Aerial-BiSeNet: A real-time semantic segmentation network for high resolution aerial imagery

The aircraft system has recently gained its reputation as a reliable and efficient tool for sensing and parsing aerial scenes. However, accurate and fast semantic segmentation of high-resolution aerial images for remote sensing applications is still facing three challenges: the requirements for limited processing resources and low-latency operations based on aerial platforms, the balance between high accuracy and real-time efficiency for model performance, and the confusing objects with large intra-class variations and small inter-class differences in high-resolution aerial images. To address these issues, a lightweight and dual-path deep convolutional architecture, namely Aerial Bilateral Segmentation Network (Aerial-BiSeNet), is proposed to perform real-time segmentation on high-resolution aerial images with favorable accuracy. Specifically, inspired by the receptive field concept in human visual systems, Receptive Field Module (RFM) is proposed to encode rich multi-scale contextual information. Based on channel attention mechanism, two novel modules, called Feature Attention Module (FAM) and Channel Attention based Feature Fusion Module (CAFFM) respectively, are proposed to refine and combine features effectively to boost the model performance. Aerial-BiSeNet is evaluated on the Potsdam and Vaihingen datasets, where leading performance is reported compared with other state-of-the-art models, in terms of both accuracy and efficiency.     

无需先验信息的水平集SAR图像分割方法

给出了一种基于水平集演化、无需任何先验信息的SAR图像分割方法.该方法是一种基于区域信息的统计活动轮廓模型方法,通过利用分段阶跃函数估计图像概率密度函数,克服了利用特定概率分布模型估计概率密度函数时,需要利用先验信息预先假定图像概率分布模型的问题;通过引入惩罚项,避免了费时且难于操作的水平集函数重新初始化过程.还给出了具体的数值实现方案和相关参数取值,改进了数值实现中的迭代终止条件.实验结果表明,固定使用列出的参数,无需任何人为干预,对于大多数图像都可获得令人满意的分割结果;对于少数图像,通过简单的参数调整也可得到良好结果.     

基于多特征的高分遥感图像分割算法研究

针对传统的图像分割算法不能完全适用具有多种特征〖BF〗（〖BFQ〗光谱特征、纹理特征和几何特征〖BF〗）〖BFQ〗的高分辨率遥感图像的问题,提出了一种基于多特征的遥感图像分割算法。算法基于改进的均值漂移滤波和自动标记分水岭分割方法来实现最终分割。首先利用自动标记分水岭分割方法对遥感图像进行分割,进而采用仿射不变矩形状特征算子提取图像几何特征;其次对图像进行主成分分析,计算第一主成分灰度共生矩阵,分析矩阵特性得出纹理特征;然后结合光谱特征通过改进的均值漂移方法得到多特征滤波结果;最后利用分水岭分割方法实现高分辨率遥感图像分割。为了表明算法的分割效果,利用基于多光谱信息熵方法对算法和单一的分水岭分割方法进行非监督评价。研究结果表明,算法可较好地改善遥感图像的过分割问题,是一种适合高空间分辨率多光谱遥感图像的分割算法。     

A model of the effects of heavy ion radiation on human tissue

In heavy ion radiotherapy and space travel humans are exposed to energetic heavy ions (C, Si, Fe and others). This type of irradiation often produces more severe biological effects per unit dose than more common X-rays. A new Monte Carlo model generates a physical space with the complex geometry of human tissue or a cell culture based model of tissue, which is affected by the passage of ionizing radiation. For irradiation, the model relies on a physical code for the ion track structure; for tissues, cellular maps are derived from two- or three-dimensional confocal microscopy images using image segmentation algorithm, which defines cells as pixilated volumes. The model is used to study tissue-specific statistics of direct ion hits and the remote ion action on cells. As an application of the technique, we considered the spatial pattern of apoptotic cells after heavy ion irradiation. The pattern of apoptosis is modeled as a stochastic process, which is defined by the action cross section taken from available experimental data. To characterize the degree of apoptosis, an autocorrelation function that describes the spatial correlation of apoptotic cells is introduced. The values of the autocorrelation function demonstrate the effect of the directionality of the radiation track on the spatial arrangements of inactivated cells in tissue. This effect is intrinsic only to high linear-energy-transfer radiation.     

基于小波包分解和FCM聚类的纹理图像分割方法

提出了一种新的图像特征提取中选取最优小波分解树的方法.塔式小波分解对信号解不够全面,而小波包全分解又引入庞大的计算量,因此小波分解最优树的选取尤为重要.结合模糊c均值(FCM,Fuzzy C-Mean)聚类,提出了一种能同时进行小波自适应分解和纹理特征分类的纹理图像分割方法,该方法将无监督聚类中的聚类有效性参数引入到自适应小波分解的判决中,能根据无监督聚类分割的需要,自适应地选取小波包分解的树形结构和分解层数.相对于小波包全分解,节省了大量的运算,并能取得良好的分割效果.      

彩色图像分割算法研究与费歇算法应用

图像分割是图像分析和模式识别需要解决的首要问题和经典难题。彩色图像比灰度图像具有更多的视觉信息,因而受到了越来越多的重视。文中对各种彩色图像分割方法进行了系统论述,分析了各种方法的优缺点,重点介绍了费歇算法。该算法能有效地对彩色图像进行分割,在工业实践中取得了比较好的效果。     

An ensemble deep learning based shoreline segmentation approach (WaterNet) from Landsat 8 OLI images

Shorelines constantly vary due to natural, urbanization and anthropogenic effects such as global warming, population growth, and environmental pollution. Sustainable monitoring of coastal changes is vital in terms of coastal resource management, environmental preservation and planning. Publicly available Landsat 8 OLI (Operational Land Manager) images provide accurate, reliable, temporal and up-to-date information about coastal areas. Recently, the use of machine learning and deep learning algorithms have become widespread. In this study, we used our public Landsat 8 OLI satellite image dataset to create a majority voting method which is an ensemble automatic shoreline segmentation system (WaterNet) to obtain shorelines automatically. For this purpose, different deep learning architectures have been utilized namely as Standard U-Net, Dilated U-Net, Fractal U-Net, FC-DenseNet, and Pix2Pix. Also, we have suggested a novel framework to create labeling data from OpenStreetMap service to create a unique dataset called YTU-WaterNet. According to the results, IoU and F1 scores have been calculated as 99.59% and 99.79% for the WaterNet. The results indicate that the WaterNet method outperforms other methods in terms of shoreline extraction from Landsat 8 OLI satellite images.     

基于纹理特征多分辨双Markov-GAR模型的SAR图像分割

为了提高SAR图像分割精度,提出在以灰度共生矩阵产生的纹理统计量为特征所生成的图像上,同时考虑SAR图像像素间空间分布特征和局部灰度均值和方差等统计量给出多分辨双Markov框架下的GAR模型,采用多分辨MPM的参数估计方法及对应的无监督分割算法,对SAR图像进行纹理分割。实验结果表明该方法用于一些高分辨SAR图像,与基于灰度图像上的多分辨双Markov-GAR模型纹理分割相比,在分割精度上能降低分割时的错分率。     

噪声图象的快速边缘提取与分割

噪声图象的快速边缘提取和分割是实时图象处理中的重要问题。本文提出了一种噪声图象快速边缘提取和分割算法。实验表明,这种方法具有很强的噪声抑制能力,且快速准确。     

基于卷积神经网络的航天复合材料缺陷智能检测

针对传统的缺陷图像识别处理方式存在着准确度与辨识度不足,且处理缺陷种类单一的问题,提出了一种基于Cascade R-CNN和Mask R-CNN的神经网络模型。首先,为了提高缺陷检测的可视化效果和检测准确度,在实例分割卷积网络Mask R-CNN的基础上,结合级联神经网络Cascade R-CNN结构,组合成了新的级联实例分割Cascade Mask R-CNN网络;其次,对组合而成的级联卷积神经网络进行了训练,将训练好的模型对复合材料缺陷图像进行了检测。实验结果表明:检测的平均准确度达到了91.5%,平均置信度达到了97.3%,达到了检测精度的要求。该研究成果可运用于航天复合材料缺陷识别。