基于新的阈值化方法的背景减法改进

首先将一种新的基于颜色空间模型的阈值化方法用于背景减法中,该阈值化方法利用每个像素的颜色畸变和亮度畸变检测出场景中所有的运动,其中像素的颜色畸变检测考虑了颜色向量所处的空间位置;同时该阈值化方法在一定程度上抑制了运动阴影的影响.其次,将一种双阈值化方法用于背景减法中,实现了复杂场景下前景目标的提取.通过VSSN 05和PETS 2006测试视频的实验,验证了本文提出算法的有效性.

DRSTN:深度残差软阈值化网络

在采用深度残差等神经网络模型解决图像分类任务时,特征提取过程损失的一些重要特征会影响模型的分类性能。神经网络“端到端”的学习模式带来的黑盒问题,也会限制其在诸多领域的应用和发展。另外,神经网络模型往往需要较长的训练时间。为了提高深度残差网络模型的分类效果和训练效率,引入了模型迁移方法和软阈值化方法,提出了DRSTN(Deep Residual Soft Thresholding Network)网络,并对此网络结构进行微调,生成了不同版本的DRSTN网络。DRSTN网络的性能得益于3个方面的有机整合:1)通过梯度加权类激活映射(Gradients-weighted Class Activation Mapping,Grad-CAM)方法对网络的特征提取进行可视化,根据可视化结果挑选进一步优化的模型;2)基于模型迁移,研究人员不必全新地搭建模型,可以直接在已有的模型上进行优化,能够节省大量训练时间;3)软阈值化作为非线性变换层嵌入到深度残差网络体系结构中,以消除样本中不相关的特征。实验结果表明,在相同训练条件下,DRSTN_KS(3*3)_RB(2:2:2)网络在CIFAR-10数据集上的分类精度相比SKNet-18,ResNet18和ConvNeXt_tiny网络分别提高了15.5%,8.8%和10.9%;该网络也具有一定的泛化性,在MNIST和Fashion MNIST数据集上能够达到快速的迁移效果,分类精度分别达到99.06%和93.15%。

基于绝对值距离的图像阈值化分割新算法

传统Otsu阈值法对图像分割缺乏一定鲁棒性的不足,将Otsu阈值法的平方欧氏距离用绝对值距离代替得到一种新的图像阈值化分割准则,提出了基于绝对值距离的图像阈值分割新算法,最后给出其参数估计方法。实验结果表明,分割新算方法是有效的,能够获得比传统Otsu方法更好的分割结果。

An enhanced image binarization method incorporating with Monte-Carlo simulation

We proposed an enhanced image binarization method.The proposed solution incorporates Monte-Carlo simulation into the local thresholding method to address the essential issues with respect to complex background,spatially-changed illumination,and uncertainties of block size in traditional method.The proposed method first partitions the image into square blocks that reflect local characteristics of the image.After image partitioning,each block is binarized using Otsu’s thresholding method.To minimize the influence of the block size and the boundary effect,we incorporate Monte-Carlo simulation into the binarization algorithm.Iterative calculation with varying block sizes during Monte-Carlo simulation generates a probability map,which illustrates the probability of each pixel classified as foreground.By setting a probability threshold,and separating foreground and background of the source image,the final binary image can be obtained.The described method has been tested by benchmark tests.Results demonstrate that the proposed method performs well in dealing with the complex background and illumination condition.

红外热像法识别陶瓷地砖空鼓试验及其机器视觉分析

分析了我国北方寒区陶瓷地砖空鼓产生的原因及带来的危害,指出了陶瓷地砖空鼓检测的工程意义及迫切性。参照红外热像法检测外墙空鼓的方法,首先设计和制作了足尺地热采暖陶瓷地砖空鼓楼板模型,然后采用红外热像仪拍摄得到了30℃-60℃下陶瓷地砖表面温度场分布的红外热像图,最后对热像图进行了机器视觉分析。采用局部阈值二值化方法对热像图进行了图像处理,将二值化图像与地砖实际空鼓重叠比较,提出了陶瓷地砖空鼓识别判定计算指标,分析了图像处理后的地砖空鼓识别精度。试验结果表明:红外热像法可用于检测陶瓷地砖空鼓,随着地热管温度升高,空鼓检测精度提高。建议红外热像法检测陶瓷地砖空鼓检测最佳温度为60℃。二值化处理方法可用于处理陶瓷地砖空鼓热像图。计算指标漏检率、误检率、面积重合率和中心偏差率可用于判定陶瓷地砖空鼓情况。

Bayesian Reliability Assessment and Degradation Modeling with Calibrations and Random Failure Threshold

A degradation model with a random failure threshold is presented for the assessment of reliability by the Bayesian approach. This model is different from others in that the degradation process is proceeding under pre-specified periodical calibrations. And here a random threshold distribution instead of a constant threshold which is difficult to determine in practice is used. The system reliability is defined as the probability that the degradation signals do not exceed the random threshold. Based on the posterior distribution estimates of degradation performance, two models for Bayesian reliability assessments are presented in terms of the degradation performance and the distribution of random failure threshold. The methods proposed in this paper are very useful and practical for multi-stage system with uncertain failure threshold. This study perfects the degradation modeling approaches and plays an important role in the remaining useful life estimation and maintenance decision making.