选择图像,利用稀疏编码学习局部特征,对特征向量进行排序;选择灰度平均梯度较大的特征向量对卷积神经网络卷积核进行初始化。结果表明:所提算法可以获得比传统底层视觉特征更好的分类结果,有效避免了网络训练陷入局部最优的问题,提高了自然场景下无人机着陆地貌的分类准确率。     

基于网格编码量化的超光谱图像压缩

提出了一个基于小波网格编码量化的超光谱图像压缩方法。谱间和空间冗余处理构成了超光谱图像压缩算法的主要内容,该算法使用一个谱间差分预测步骤来去除谱间冗余,而后对预测残差图像进行小波变换并利用均匀阈值网格编码量化(trellis-coded quantization)方法来量化各小波子带,最后使用自适应算术编码对量化码字进行熵编码。为使编码器能为所有子带获取率-失真意义上最优的量化阈值,设计了一个基于子带统计特性和网格编码量化器率-失真特性的比特分配算法。在实验中,该算法表现出优良的压缩性能,对于实验的超光谱图像,该方法在压缩比为32时可得到37．1dB的峰值信噪比,这表明本算法能有效压缩超光谱图像,适于超光谱图像压缩应用。     

基于邻域分割的空谱联合稀疏表示高光谱图像分类技术研究

传统的高光谱遥感影像分类算法侧重于光谱信息的应用。随着高光谱遥感影像的空间分辨率的增加,高光谱影像中相同类别的地物在空间分布上呈现聚类特性,将空间特性有效地应用于高光谱遥感影像分类算法对分类精度的提升非常关键。但是,高光谱影像的高分辨率提供空间聚类特性的同时,在不同地物边缘处表现出的差异性更加明显,若不对空间邻域像素进行甄选,直接将邻域光谱信息引入,设计空谱联合稀疏表示进行图像分割,则分类误差较大,收敛速度大大降低。将光谱角引入空谱联合稀疏表示图像分类理论中,提出了一种基于邻域分割的空谱联合稀疏表示分类算法。该算法利用光谱角计算相邻像素的空间相似度,剥离相似度较低的邻域像素,将相似度高的邻域像素定义为同类地物,引入空谱联合稀疏表示模型中,采用子联合空间追踪算子和联合正交匹配追踪算子对其优化求解,以最小重构误差为准则进行分类。选取AVIRIS及ROSIS典型光谱影像数据进行实验仿真,从中可以看出,随着光谱角分割阈值的提高,复杂的高光谱影像分类精度和平滑区域的高光谱影像分类精度均逐步提高,表明邻域分割在空谱联合稀疏表示分类中的必要性。     

基于方向金字塔框架变换的遥感图像融合算法

为了综合利用多光谱遥感图像与全色遥感图像之间的互补信息,提出了一种方向金字塔框架变换(SPFT),并基于此变换提出了一种遥感图像融合算法。具体融合过程是将多光谱图像的每个波段分别与高分辨力全色图像进行融合,首先将高分辨力全色图像与多光谱图像的待融合波段进行直方图匹配,然后对该波段图像以及直方图匹配后的高分辨力全色图像分别进行方向金字塔框架变换分解,融合过程就是对两图像方向金字塔框架变换分解后的系数进行组合,最后对组合后的系数进行方向金字塔框架逆变换即可得到该波段图像与高分辨力全色图像的融合图像。实验结果表明该算法在性能上优于基于亮度-色调-饱和度(1HS)的彩色空间变换以及基于离散小波框架变换(DWFT)的遥感图像融合方法,尤其对源图像之间存在配准误差的情况。     

结合稀疏编码和空间约束的红外图像聚类分割研究

提出了结合稀疏编码和空间约束的红外图像聚类分割新算法, 在稀疏编码的基础上融合聚类算法, 扩展了传统的基于K-means聚类的图像分割方法. 结合稀疏编码的聚类分割算法能有效融合图像的局部信息, 便于利用像素之间的内在相关性, 但是对于分割会出现过分割和像素难以归类的问题.为此, 在字典的学习过程中, 将原子的聚类算法引入其中, 有助于缩减字典中原子所属类别的数目, 防止出现过分割; 考虑到像素及其邻域像素具有类别属性一致性的特点, 引入了空间类别属性约束信息, 并给出了一种交替优化算法. 联合学习字典、稀疏系数、聚类中心和隶属度, 将稀疏编码系数同原子对聚类中心的隶属程度相结合, 构造像素归属度来判断像素所属的类别. 实验结果表明, 该方法能够有效提高红外图像重要区域的分割效果, 具有较好的鲁棒性. 关键词： 图像分割 稀疏编码 聚类 空间约束     

基于稀疏表示分类和近红外光谱的烟叶自动分级研究

以近红外光谱技术和深度学习算法为依托,提出了一种基于稀疏表示分类算法的烟叶分级方法。该方法首先将所有训练样本通过稀疏编码建立稀疏表示数据字典,并对所有测试样本在该字典下通过稀疏编码进行稀疏表示,然后计算每个测试样本在数据字典上的投影,将具有最小残差的等级作为测试样本的级别。本文算法与线性判别方法与粒子群支持向量机算法进行了比较和分析,实验结果表明本文所提出的稀疏表示分类算法不仅能够获得更高的分类正确率,同时具有更高的计算效率。本文所提出的方法能够对烟叶的不同等级进行准确识别,为烟叶收购中的质量等级评价提供了一种新技术。     

基于非冗余轮廓波的图像质量可伸缩编码算法

提出一种用非冗余轮廓波的中低比特率图像质量可伸缩编码算法。该算法采用双正交小波分解和方向滤波器组(DFB)实现图像的非冗余稀疏表示, 不但具有轮廓波对图像中线状奇异性边缘和纹理细节的稀疏表示特点, 而且克服了轮廓波变换系数4/3冗余的缺点。算法中对图像非冗余轮廓波系数各子带系数分布进行统计分析, 通过对变换系数的重新组合, 构造了有利于图像编码的空间方向树结构, 并统计验证了其零树特性, 采用分级树集合分裂和阈值量化达到图像质量可伸缩的嵌入式编码。实验结果表明,其解码算法在中低比特率压缩情况下, 压缩后重构图像的感知质量明显优于小波域SPIHT,JPEG2000编码标准, 峰值信噪比PSNR值与JPEG2000相当, 而图像纹理和边缘细节的视觉效果优于JPEG2000和小波域SPIHT算法。     

高光谱图像的分布式近无损压缩

星载高光谱图像的有效压缩已经成为高光谱遥感领域亟待解决的难题。分布式信源编码具有较低的编码复杂度与良好的抗误码性,在高光谱图像压缩领域具有广阔的应用前景。提出了一种基于多元陪集码的高光谱图像分布式近无损压缩算法。根据多元陪集码的Slepian-Wolf无损编码的压缩过程,提出了面向高光谱图像分布式近无损压缩的最优量化方案,使得高光谱图像在给定目标码率条件下的失真达到最小,在此基础上对量化值进行Slepian-Wolf无损编码,从而实现了高光谱图像的分布式近无损压缩。实验结果表明,与典型的传统算法相比,该算法取得了较好的近无损压缩性能和较低的编码复杂度。     

Spatially regularized and locality-constrained linear coding for human action recognition

To reduce quantization error, preserve the manifold of local features, distinguish the ambiguous features, and model the spatial configuration of features for Bag-of-Features (BoF) model-based human action recognition, a novel feature coding method called spatially regularized and locality-constrained linear coding (SLLC) is proposed. The spatial regularization and locality constraint are involved in the feature coding phase to model the spatial configuration of features and preserve their nonlinear manifold. The action recognition experimental results on benchmark datasets show that SLLC achieves better performance than the state-of-the-art feature coding methods such as soft vector quantization, sparse coding, and locality-constrained linear coding.     

Fast aircraft detection using cascaded discriminative model in photoelectric sensing system

Aircraft detection is a fundamental problem in computer vision. As a vision-based system, the photoelectric sensing system (in airport) needs to capture the aircrafts quickly and accurately by the optical camera. Although many existing detection models reach to favorable accuracy, they are time consuming in training and testing, which is not suitable for this system. In practice, as a core part of vision-based system, detection module always occupies a lot of time in image processing and target matching. To reduce the (detection) time cost without losing detection accuracy, we designed a cascade discriminative model which includes two stages: coarse pre-detection stage and fine detection stage. In the traditional object detection models, generally, an object feature template was employed to search for all positions and levels in image pyramid with sliding window fashion. However, in our detection model, only a small number of candidate regions were pre-detected to reduce the searching space at the first stage. At the second stage, an assembled method (which includes partitioned bag-of-words method and random forest) was adopted for accelerating the feature quantization and formation. Then, the possible regions including object were decided by a non-linear SVM classifier. We evaluated our model on two benchmark databases (Caltech 101 and PASCAL 2007) and our own database (images were obtained from the optical camera), and it yields high performance. Compared with other state-of-the-art methods, our model outperforms them not only in detection speed, but also in detection accuracy.     

SFCVQ and EZW coding method based on Karhunen-Loeve transformation and integer wavelet transformation

A new hyperspectral image compression method of spectral feature classification vector quantization (SFCVQ) and embedded zero-tree of wavelet (EZW) based on Karhunen-Loeve transformation (KLT) and integer wavelet transformation is represented. In comparison with the other methods, this method not only keeps the characteristics of high compression ratio and easy real-time transmission, but also has the advantage of high computation speed. After lifting based integer wavelet and SFCVQ coding are introduced, a system of nearly lossless compression of hyperspectral images is designed. KLT is used to remove the correlation of spectral redundancy as one-dimensional (1D) linear transform, and SFCVQ coding is applied to enhance compression ratio. The two-dimensional (2D) integer wavelet transformation is adopted for the decorrelation of 2D spatial redundancy. EZW coding method is applied to compress data in wavelet domain. Experimental results show that in comparison with the method of wavelet SFCVQ (WSFCVQ),the method of improved BiBlock zero tree coding (IBBZTC) and the method of feature spectral vector quantization (FSVQ), the peak signal-to-noise ratio (PSNR) of this method can enhance over 9 dB, and the total compression performance is improved greatly.     

Palmprint recognition method based on score level fusion

Different palmprint recognition methods have different advantages. The texture- and feature-based palmprint recognition methods can well exploit the minutiae of the palmprint but are not very robust to the possible variation such as the rotation and shift of the palm. The representation-based palmprint recognition method can well take advantage of the holistic information but seems not to be able to fully exploit the minutiae of the palmprint. In this paper, we propose to fuse the competitive coding method and two-phase test sample sparse representation (TPTSR) method for palmprint recognition. As one of representation-based methods, TPTSR method takes the whole palmprint image as the input and determines the contribution of the training samples of each class in representing the test sample. TPTSR also uses the contribution to calculate the similarities between the test sample and every class. The competitive coding method is a feature-based method and is highly complementary with TPTSR. We use a weighted fusion scheme to combine the matching scores generated from TPTSR and the competitive coding method. The experimental results show that the proposed method can obtain a very high classification accuracy and outperforms both TPTSR and the competitive coding method.     

An infrared image super-resolution reconstruction method based on compressive sensing

Limited by the properties of infrared detector and camera lens, infrared images are often detail missing and indistinct in vision. The spatial resolution needs to be improved to satisfy the requirements of practical application. Based on compressive sensing (CS) theory, this thesis presents a single image super-resolution reconstruction (SRR) method. With synthetically adopting image degradation model, difference operation-based sparse transformation method and orthogonal matching pursuit (OMP) algorithm, the image SRR problem is transformed into a sparse signal reconstruction issue in CS theory. In our work, the sparse transformation matrix is obtained through difference operation to image, and, the measurement matrix is achieved analytically from the imaging principle of infrared camera. Therefore, the time consumption can be decreased compared with the redundant dictionary obtained by sample training such as K-SVD. The experimental results show that our method can achieve favorable performance and good stability with low algorithm complexity.     

融合自适应稀疏表示和相关系数的高光谱伪装分类方法

目前比较成熟的高光谱成像手段有卫星遥感和航空成像技术,这两种成像方式侦察时间大致相同,入射光方向基本一致,因而地物的光谱曲线比较固定;在陆基条件下,地物的光谱曲线受成像环境的影响凸显,因此应该对适用于陆基条件下的高光谱图像分类方法进行研究。在陆基高光谱图像中,对每个地物进行类型以及种类的判别有利于后续对目标的识别和处理,不同于传统遥感图像分类,陆基条件下的高光谱图像目标分类训练样本不仅较难获得,并且在陆基条件下的高光谱图像中,训练样本之间的相关性随着目标类型、探测器参数以及成像环境等因素时刻发生变化。基于稀疏性表示的分类方法已经被广泛应用于处理图像问题以及各种机器视觉问题。对于陆基高光谱图像来说,基于固定范数约束的稀疏编码策略无法适应陆基条件下高光谱成像多变的环境,而自适应稀疏表示可以根据样本相关性自适应的调节范数约束,相关系数可以提高图像中的破坏因素（阴影、噪声点等）的识别精度。通过引入正则化参数,融合了自适应稀疏表示和相关系数,提出了一种新的高光谱图像分类方法。为了验证所提方法的有效性,分别在绿色植被背景和荒漠背景中设置伪装物,通过不同的分类方法对图像进行分类,实验结果表明,不管是分类精度还是分类一致性,该方法都有明显的优势,可以应用于陆基条件下的高光谱图像分类,为目标分类提供了理论基础。     

基于GoogLeNet和空间谱变换的高光谱图像超分辨率方法

为了提高高光谱图像的空间分辨率,提出了一种基于GoogLeNet和空间谱变换的高光谱图像超分辨率(SR)方法.设计出遥感图像的光谱SR框架,对图像中不同反射光谱进行提取;采用GoogLeNet的稀疏编码对粗像素光谱进行放大,并投影到高分辨率字典上,将潜在SR表示进行反转,以获得超分辨光谱;为了提高图像重构的保真度,利用...     

Structural similarity based single image super-resolution with nonlocal regularization

Recently, sparse coding based image super-resolution has attracted increasing interests. This paper proposes an improved image super-resolution method, by incorporating structural similarity (SSIM) index and nonlocal regularization into the framework of image super-resolution via sparse coding. Firstly, an algorithm of combining SSIM based sparse coding and K-SVD is proposed to train the high resolution (HR) and low resolution (LR) dictionary pairs. And then, the sparse representations of observed LR image are sought to reconstruct the HR image with the trained LR and HR dictionary pairs by exploiting nonlocal self-similarities. Experimental results demonstrate the effectiveness of the proposed method, both in its visual effects and in quantitative terms.