Spatio-temporal segmentation of moving objects using edge features in infrared videos

In this paper, a novel method is proposed for spatio-temporal segmentation of moving objects using edge features in infrared videos. We define motion saliency of edge (MSoE) to generate the MSoE-map. The seeds of moving objects are extracted from the MSoE-map by using Otsu's method and subsequently compensated by historical data. An improved layer-based region growing method is applied to the seeds to achieve spatial segmentation of moving objects. The region growing method has an adjustable growing threshold. So, one of the focuses of our work is how to determine the best growing threshold. A Markov Random Field (MRF) based criterion with maximum a posterior (MAP) estimation principle is proposed for performance evaluation of moving object segmentation without ground truth (GT) in infrared videos. This criterion can be considered as an object function of threshold determination during global searching. The global optimum is accomplished by using simulated annealing (SA) algorithm to obtain the best growing threshold. The final segmentation mask of moving objects is grown from the seeds with the best growing threshold. Experimental results are provided to illustrate that the proposed method has better performance for moving object segmentation with fewer effects of object-background misclassification in infrared videos.     

An unmanned aerial vehicle identification and tracking system based on weakly supervised semantic segmentation technology

This paper presents an unmanned aerial vehicle (UAV) identification and tracking system aimed at monitoring UAVs based on weakly supervised semantic segmentation. A camera is equipped with a pan–tilt to collect images for semantic segmentation network in real time. The GrabCut+ algorithm and annotation boxes are employed to generate the UAV “pseudo pixel labels” for supervised model learning and reduce labelling costs. A new loss function combining the focus loss function and dice loss function is designed to balance positive and negative samples and improve the segmentation effect. The Mixup method is introduced for model training to prevent overfitting and enhance the generalization ability of the model. The semantic segmentation network outputs the prediction results by a fully connected conditional random field to smooth the target image. Furthermore, a region-based tracking method is proposed to solve the hysteresis problem of the pan–tilt control system and improve the system tracking performance. Finally, an experiment based on a dataset is carried out to prove the effectiveness of the segmentation algorithm with 66.3% mIoU. Considering that 10% of the central area of view is specified as the view centre, a UAV falling in the centre of the field accounts for more than 80% of this view area, demonstrating the real-time effectiveness of the designed UAV identification and tracking system.     

基于颜色和空间信息的多特征融合目标跟踪算法

为解决单一特征目标跟踪鲁棒性较差的问题,提出一种基于颜色和空间信息的多特征融合目标跟踪算法。采用一种自适应划分颜色区间的方法提取目标颜色特征,利用空间直方图提取目标颜色的空间分布信息。在粒子滤波框架下将自适应颜色直方图和空间直方图相结合,在特征融合中引入特征不确定性度量方法,自适应调整不同特征对跟踪结果的贡献,提高算法的鲁棒性。仿真实验结果表明,该跟踪算法平均位置最小误差值仅6.967 像素,而单一特征跟踪算法以及传统融合算法的跟踪误差达192.576 像素和199.464像素。说明本文算法在跟踪准确性上优于单一特征跟踪算法及传统融合算法,具有更好的跟踪精度和更高的鲁棒性。     

Nonuniformity correction of infrared images based on infrared radiation and working time of thermal imager

The spatial fixed-pattern noise (FPN) reduces the quality of the infrared image seriously, even makes infrared images inappropriate for some applications. In order to lower the FPN, some critical nonuniformity correction (NUC) algorithms such as NUC based on linear model, scene-based NUC and so on have been developed. But the algorithms have some drawbacks: restricted application in small dynamic range of objects temperature, low performance under the drift with the working time and complex calculations. In these cases, we develop a bivariate and quadratic model (bivariate is radiation and working time) of the FPA and the NUC technique based on the model. The proposed method is a true reflection of the infrared response and is a good solution for hardware implementation. It overcomes the drawbacks of the critical algorithm mentioned above. The last simulations and experiments show that the proposed algorithm exhibits a superior correction effect in both large objects temperature range and long working time of the thermal imager.     

Automatic detection of colloidal particles based on a shape regularized integrated active contour model

Manual segmentation of single colloidal particle in suspension encounters a bottleneck when a number of defocused particles simultaneously exist in an image. In this paper, we describe an image processing algorithm for extracting individual particle from digitized microscope images of colloidal suspensions. We propose a particle detection and location solution using a shape regularized integrated active contour model (ACM). Compared with existing methods where active contour models are not applied well to deal with multiple objects in complicated background, the proposed approach can automatically identify and locate multiple particles by combining characteristics of the particles such as shape, boundary and region. A regularization term is defined by prior information of specific shape, which is able to drive the shape of evolving curve toward the shape prior gradually. To locate the centers of the particles, the Hough transform is applied. Experimental results using polystyrene beads as sample particles reveal that the method has high efficiency and ability to deal with colloidal particles.     

Automatic segmentation of white matter lesions on magnetic resonance images of the brain by using an outlier detection strategy

White matter lesions (WMLs) are commonly observed on the magnetic resonance (MR) images of normal elderly in association with vascular risk factors, such as hypertension or stroke. An accurate WML detection provides significant information for disease tracking, therapy evaluation, and normal aging research. In this article, we present an unsupervised WML segmentation method that uses Gaussian mixture model to describe the intensity distribution of the normal brain tissues and detects the WMLs as outliers to the normal brain tissue model based on extreme value theory. The detection of WMLs is performed by comparing the probability distribution function of a one-sided normal distribution and a Gumbel distribution, which is a specific extreme value distribution. The performance of the automatic segmentation is validated on synthetic and clinical MR images with regard to different imaging sequences and lesion loads. Results indicate that the segmentation method has a favorable accuracy competitive with other state-of-the-art WML segmentation methods.     

基于C-V模型的改进快速水平集图像分割法

针对水平集方法计算复杂度高,无法满足实时系统要求的缺陷,提出一种改进的快速水平集算法。该算法对快速水平集算法进行简化,采用单链表表示轮廓曲线。利用C-V模型的二值拟合项来设计曲线演化的速度函数,保留了C-V模型的全局优化特性。还给出了一个基于单链表中轮廓点个数变化的水平集演化终止准则。该算法不仅明显提高了分割速度,且对噪声图像也能实现高效的分割。     

一种基于区域分割与跟踪的多视点视频校正算法

针对多视点图像系统中视点图像颜色不一致的问题,提出了基于区域分割与跟踪的多视点视频校正算法.采用3维高斯混合模型来描述颜色信息,利用期望-最大算法来精炼模型参量,并通过自适应聚类和概率平滑操作来得到精确的分割图像.这样建立起多视点图像分割区域间的局部映射关系,并利用这种局部映射关系对全局图像进行校正.最后利用视频跟踪技术实现对视频图像的校正.实验结果表明,该算法能消除颜色过饱和或颜色区域混淆的影响,且具有较好的校正效果.     

基于深度学习的铸件X射线图像分割研究

针对当前图像分割算法在实现工业铸件内部缺陷分割上精度低且算法不够轻量化的问题,提出一种基于改进DeepLabv3+的工业铸件内部缺陷检测算法Effi-DeepLab。该方法采用EfficientNet中的MBConv来代替原有的Xception模块进行特征提取,使特征提取网络更加高效与轻量化;针对工业铸件内部缺陷尺寸小的问题,重新设计空洞空间金字塔池化（ASPP）层中空洞卷积的扩张率,使得卷积块对小目标具有更高的鲁棒性;在解码端充分利用特征提取阶段的低阶语义信息进行多尺度特征融合,以提高小目标缺陷分割的精度。实验结果表明,在本文使用的汽车轮毂内部缺陷图像数据集中,Effi-DeepLab模型对缺陷的分割准确率和平均交并比（mIoU）分别为93.58%和89.39%,相比DeepLabv3+分别提升了2.65%和2.24%,具有更好的分割效果;此外,还通过实验验证了本文提出算法具有良好的泛化性。     

高帧频信标光定位与跟踪实验研究

信标光斑准确定位是完成空间光通信跟踪和捕获时的一个重要方法。应用改进的Otsu分割方法,对采集序列图像进行实时处理,提取潜在的信标光斑,对后续图像处理引入感兴趣区域的读入技术,在感兴趣区域内对信标光图像进行处理,应用卡尔曼预测模型实现了信标光跟踪,并将跟踪误差控制在精跟踪视场之内。实验结果表明,改进的Otsu具有更佳的抗噪能力和分割效果,并且实时性和定位精度均获得了满意的结果。     

基于偏振测量的雾天图像场景分割

现有场景分割方法主要依赖于图像亮度、颜色和纹理等特征,然而在雾天图像中提取这些特征将变得困难且不稳定.基于此本文提出了适用于雾天图像场景分割的特征矢量,以及相应的特征提取算法.特征矢量由目标偏振度、深度和颜色三部分组成.特征提取算法分别为:用去相关的方法从图像偏振度分离出大气偏振度和目标偏振度;根据雾天退化模型和雾天图像偏振表示形式推导出场景深度信息;利用两幅偏振图像求出非偏振彩色图像,从而得到场景的颜色信息.将这些特征构成的特征矢量用于基于图的分割算法中,并从两个方面比较了仅使用颜色特征和使用本文特征矢量的分割结果.最后得出结论:对于雾天图像而言,这些特征比通常的颜色特征更加有效和鲁棒.     

结合区域提取和改进卷积神经网络的水下小目标检测

针对水下小目标信息量有限而难以提取有效特征导致的检测性能不佳问题,提出了一种结合区域提取和融合Hu矩特征的改进卷积神经网络水下小目标检测方法。该方法包含区域提取和分类两个步骤。首先以马尔可夫随机场分割算法为基础进行区域提取,对潜在目标定位的同时降低伪目标对后续分类的干扰;然后提取潜在目标区域的Hu矩特征并融入卷积神经网络,形成一种形状特征表征能力更强的改进卷积神经网络用于分类。声呐实测数据处理结果表明,该方法可以有效提升对水下小目标的发现概率和正确报警率,与其他目标检测方法相比,该方法具有更好的检测性能和泛化性。     

对数似然图像分割的快速主动轮廓跟踪算法

针对跟踪目标尺度变化问题,提出了基于灰度对数似然图像分割的快速主动轮廓跟踪算法。改进的主动轮廓跟踪算法将根据以目标与背景的颜色差异而建立的对数似然图对图像进行阈值分割和数学形态学处理,再将Kalman滤波器结合到主动轮廓跟踪算法进行目标跟踪。改进的主动轮廓跟踪算法对目标分割准确,轮廓特征显著,跟踪效果稳定,算法能很好地适应跟踪目标尺度变化。通过Kalman滤波器对目标位置点的预测减少了主动轮廓跟踪算法收敛的迭代次数,使算法的运算效率提高了33%左右。     

Fast Poissonian image segmentation with a spatially adaptive kernel

The variational models with the goal of minimizing the local variation are widely used for the segmentation of the intensity inhomogeneous images recently. Local variation is a good measure for the images corrupted by Gaussian noise. However, in many applications such as astronomical imaging, electronic microscopy and positron emission tomography, Poisson noise often occurs in the observed images. To deal with this kind of images, we develop a novel segmentation model based on minimizing local generalized Kullback–Leibler (KL) divergence with a spatially adaptive kernel. A fast algorithm based on the split-Bregman method is proposed to solve the corresponding optimization problem. Numerical experiments for synthetic and real images demonstrate that the proposed model outperforms most of the current state-of-the-art methods in the present of Poisson noise.     

基于改进DeepLabv3+的无人车夜间红外图像语义分割

为了增强无人车对夜间场景的理解能力,针对无人车在夜间获取的红外图像,提出了一种基于改进DeepLabv3+网络的无人车夜间红外图像语义分割算法。由于自动驾驶场景中的对象往往显示出非常大的尺度变化,该算法在DeepLabv3+网络的基础上,通过引入密集连接的空洞卷积空间金字塔模块,使网络生成的多尺度特征能覆盖更大的尺度范围。此外,该算法将编码器模块的多层结果拼接在译码器模块中,以恢复更多在降采样过程中丢失的空间信息和低级特征。通过端到端的学习和训练,可直接用于对夜间红外图像的语义分割。实验结果表明,该算法在红外数据集上的分割精度优于原DeepLabv3+算法,平均交并比达到80.42,具有良好的实时性和准确性。     

Content-based adaptive image denoising using spatial information

The maximum a posteriori (MAP) model is widely used in image processing fields, such as denoising, deblurring, segmentation, reconstruction, and others. However, the existing methods usually employ a fixed prior item and regularization parameter for the whole image and ignore the local spatial adaptive properties. Though the non-local total variation model has shown great promise because of exploiting the correlation in the image, the computation cost and memory load are the issues. In this paper, a content-based local spatial adaptive denoising algorithm is proposed. To realize the local spatial adaptive process of the prior model and regularization parameter, first the degraded image is divided into several same-sized blocks and the Tchebichef moment is used to analyze the local spatial properties of each block. Different property prior items and regularization parameters are then applied adaptively to different properties’ blocks. To reduce the computational load in denoising process, the split Bregman iteration algorithm is employed to optimize the non-local total variation model and accelerate the speed of the image denoising. Finally, a set of experiments and performance evaluation using recent image quality assessment index are provided to assess the effectiveness of the proposed method.     

A modified region growing algorithm for multi-colored image object segmentation

A hybrid algorithm based on seeded region growing and k-means clustering was proposed to improve image object segmentation result. A user friendly segmentation tool was provided for the definition of objects,then k-means algorithm was utilized to cluster the selected points into k seeds-clusters, finally the seeded region growing algorithm was used for object segmentation. Experimental results show that the proposed method is suitable for segmentation of multi-colored object, while conventional seeded region growing methods can only segment uniform-colored object.     

Analysis and synthesis of multicolored objects in a single image

We present a method with which to recover the intrinsic shading and reflectance characteristics of multicolored three-dimensional objects in a single image, with which realistic new scenes can be synthesized. A color watershed algorithm, which is based on a regularized dichromatic fitting error, is proposed for robust image segmentation. For shading recovery in small regions, a weighted interpolation is employed, whereas in large regions the reflectance and shading are calculated based on the assumption of gradual shape variation. It is demonstrated that the proposed method is promising and can be applied in image simulation.     

A joint shape evolution approach to medical image segmentation using expectation-maximization algorithm

This study proposes an expectation–maximization (EM)-based curve evolution algorithm for segmentation of magnetic resonance brain images. In the proposed algorithm, the evolution curve is constrained not only by a shape-based statistical model but also by a hidden variable model from image observation. The hidden variable model herein is defined by the local voxel labeling, which is unknown and estimated by the expected likelihood function derived from the image data and prior anatomical knowledge. In the M-step, the shapes of the structures are estimated jointly by encoding the hidden variable model and the statistical prior model obtained from the training stage. In the E-step, the expected observation likelihood and the prior distribution of the hidden variables are estimated. In experiments, the proposed automatic segmentation algorithm is applied to multiple gray nuclei structures such as caudate, putamens and thalamus of three-dimensional magnetic resonance imaging in volunteers and patients. As for the robustness and accuracy of the segmentation algorithm, the results of the proposed EM-joint shape-based algorithm outperformed those obtained using the statistical shape model-based techniques in the same framework and a current state-of-the-art region competition level set method.     

利用二维属性直方图的最大熵的图像分割方法

提出二维属性直方图的概念。它是一种由先验知识约束的二维直方图,可以使一些图像处理方法得到简化和变得可行。在此基础上提出一种基于二维属性直方图的图像分割方法。该方法步骤是构造图像的属性集,确定相应的二维属性直方图,然后利用二维属性直方图的最大熵法确定灰度阈值。为了说明该方法的性能,将其用于一种海底小目标图像分割。同时,也使用一维属性直方图的最大熵分割法。结果表明该方法比一维属性直方图的最大熵法抗干扰性更强,分割效果更好。二维属性直方图的概念具有理论意义与应用价值。该方法适用于图像有某种先验知识的场合。