Choice of a pertinent color space for color texture characterization using parametric spectral analysis

This article presents a comparison of different color spaces including RGB, IHLS and L?a*b* for color texture characterization. This comparison is based on the fusion of the independent spatial structure and color feature cues. In IHLS and L*a*b*, two channel complex color images are created from the luminance and the chrominance values. For such images, two dimensional complex multichannel linear prediction models are used to perform parametric power spectrum estimation and the structure feature cues are computed from this estimated power spectrum. Quantitative comparison of auto spectra of luminance and combined chrominance channels for different color spaces is done. This comparison is based on the degree of decorrelation between luminance and chrominance information provided by different color space transformations. Three dimensional histograms are used as color feature cues. Then, to classify color textures, Kullback-Leibler divergence based symmetric distance measures are calculated for pure color, luminance structure and chrominance structure feature cues. Individual as well as combined effect of information from all feature cues on classification results is then compared for different color spaces and different color texture data sets. The proposed color texture classification method performs better than the state of the art methods in certain cases. The L*a*b* color space gives us a better characterization of the chrominance spatial structure as well as the overall spatial structure for all of the chosen data sets. Experimental results on pixel classification of color textures are also presented and discussed.     

稠密融合卷积神经网络的多模态地基云状分类

为了解决现有的地基云状分类方法对多模态信息利用不充分的问题,有效融合地基云样本的视觉特征与多模态特征,提出稠密融合卷积神经网络的多模态地基云状分类方法.稠密融合卷积神经网络采用卷积神经网络作为视觉子网络提取地基云图像的视觉特征,采用多模态子网络提取多模态特征,在网络内部加入了5个稠密融合模块,用于充分融合视觉特征与多模...     

复杂场景下多尺度船舶实时检测方法

船舶检测在军事侦察、海上目标跟踪、海上交通管制等任务中发挥着重要作用。然而,受船舶外形尺度多变和复杂海面背景的影响,在复杂海面上检测多尺度船舶仍然是一个挑战。针对此难题,提出了一种基于多层信息交互融合和注意力机制的 YOLOv4 改进方法。该方法主要通过多层信息交互融合（multi-layer information interactive fusion,MLIF）模块和多注意感受野（multi-attention receptive field,MARF）模块构建一个双向细粒度特征金字塔。其中,MLIF模块用于融合不同尺度的特征,不仅能将深层的高级语义特征串联在一起,而且将较浅层的丰富特征进行重塑;MARF由感受野模块（receptive field block,RFB）与注意力机制模块组成,能有效地强调重要特征并抑制冗余特征。此外,为了进一步评估提出方法的性能,在新加坡海事数据集（Singapore maritime dataset,SMD）上进行了实验。实验结果表明,所提方法能有效地解决复杂海洋环境下多尺度船舶检测的难题,且同时满足了实时需求。     

Efficient graph attentional network for 3D object detection from Frustum-based LiDAR point clouds

LiDAR-based 3D object detection is important for autonomous driving scene perception, but point clouds produced by LiDAR are irregular and unstructured in nature, and cannot be adopted by the conventional Convolutional Neural Networks (CNN). Recently, Graph Convolutional Networks (GCN) has been proved as an ideal way to handle non-Euclidean structure data, as well as for point cloud processing. However, GCN involves massive computation for searching adjacent nodes, and the heavy computational cost limits its applications in processing large-scale LiDAR point cloud in autonomous driving. In this work, we adopt a frustum-based point cloud-image fusion scheme to reduce the amount of LiDAR point clouds, thus making the GCN-based large-scale LiDAR point clouds feature learning feasible. On this basis, we propose an efficient graph attentional network to accomplish the goal of 3D object detection in autonomous driving, which can learn features from raw LiDAR point cloud directly without any conversions. We evaluate the model on the public KITTI benchmark dataset, the 3D detection mAP is 63.72% on KITTI Cars, Pedestrian and Cyclists, and the inference speed achieves 7.9 fps on a single GPU, which is faster than other methods of the same type.     

红外双波段成像系统的研究与发展

红外双波段成像系统利用探测不同波长的红外辐射提高装备的侦察能力。本文讨论了分体式红外双波段成像系统的实现方式及技术途径,分析了分孔径和共孔径系统各自的特点,探讨影响双波段红外图像处理质量的因素及处理方法;最后介绍了双色探测器的发展及应用。     

一种基于图像处理的高精度自动线宽测量方法

文章提出一种高精度的自动线宽测量方法,在PCB板图像中,通过矩形框选定被测量的线路部分,对该矩形框内的图像进行处理,精确定位线路边缘,获取线宽测量结果,经验证在不同倍率情况下测量值稳定在一个像素以内。     

编队电子战信息融合仿真系统设计

根据编队电子战系统信息融合的特点,构造信息融合仿真系统结构,阐述了编队电子战系统多源信息融合方法和策略．提出了信息融合评估的数学模型以及编队电子战系统信息融合需重点解决的问题。     

基于CLAHE和多尺度细节融合的静脉图像增强算法

利用静脉识别原理采集的静脉图像通常模糊不清、难以分辨。传统的CLAHE算法虽然能够提高静脉图像的对比度,但是会丢失图像的一些细节信息。文章提出了一种基于CLAHE和多尺度细节融合的静脉图像增强算法。首先对静脉图像进行ROI提取,采用CLAHE算法增强静脉与手背间的对比度;然后利用多尺度细节融合算法得到静脉图像的细节图,再通过均值滤波滤除细节层中的高频噪声;最后把上面两种方法得到的图像加权叠加得到细节增强后的静脉图像。实验结果表明,该方法在提高静脉图像对比度的同时保留了原图像的细节信息。     

特征增强和双线性特征向量融合的移动端工业货箱文本检测

在实际工业环境下,光线昏暗、文本不规整、设备有限等因素,使得文本检测成为一项具有挑战性的任务。针对此问题,设计了一种基于双线性操作的特征向量融合模块,并联合特征增强与半卷积组成轻量级文本检测网络RGFFD(ResNet18+GhostModule+特征金字塔增强模块(feature pyramid enhancement module,FPEM)+特征融合模块(feature fusion module,FFM)+可微分二值化(differenttiable binarization,DB))。其中,Ghost模块内嵌特征增强模块,提升特征提取能力,双线性特征向量融合模块融合多尺度信息,添加自适应阈值分割算法提高DB模块分割能力。在实际工厂环境下,采用嵌入式设备UP2 board对货箱编号进行文本检测,RGFFD检测速度达到6.5 f/s。同时在公共数据集ICDAR2015、Total-text上检测速度分别达到39.6 f/s和49.6 f/s,在自定义数据集上准确率达到88.9%,检测速度为30.7 f/s。     

Presentation attack detection based on two-stream vision transformers with self-attention fusion

Aiming at the performance degradation of the existing presentation attack detection methods due to the illumination variation, a two-stream vision transformers framework (TSViT) based on transfer learning in two complementary spaces is proposed in this paper. The face images of RGB color space and multi-scale retinex with color restoration (MSRCR) space are fed to TSViT to learn the distinguishing features of presentation attack detection. To effectively fuse features from two sources (RGB color space images and MSRCR images), a feature fusion method based on self-attention is built, which can effectively capture the complementarity of two features. Experiments and analysis on Oulu-NPU, CASIA-MFSD, and Replay-Attack databases show that it outperforms most existing methods in intra-database testing and achieves good generalization performance in cross-database testing.