一种基于深层次多尺度特征融合CNN的SAR图像舰船目标检测算法

基于深度学习的目标检测技术在目标检测领域有强大的生命力,但是将其用于合成孔径雷达(SAR)图像舰船目标检测时并没有达到预期的效果。提出了一种基于卷积神经网络的SAR图像舰船目标检测算法用来检测多场景下的多尺度舰船目标,在单发多盒探测器检测框架的基础上,使用性能更好的Darknet-53作为特征提取网络,加入更深层次的特征融合网络,生成语义信息更加丰富的新的特征预测图。同时在训练策略上使用了一种新的二分类损失函数来解决训练过程中难易样本失衡的问题。在扩展的公开SAR图像舰船数据集上进行验证实验,实验结果表明,所提方法对复杂场景下不同尺寸的舰船目标的检测展现出了良好的适应性。     

双注意力循环卷积显著性目标检测算法

显著性目标检测是机器视觉领域的研究热点,具有广泛的应用前景。针对现有显著性目标检测算法存在的显著区域检测不均匀、边缘表示模糊等问题,提出一种双注意力循环卷积显著性目标检测算法。在U-Net全卷积骨干网络中添加像素间-通道间双注意力模块,在跨层连接前对底层特征进行预处理,减小噪声和杂波干扰,提高显著区域检测性能。在骨干网络后端使用循环卷积模块,将最后的预测图与底层卷积层特征进一步结合,增强预测区域边缘的表示效果。在三个公开数据集上进行实验评测,并与相关算法进行对比,结果表明所提算法能更好地均匀突显显著区域和细化区域边缘。     

基于自适应多层卷积特征决策融合的目标跟踪

针对在复杂环境中目标尺度变化、形状变化以及场景光照变化、背景干扰等因素导致的目标跟踪稳定性下降问题,提出一种基于自适应多层卷积特征决策融合的目标跟踪算法。首先,通过卷积神经网络VGG-Net-19提取目标候选区域的多层卷积特征;其次,在相关滤波模型框架下,利用这些卷积特征构建多个弱跟踪器;接着,根据每个弱跟踪器的决策损失变化自适应地调节它们的决策权重,完成基于多层卷积特征的目标位置估计;然后,根据尺度相关滤波模型在目标中心区域进行多尺度采样,并利用相邻帧的尺度变化先验分布完成对目标尺度的预测。选取51组具有多种挑战因素的视频序列对所提算法的跟踪性能进行测试。实验结果表明,与当前主流的目标跟踪算法相比,所提算法取得了更高的跟踪精度和成功率,同时可以较好地适应目标的尺度变化,并且在目标发生形变、场景出现光照变化及背景干扰等复杂条件下仍具有较好的跟踪鲁棒性。     

融合多尺度局部特征与深度特征的双目立体匹配

针对立体匹配中不适定区域难以找到精确匹配点的问题,提出一种融合多尺度局部特征与深度特征的立体匹配方法。特征融合阶段包括两部分,其一是融合不同尺度下Log-Gabor特征和局部二值模式特征组合的浅层次特征,其二是将多尺度浅层融合特征和卷积神经网络提取的深度特征进行级联,形成既包含语义信息又包含结构化信息的特征图像。通过在极线垂直方向添加不同强度的噪声来构造正负样本,减小图像中极线对齐欠准带来的误差。将该方法与两种变体方法(改变或舍弃部分模块)在KITTI数据集进行对比实验,结果表明各模块设置具有合理性;与一些经典方法相比,所提方法取得了有竞争力的匹配性能。     

基于边缘线分析与聚合通道特征的港口舰船检测

针对可见光学遥感图像港口舰船检测过程中,人造目标造成检测结果准确率低、虚警率高的问题,提出了一种基于边缘线梯度特征定位和聚合通道特征的舰船检测方法。基于多尺度多结构元素形态学滤波实现海陆分割;并结合遥感图像中港口的矩形形状特点,定义边缘梯度正切角和港口凹凸度特征以对港口进行定位,获取港口感兴趣区域集合。提取舰船目标的聚合通道特征,并通过聚合通道特征构建的样本训练库和AdaBoost算法完成分类器的训练,利用训练完成后的分类器完成舰船目标的最终判别确认。实验结果表明该算法相较于传统的HOG特征和Haar特征,检测效果良好,准确率和召回率得到较大的提升。     

基于全局感知孪生网络的红外目标跟踪

目前大多数热红外(TIR)目标跟踪算法都是基于相关滤波或者使用彩色跟踪器的模型进行特征提取.然而,两者都存在适用于彩色目标跟踪却对红外目标特征不敏感的缺陷,导致无法良好地应用到红外目标跟踪.为此,提出一种基于全局感知的孪生神经网络的红外目标跟踪器.将孪生神经网络的后三层特征进行融合优化,得到新的特征,同时加入了由空间转...     

基于特征融合的遥感图像舰船目标检测方法

针对常用的目标检测算法对遥感图像中的舰船目标进行检测时存在检测精度与实时性兼顾不佳的问题,提出了基于特征融合的遥感图像舰船目标检测算法来检测复杂场景下的多尺度舰船目标.该算法以多尺度单发射击检测框架为基础,增加反卷积特征融合模块和池化特征融合模块,增强网络特征提取的能力.同时设计聚焦分类损失函数来解决训练过程中正负样本失衡的问题.在高分遥感舰船目标数据集上的实验结果表明,所提方法能够有效地增强复杂场景下舰船目标的检测精度.此外,该算法对遥感图像中的模糊舰船目标的检测效果也优于多尺度单发射击检测框架.     

Spiking Neural Network Based on Multi-Scale Saliency Fusion for Breast Cancer Detection

Deep neural networks have been successfully applied in the field of image recognition and object detection, and the recognition results are close to or even superior to those from human beings. A deep neural network takes the activation function as the basic unit. It is inferior to the spiking neural network, which takes the spiking neuron model as the basic unit in the aspect of biological interpretability. The spiking neural network is considered as the third-generation artificial neural network, which is event-driven and has low power consumption. It modulates the process of nerve cells from receiving a stimulus to firing spikes. However, it is difficult to train spiking neural network directly due to the non-differentiable spiking neurons. In particular, it is impossible to train a spiking neural network using the back-propagation algorithm directly. Therefore, the application scenarios of spiking neural network are not as extensive as deep neural network, and a spiking neural network is mostly used in simple image classification tasks. This paper proposed a spiking neural network method for the field of object detection based on medical images using the method of converting a deep neural network to spiking neural network. The detection framework relies on the YOLO structure and uses the feature pyramid structure to obtain the multi-scale features of the image. By fusing the high resolution of low-level features and the strong semantic information of high-level features, the detection precision of the network is improved. The proposed method is applied to detect the location and classification of breast lesions with ultrasound and X-ray datasets, and the results are 90.67% and 92.81%, respectively.     

基于边缘链码高阶分形特征的舰船目标检测算法

针对舰船目标和海杂波轮廓结构的不同,提出了基于边缘链码高阶分形特征的舰船目标检测算法,算法利用相对链码对5类舰船目标轮廓进行编码,分别计算分形维和缝隙,得到了舰船目标的4个分形特征的范围。实验结果表明边缘链码的4个分形特征能有效区分舰船目标和海杂波。     

纹理高阶分形特征在海面舰船目标检测中的应用

针对复杂海面环境下的舰船目标检测，分析了高阶分形特征缝隙在纹理分类中的应用，提出了一种基于分形维与缝隙的目标检测新方法，并利用该方法对海面舰船目标进行了检测。实验结果表明利用纹理分形维与缝隙特征进行海面舰船目标检测，可以取得较单一分形维检测更高的准确率。     

基于多尺度特征提取与多元回归分析的人脸识别

为提高人脸识别的正确率,提出了一种改进的特征提取及分类算法。首先采用Contour-let变换对人脸图像进行多尺度分解,然后由低频子带和各尺度各方向的高频子带得到人脸的特征值,并将它们组合成多尺度特征向量,再应用多元回归分析方法进行人脸识别。由于多尺度特征向量不仅反映了整幅图像的全局特征,还反映了图像各种尺度下的边缘、纹理等奇异特征,因此具有更多的鉴别信息;多元回归分析则充分考虑了同一总体的各样本间的强线性关系。在ORL人脸库上的实验显示人脸识别率达97．78％,优于其他的方法。     

Multi-Focus Image Fusion Based on Multi-Scale Generative Adversarial Network

The methods based on the convolutional neural network have demonstrated its powerful information integration ability in image fusion. However, most of the existing methods based on neural networks are only applied to a part of the fusion process. In this paper, an end-to-end multi-focus image fusion method based on a multi-scale generative adversarial network (MsGAN) is proposed that makes full use of image features by a combination of multi-scale decomposition with a convolutional neural network. Extensive qualitative and quantitative experiments on the synthetic and Lytro datasets demonstrated the effectiveness and superiority of the proposed MsGAN compared to the state-of-the-art multi-focus image fusion methods.     

Network Traffic Anomaly Detection Method Based on a Feature of Catastrophe Theory

For the existing problems of current network traffic anomaly detection, the behavior of the network traffic anomaly will show nonlinearity, non-stationarity and complexity according to the network traffic often driven by the control of multiple factors. Owing to the characteristic that the internal evolution equation will lead to dynamical structure catastrophe, the phase space reconstruction method and the statistical physics method can be used to compute the macro feature values of the network traffic. By choosing some of the feature values which can obviously retlect the unusual change in the network traffic volume as control variables, a network traffic anomaly detection method based on the catastrophe series theory model is developed. Many experimental results show that the proposed network traffic anomaly detection method has a low false alarm rate under the same condition of detection rate.     

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。     

Multi-Scale Aggregation Graph Neural Networks Based on Feature Similarity for Semi-Supervised Learning

The problem of extracting meaningful data through graph analysis spans a range of different fields, such as social networks, knowledge graphs, citation networks, the World Wide Web, and so on. As increasingly structured data become available, the importance of being able to effectively mine and learn from such data continues to grow. In this paper, we propose the multi-scale aggregation graph neural network based on feature similarity (MAGN), a novel graph neural network defined in the vertex domain. Our model provides a simple and general semi-supervised learning method for graph-structured data, in which only a very small part of the data is labeled as the training set. We first construct a similarity matrix by calculating the similarity of original features between all adjacent node pairs, and then generate a set of feature extractors utilizing the similarity matrix to perform multi-scale feature propagation on graphs. The output of multi-scale feature propagation is finally aggregated by using the mean-pooling operation. Our method aims to improve the model representation ability via multi-scale neighborhood aggregation based on feature similarity. Extensive experimental evaluation on various open benchmarks shows the competitive performance of our method compared to a variety of popular architectures.     

基于GA特征选择和BP神经网络的模拟电路故障检测

针对模拟电路故障检测中存在测试节点数较多的问题,提出遗传算法与BP神经网络相结合的方法;利用遗传算法的全局、并行寻优能力对模拟电路的系统特征进行优化选择,从而减少BP神经网络输入层节点数;用MATLAB软件对仿真实例数据进行编程实验,直接使用BP神经网络,检测率为66.7%,采用遗传算法与BP神经网络结合的方法,检测率可为100%;结果表明,相对于传统的BP神经网络方法,该方法提高了模拟电路故障检测的平均正确率。