The infrared and visible image fusion algorithm based on target separation and sparse representation

Although the fused image of the infrared and visible image takes advantage of their complementary, the artifact of infrared targets and vague edges seriously interfere the fusion effect. To solve these problems, a fusion method based on infrared target extraction and sparse representation is proposed. Firstly, the infrared target is detected and separated from the background rely on the regional statistical properties. Secondly, DENCLUE (the kernel density estimation clustering method) is used to classify the source images into the target region and the background region, and the infrared target region is accurately located in the infrared image. Then the background regions of the source images are trained by Kernel Singular Value Decomposition (KSVD) dictionary to get their sparse representation, the details information is retained and the background noise is suppressed. Finally, fusion rules are built to select the fusion coefficients of two regions and coefficients are reconstructed to get the fused image. The fused image based on the proposed method not only contains a clear outline of the infrared target, but also has rich detail information.     

基于特征级融合的多波段舰船目标识别方法

针对复杂情况下海上舰船目标单波段特征识别能力不足的问题,研究可见光、中波红外和长波红外三波段特征图像融合技术,重点解决图像融合方法中存在的算法耗时和融合策略选择的问题,提出了一种新的基于区域协方差矩阵的多波段特征级融合方法,针对可见光图像和红外图像分别设计11维和5维特征向量,协方差矩阵可以将多个特征进行融合,既保证了不同目标之间的区别性,同时又减小计算量。该方法首先利用显著性检测,快速定位图像中的目标区域,然后,针对不同波段图像设计的特征向量定义协方差阵的距离计算公式并进行匹配,通过对图像的一次遍历操作获得积分图像,在协方差计算时达到快速计算的目的,最后利用k-阶最近邻算法对多种舰船目标进行分类识别。利用实拍的3 400余张三波段舰船目标图像作为测试数据。实验主要分为两部分,首先对比单波段和三波段融合识别的识别率,验证所提出的融合方法具有更广的应用范围;然后,在计算效率上对比多种传统的像素级方法,验证采用的特征级融合在计算时间上的优势。实验结果表明,该方法可达到95.1%的识别率,单帧计算耗时约为0.5 s,在实时性和检测率方面都有明显提高。     

基于图像局部区域梯度特征描述的红外人体识别算法

提出了一种新的红外图像中人体目标识别方案并进行了算法实现。通过直方图聚类分析对红外图像进行分割,根据二值化图像团块的特点,确定图像中的候选目标图像区域。将候选目标图像按比例划分为多个区域,使用梯度位置朝向直方图(GLOH,Gradient location-orientation histogram)对候选目标图像进行描述。与其它红外图像中人体识别算法相比,不需要多种特征提取算法组合进行分步骤识别,仅使用单个SVM分类器即可达到满意的识别率,避免了分类器的级联,算法简单有效。     

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     

联合稀疏表示在水下目标分类中的应用

水下目标分类识别的性能受所选特征的限制,多特征往往可以获得更加稳定的结果,针对这一问题,提出了一种基于联合稀疏表示模型的水下目标分类识别方法。首先对水下目标回波信号提取3种具有信息互补性与关联性的特征:中心矩特征、小波包能量谱特征、梅尔频率倒谱系数特征,然后应用加速近端梯度法对联合稀疏表示模型进行优化,求解得到最优联合稀疏系数,最后根据最小误差准则确定目标类别。在消声水池开展模拟实验,对6类目标进行分类识别,结果表明:与传统算法相比,提出的算法具有更高识别准确率,并且其执行效率较传统算法有很大提升。      

Infrared small target tracking based on sample constrained particle filtering and sparse representation

Infrared search and track technology for small target plays an important role in infrared warning and guidance. In view of the tacking randomness and uncertainty caused by background clutter and noise interference, a robust tracking method for infrared small target based on sample constrained particle filtering and sparse representation is proposed in this paper. Firstly, to distinguish the normal region and interference region in target sub-blocks, we introduce a binary support vector, and combine it with the target sparse representation model, after which a particle filtering observation model based on sparse reconstruction error differences between sample targets is developed. Secondly, we utilize saliency extraction to obtain the high frequency area in infrared image, and make it as a priori knowledge of the transition probability model to limit the particle filtering sampling process. Lastly, the tracking result is brought about via target state estimation and the Bayesian posteriori probability calculation. Theoretical analyses and experimental results show that our method can enhance the state estimation ability of stochastic particles, improve the sparse representation adaptabilities for infrared small targets, and optimize the tracking accuracy for infrared small moving targets.     

基于兴趣区域掩码卷积神经网络的红外-可见光图像融合与目标识别算法研究

建立权重独立的双通道残差卷积神经网络,对可见光与红外频段下的目标图像进行特征提取,生成多尺度复合频段特征图组.基于像点间的欧式距离计算双频段特征图显著性,根据目标在不同成像频段下的特征贡献值进行自适应融合.通过热源能量池化核与视觉注意力机制,分别生成目标在双频段下的兴趣区域逻辑掩码并叠加在融合图像上,凸显目标特征并抑制...     

稀疏降噪自编码结合高斯过程的近红外光谱药品鉴别方法

提出一种稀疏降噪自编码结合高斯过程的近红外光谱药品鉴别方法。首先对近红外光谱数据进行小波变换以消除基线漂移,然后用稀疏降噪自编码(SDAE)网络提取光谱特征并降维表示,最后采用高斯过程(GP)进行二分类,其中GP选用光谱混合(SM)核函数作为协方差函数,记此分类网络为wSDAG_SM。自编码网络具有很强的模型表示能力,高斯过程分类器在处理小样本数据时具有优势。wSDAG_SM网络通过稀疏降噪自编码学习得到维数更低但更有价值的特征来表示输入数据,同时将具有很好表达力的光谱混合核作为高斯过程的协方差函数,有利于更准确的光谱数据分类。以琥乙红霉素及其他药品的近红外光谱为实验数据,将该方法与经过墨西哥帽小波变换的BP神经网络(wBP)、支持向量机(wSVM), SDAE结合Logistic二分类(wSDAL)、SDAE结合采用平方指数(SE)协方差核的GP二分类(wSDAG_SE),以及未采用小波变换的SDAG_SM网络等方法进行对比。实验结果表明,对光谱数据进行墨西哥帽小波变换预处理能有效提升SDAG_SM网络的分类准确率和稳定性。wSDAG_SM方法无论从分类准确率还是分类结果稳定性方面,都优于其他分类器。     

多维特征点空间的红外弱小目标检测方法

将人工智能算法引入目标检测,空间红外弱小目标的检测也可归为模糊检测的二分类问题。依据空中红外弱小目标的探测模型,建立了信号电压比光谱模型,仿真分析表明电压比变化趋势与目标的速度、姿态和两机态势有关,可用以检测目标。采用动态特征构建理论,构建了红外弱小目标的双色比特征空间,基于该特征空间,优化最小二乘分类算法,用于从光谱信号层级检测目标。该方法不仅缩小了样本数据量,而且防止了高斯核函数参数选择引起的“过拟合”现象,既保证了分类精度,又使分类速率提高近1倍,为人工智能算法用于红外弱小目标检测提供了参考依据。     

倒谱参数稀疏分解下的汉语音谎言检测

为了提高汉语语音的谎言检测准确率,提出了一种对信号倒谱参数进行稀疏分解的方法。首先,采用小波包滤波器组对语音信号进行多频带划分,求得子频带对数能量并进行离散余弦变换以提取小波包频带倒谱系数,结合梅尔频率谱系数得到倒谱参数;其次,依据K-奇异值分解方法分别利用说谎和非说谎两种状态下的语音倒谱参数集训练得到过完备混合字典,在此字典上根据正交匹配追踪算法对参数集进行稀疏编码提取稀疏特征;最终进行多种分类模型下的识别实验·实验结果表明,稀疏分解方法相比传统参数降维方法具有更好的优化性能,本文推荐的稀疏谱特征最佳识别率达到78.34%,优于其他特征参数,显著提高了谎言检测识别准确率。      

Joint detection and tracking of size-varying infrared targets based on block-wise sparse decomposition

The high variability of target size makes small target detection in Infrared Search and Track (IRST) a challenging task. A joint detection and tracking method based on block-wise sparse decomposition is proposed to address this problem. For detection, the infrared image is divided into overlapped blocks, and each block is weighted on the local image complexity and target existence probabilities. Target-background decomposition is solved by block-wise inexact augmented Lagrange multipliers. For tracking, label multi-Bernoulli (LMB) tracker tracks multiple targets taking the result of single-frame detection as input, and provides corresponding target existence probabilities for detection. Unlike fixed-size methods, the proposed method can accommodate size-varying targets, due to no special assumption for the size and shape of small targets. Because of exact decomposition, classical target measurements are extended and additional direction information is provided to improve tracking performance. The experimental results show that the proposed method can effectively suppress background clutters, detect and track size-varying targets in infrared images.     

Deceptive Chinese speech detection based on sparse decomposition of cepstral feature

In order to improve the performance of deception detection based on Chinese speech signals, a method of sparse decomposition on spectral feature is proposed. First, the wavelet packet transform is applied to divide the speech signal into multiple sub-bands. Band cepstral features of wavelet packets are obtained by operating the discrete cosine transform on loga?rithmic energy of each sub-band. The cepstral feature is generated by combing Mel Frequency Cepstral Coefficient and Wavelet Packet Band Cepstral Coefficient. Second, K-singular value decomposition algorithm is employed to achieve the training of an over-complete mixture dictionary based on both the truth and deceptive feature sets, and an orthogonal matching pursuit algorithm is used for sparse coding according to the mixture dictionary to get sparse feature.Finally, recognition experiments axe performed with various classified modules. Experimental results show that the sparse decomposition method has better performance comparied with con?ventional dimension reduced methods. The recognition accuracy of the method proposed in this paper is 78.34%, which is higher than methods using other features, improving the recognition ability of deception detection system significantly.     

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.     

Infrared moving object detection based on local saliency and sparse representation

The key issue of infrared object detection is to locate moving object in image sequence. In order to improve detection precision, an infrared object detection method based on local saliency and sparse representation is proposed in this paper. Motion information, such as velocity, acceleration components are added into the eigenvectors to build local saliency model. And the approximate position of the infrared target is located based on the local saliency. To accurately extract the infrared object, sparse representation is used to capture complete edge of the object. Experiments show that the proposed method can accurately detect infrared moving objects, and has good robustness to external disturbances and dynamic background.     

基于热红外图像处理技术的农作物冠层识别方法研究

为解决农作物冠层热红外图像边缘灰度级分布不均且噪声较大,而传统图像分割方法难以实现其目标区域有效识别的难题,以苗期红小豆冠层热红外图像为研究对象,将模糊神经网络和仿射变换有机结合,提出了基于热红外图像处理技术的农作物冠层识别模型。首先利用五层线性归一化模糊神经网络的自适应特性,选取高斯隶属度函数,自动计算冠层可见光图像识别的推理规则,有效地分割了可见光图像中的冠层区域。通过分析3种分割指标和熵,定量评价可见光图像冠层分割质量。网络迭代38次时,误差精度为0.000 952,该算法平均有效识别率为96.13%,获取可见光冠层图像的像元信息熵值范围为2.454 4~5.198 7,与标准算法所得冠层图像的像元信息熵仅相差0.245 9。然后以取得可见光图像的冠层有效区域为参考图像,采用仿射变换算法,调整优选平移、旋转、缩放等图像变换因子,配准原始热红外图像,提出了基于仿射变换的冠层热红外图像识别方法。对于初始温度范围值在16.35~19.92 ℃的农作物热红外图像,计算选取旋转幅度为1.0和缩放因子为0.9时,作为异源图像的最优配准参数,获取目标图像的最大温差为3.17 ℃,相对于原图像的平均温度值由18.711 ℃下降至17.790 ℃,进而实现了基于热红外图像处理技术的农作物冠层识别。最后以熵的互信息作为监督指标,对农作物冠层热红外图像识别方法进行评价。提出的冠层热红外图像识别方法,所获取的目标图像与初始热红外图像的平均互信息为4.368 7,标准目标图像和初始热红外图像的平均互信息为3.981 8,二者仅相差0.486 9。同时,两种冠层热红外图像的平均温度差值为0.25 ℃,高效消除了原始热红外图像的背景噪声。结果表明本研究方法的有效性和实用性,能够为应用热红外图像反映农作物生理生态信息特征指标参数提供技术借鉴。     

粒子区别性稀疏表征的小弱运动目标跟踪算法

评估每个粒子的重要性是确保粒子滤波法跟踪目标准确性的重要因素。针对背景杂波和噪声干扰形成的大量虚警导致小弱目标跟踪识别的随机性和不确定性问题, 提出了一种基于粒子区别性稀疏表征的小弱目标跟踪方法。该方法根据红外图像信号自适应构建分类超完备字典, 即反映目标信号特征的目标字典和表示背景杂波的背景字典, 有利于突出目标粒子和背景粒子在联合分类字典的稀疏表征差异程度;建立基于目标粒子和背景粒子稀疏重构残差差异性的粒子滤波观测模型, 采用随机估计法对字典子空间进行在线更新, 实现对目标状态估计与跟踪。理论分析和试验结果表明, 该方法增强了随机粒子的状态估计能力, 提升了粒子稀疏表征对小弱运动目标的适应能力和跟踪识别准确度。     

A novel spatial–temporal detection method of dim infrared moving small target

Moving small target detection under complex background in infrared image sequence is one of the major challenges of modern military in Early Warning Systems (EWS) and the use of Long-Range Strike (LRS). However, because of the low SNR and undulating background, the infrared moving small target detection is a difficult problem in a long time. To solve this problem, a novel spatial–temporal detection method based on bi-dimensional empirical mode decomposition (EMD) and time-domain difference is proposed in this paper. This method is downright self-data decomposition and do not rely on any transition kernel function, so it has a strong adaptive capacity. Firstly, we generalized the 1D EMD algorithm to the 2D case. In this process, the project has solved serial issues in 2D EMD, such as large amount of data operations, define and identify extrema in 2D case, and two-dimensional signal boundary corrosion. The EMD algorithm studied in this project can be well adapted to the automatic detection of small targets under low SNR and complex background. Secondly, considering the characteristics of moving target, we proposed an improved filtering method based on three-frame difference on basis of the original difference filtering in time-domain, which greatly improves the ability of anti-jamming algorithm. Finally, we proposed a new time–space fusion method based on a combined processing of 2D EMD and improved time-domain differential filtering. And, experimental results show that this method works well in infrared small moving target detection under low SNR and complex background.