基于CNN与Transformer的医学图像分割

医学图像对疾病的诊断、治疗和评估均有所帮助,准确分割医学图像中的器官对于辅助医生的诊断具有重要的实际意义.由于医学图像中各器官部位与周围组织的图像对比度低,不同器官的边缘和形状也会存在很大差异,从而增加了分割的难度.针对这些问题,本文提出了一种基于卷积神经网络和Transformer的医学图像语义分割网络,有效提高了医学图像语义分割的精度.特征提取部分使用ResNet-50网络结构,在特征提取后使用Transformer模块来扩大感受野.在上采样过程中加入多个跳跃连接层,充分利用各阶段的特征提取信息,来恢复至与输入图像相近的分辨率.在胃肠道医学图像分割数据集上的实验结果证明本文的方法可以有效分割医学图像中的器官组织,提升分割准确率.     

深度学习屈光检测方法研究

屈光不正是一种非常常见且对视功能发育有严重危害的眼科问题。准确与方便的屈光检测技术,对于及时发现屈光不正问题以及采取相应措施进行干预具有非常重要的意义。目前的屈光筛查设备虽然能较快进行屈光检测,但主要存在两个问题：检测准确度较低,对被测者配合度要求较高。因此,提出一种新的屈光检测方法,此方法使用基于偏心摄影验光原理的光学系统获取人脸面部近红外图像,使用图像处理技术对面部近红外图像进行处理,得到左右瞳孔图像和瞳孔位置信息,使用提出的结合了深度可分离卷积和SE模块的混合数据多输入神经网络模型进行训练与屈光度的计算。与传统偏心摄影验光原理的屈光检测方法相比,此方法有望随着数据集的扩增而达到更高的准确度,并且此方法将瞳孔位置信息作为模型的输入,可以解决传统算法对被测者配合度要求较高的问题。该研究是对屈光检测新方法的一种有益探索,使用此方法有利于屈光筛查更便利地进行,为实现非接触自助式的屈光筛查提供基础。     

基于雨雾分离处理和多尺度网络的图像去雨方法

雨带来的雨条纹和雨雾会降低户外拍摄图像的质量,为了去除雨雾对图像的影响,提出了一种基于雨雾分离处理和多尺度卷积神经网络的图像去雨方法。首先利用导向滤波将雨线和图像细节信息提取到高频层,雨雾和背景信息则分离到低频层;然后构建多尺度卷积神经网络来去除高频层中的雨线,网络中融入多个稠密连接模块以提升特征提取的准确性;其次构建多层特征融合的轻量级去雾网络来去除低频层中的雨雾,采用参数一体化结构避免了估计多个大气散射模型参数导致的次优解;最后再结合处理后的高低频结果还原出清晰图像。在多个合成的雨雾数据集以及真实自然场景图像上进行测试,定性和定量结果表明,提出的方法在去除雨雾影响的同时较好地保留了色彩信息,和近年的算法相比,图像结构相似性约提升了0.02~0.08,图像峰值信噪比约提升了0.2~3.5 dB。     

Three-dimensional quantum wavelet transforms

Wavelet transform is being widely used in the field of information processing. One-dimension and two-dimension quantum wavelet transforms have been investigated as important tool algorithms. However, three-dimensional quantum wavelet transforms have not been reported. This paper proposes a multi-level three-dimensional quantum wavelet transform theory to implement the wavelet transform for quantum videos. Then, we construct the iterative formulas for the multi-level three-dimensional Haar and Daubechies D4 quantum wavelet transforms, respectively. Next, we design quantum circuits of the two wavelet transforms using iterative methods. Complexity analysis shows that the proposed wavelet transforms offer exponential speed-up over their classical counterparts. Finally, the proposed quantum wavelet transforms are selected to realize quantum video compression as a primary application. Simulation results reveal that the proposed wavelet transforms have better compression performance for quantum videos than two-dimension quantum wavelet transforms.     

Jointly beam stealing attackers detection and localization without training: an image processing viewpoint

Recently revealed beam stealing attacks could greatly threaten the security and privacy of IEEE 802.11ad communications. The premise to restore normal network service is detecting and locating beam stealing attackers without their cooperation. Current consistency-based methods are only valid for one single attacker and are parameter-sensitive. From the viewpoint of image processing, this paper proposes an algorithm to jointly detect and locate multiple beam stealing attackers based on RSSI (Received Signal Strength Indicator) map without the training process involved in deep learning-based solutions. Firstly, an RSSI map is constructed based on interpolating the raw RSSI data for enabling high-resolution localization while reducing monitoring cost. Secondly, three image processing steps, including edge detection and segmentation, are conducted on the constructed RSSI map to detect and locate multiple attackers without any prior knowledge about the attackers. To evaluate our proposal’s performance, a series of experiments are conducted based on the collected data. Experimental results have shown that in typical parameter settings, our algorithm’s positioning error does not exceed 0.41 m with a detection rate no less than 91%.     

回声信号处理综合实验设计及实现

针对学生对卷积和相关概念不清的问题,结合生活现象,本文设计了回声信号处理综合实验。实验内容包括回声产生、回声特性分析、回声消除,它将难以理解的卷积、自相关、互相关概念有机地串在一起,帮助学生理解和应用。实践表明,理论推导和实验编程相结合有助于学生将所学的知识融会贯通,且学生在做与生活密切联系的综合实验时,积极性高,收获大。     

面向典型战场应用的目标智能融合技术

针对战场多源信息融合的典型应用需求,提出了基于人工智能的目标信息融合技术思路,并对其中的两项关键技术,即新型融合知识库构建技术和基于本体核的目标知识融合技术进行了分析,最后对多源信息融合系统在应用过程中存在的技术问题及其解决思路进行了探讨。     

面向鲁棒频谱感知的模糊K-means++算法

恶意用户通过向数据融合中心发送伪造的频谱感知数据,解决自身频谱资源短缺问题,但会极大地降低频谱感知系统的检测概率。为了解决此问题,提出了基于模糊K means++的数据融合算法。该算法首先引入模糊处理机制处理样本的数据特征值,以此来增加样本间的差异性;然后将模糊处理后的数据发送到融合中心,融合中心采用离群点挖掘的方法排除恶意用户,并对保留下来的用户进行融合,使样本向量具有鲁棒性;最后运用K means++算法对样本向量进行聚类。该算法利用轮盘法选择聚类中心,可有效抵御恶意用户的攻击,提高系统感知性能;无需知晓信号与噪声的分布等一些先验信息,也避免了繁杂的门限推导。从仿真结果可以看出,该算法对抵御恶意用户攻击具有突出的效果,有效提升了协同频谱感知系统的稳定性和鲁棒性。     

Personalized voice activated grasping system for a robotic exoskeleton glove

This paper proposes a novel human machine interface (HMI) and electronics system design to control a rehabilitation robotic exoskeleton glove. Such system can be activated with the user’s voice, take voice commands as input, recognize the command and perform biometric authentication in real-time with limited computing power, and execute the command on the exoskeleton. The electronics design is a stand-alone plug-and-play modulated design independent of the exoskeleton design. This personalized voice activated grasping system achieves better wearability, lower latency, and improved security than any existing exoskeleton glove control system.     

Multi-scale fusion residual encoder-decoder approach for low illumination image enhancement

The sensing light source of the line scan camera cannot be fully exposed in a low light environment due to the extremely small number of photons and high noise, which leads to a reduction in image quality. A multi-scale fusion residual encoder-decoder (FRED) was proposed to solve the problem. By directly learning the end-to-end mapping between light and dark images, FRED can enhance the image's brightness with the details and colors of the original image fully restored. A residual block (RB) was added to the network structure to increase feature diversity and speed up network training. Moreover, the addition of a dense context feature aggregation module (DCFAM) made up for the deficiency of spatial information in the deep network by aggregating the context's global multi-scale features. The experimental results show that the FRED is superior to most other algorithms in visual effect and quantitative evaluation of peak signa-to-noise ratio (PSNR) and structural similarity index measure (SSIM). For the factor that FRED can restore the brightness of images while representing the edge and color of the image effectively, a satisfactory visual quality is obtained under the enhancement of low-light.