（英）CCNet:面向多光谱图像的高速船只检测级联卷积神经网络

针对实现遥感图像中船只目标的快速检测,提出了一个采用多光谱图像、基于级联的卷积神经网络(CNN)船只检测方法CCNet。该方法所采用两级级联的CNN依次实现感兴趣区域(ROI)的快速搜索、基于感兴趣区域的船只目标定位和分割。同时,采用含有更多细节信息的多光谱图像作为CCNet的输入,能够提升网络提取特征鲁棒性,从而使得检测更加精确。基于SPOT 6卫星多光谱图像的实验表明：与当前主流的深度学习船只检测方法相比,该方法能够在实现高检测精准度的基础上将检测速度提高5倍以上。     

基于弱显著图的实时热红外图像行人检测

针对现有热红外图像行人检测方法在精度和速度方面存在的问题,提出一种基于弱显著图的实时行人检测方法。该方法以轻量级LFFD（Light and Fast Face Detector）网络为基础,由两级改进网络即SD-LFFD（Saliency Detection-LFFD）和SF-LFFD（Saliency Fusion-LFFD）组成,首先以热红外图像作为输入经SD-LFFD网络产生初步行人检测结果和行人区域弱显著图,接着将该弱显著图与原热红外图像结合“点亮”潜在行人区域并经SF-LFFD网络产生新的行人检测结果,最后将两级改进网络的行人检测结果融合得到最终结果。在数据集CVC-09和CVC-14上实验结果表明,该方法与现有轻量级神经网络相比行人检测的平均精确率有大幅提升,且在有限硬件资源下可实现实时检测。     

基于上下文信息的监控场景行人检测方法

为了提高监控场景中行人检测的准确度,提出了一种基于上下文信息的行人检测方法.该方法将监控场景的上下文信息融入到卷积神经网络中,选择性地学习对行人检测有帮助的上下文信息.首先,利用一个截断的卷积神经网络提取输入图像的多张特征图.然后,将多张特征图通过两个包含上下文信息的卷积层,形成一张掩码图.最后,通过在掩码图上估计行人的边界框,获得行人检测的结果.实验表明,该方法能实现监控场景中准确且快速的行人检测.     

深度学习与图像融合的行人检测算法研究

为解决智能辅助驾驶技术中可见光摄像机受光照和气候影响而导致行人目标识别困难的问题。通过研究图像融合技术,结合深度卷积神经网络,实现并改进了一种道路行人目标检测算法。方法是利用多源传感器图像融合技术,采用可见光相机与红外热成像相机融合的策略,以Faster RCNN算法为基础,从改进网络结构、特征融合、优化模型训练等方面展开研究,对复杂环境下的行人检测与定位跟踪展开研究,提出一种基于图像融合技术和改进的深度卷积神经网络的道路行人目标检测算法。实验结果表明,该算法对复杂气候环境下行人目标检测提高了检测效率和准确率,增加了智能辅助驾驶汽车的安全性。     

Two-stream small-scale pedestrian detection network with feature aggregation for drone-view videos

Detecting small-scale pedestrians in aerial images is a challenging task that can be difficult even for humans. Observing that the single image based method cannot achieve robust performance because of the poor visual cues of small instances. Considering that multiple frames may provide more information to detect such difficult case instead of only single frame, we design a novel video based pedestrian detection method with a two-stream network pipeline to fully utilize the temporal and contextual information of a video. An aggregated feature map is proposed to absorb the spatial and temporal information with the help of spatial and temporal sub-networks. To better capture motion information, a more refined flow net (SPyNet) is adopted instead of a simple flownet. In the spatial stream subnetwork, we modified the backbone network structure by increasing the feature map resolution with relatively larger receptive field to make it suitable for small-scale detection. Experimental results based on drone video datasets demonstrate that our approach improves detection accuracy in the case of small-scale instances and reduces false positive detections. By exploiting the temporal information and aggregating the feature maps, our two-stream method improves the detection performance by 8.48% in mean Average Precision (mAP) from that of the basic single stream R-FCN method, and it outperforms the state-of-the-art method by 3.09% on the Okutama Human-action dataset.

     

基于历史信息的区域卷积神经网络行人检测

为了解决卷积神经网络在进行连续行人检测时, 检测行人速度较慢, 达不到实时性要求的问题, 采用基于历史信息的区域卷积神经网络行人检测算法, 利用前一幅图像中的检测结果对当前图像的检测过程进行优化, 将前一帧的检测结果作为对当前帧提取推荐区域的参考信息, 并使用当前帧与前一帧的灰度值差异图对当前图像的卷积特征进行过滤, 以缩小滑动窗口检测时的搜索区域。在加州理工学院行人检测数据集上进行了检测实验。结果表明, 结合历史信息的算法与先进的算法相比检测速度提升了2.5倍, 同时检测准确率提升了1.5%。该算法实现了实时行人检测, 设计的网络能有效检测小目标行人。     

基于Word Embedding的遥感影像检测分割

遥感影像检测分割技术通常需提取影像特征并通过深度学习算法挖掘影像的深层特征来实现.然而传统特征（如颜色特征、纹理特征、空间关系特征等）不能充分描述影像语义信息,而单一结构或串联算法无法充分挖掘影像的深层特征和上下文语义信息.针对上述问题,本文通过词嵌入将空间关系特征映射成实数密集向量,与颜色、纹理特征的结合.其次,本文构建基于注意力机制下图卷积网络和独立循环神经网络的遥感影像检测分割并联算法（Attention Graph Convolution Networks and Independently Recurrent Neural Network,ATGIR）.该算法首先通过注意力机制对结合后的特征进行概率权重分配;然后利用图卷积网络（GCNs）算法对高权重的特征进一步挖掘并生成方向标签,同时使用独立循环神经网络（IndRNN）算法挖掘影像特征中的上下文信息,最后用Sigmoid分类器完成影像检测分割任务.以胡杨林遥感影像检测分割任务为例,我们验证了提出的特征提取方法和ATGIR算法能有效提升胡杨林检测分割任务的性能.     

基于U2-Net和VGG16的天然气泄露检测

目前在深度学习领域很少以天然气泄露图像为数据进行研究,本文使用甲烷红外图像训练的卷积神经网络(VGG16)来实现泄露检测。另外,针对泄露的甲烷气体与背景图像存在相似性的问题,使用U²-Net图像分割网络代替背景建模方法来提取泄露气体区域。通过迁移VGG16网络模型结构和卷积层参数,在卷积层和激励层之间加入BN层以提高训练速度,将最后一层池化层替换为基于最大池化算法的动态自适应池化方法以提高检测精度。将改进的VGG16神经网络对分割的红外图像进行训练并与其他卷积神经网络进行对比,使用准确率,精准率,召回率和F1-score来对模型进行综合评价,其表现效果最好。与现有的检测方法进行对比,所提出的检测方法准确率更高。该检测方法能够实现高精度泄漏检测,满足天然气泄露检测准确性的要求,且模型具有较好的泛化能力和鲁棒性。     

联合多流融合和多尺度学习的卷积神经网络遥感图像融合方法

为尽可能保持原始低分辨率多光谱(LRMS)图像光谱信息的同时,显著提高融合后的多光谱图像的空间分辨率,该文提出一种联合多流融合和多尺度学习的卷积神经网络遥感图融合方法.首先将原始MS图像输入频谱特征提取子网得到其光谱特征,然后分别将通过梯度算子处理全色图像得到的梯度信息和通过卷积后的全色图像与得到的光谱特征图在通道上拼...     

基于YOLO的轻量红外图像行人检测方法

红外图像中行人的快速检测一直是计算机视觉领域的热点和难点。针对红外图像行人目标检测算法检测速度和检测精度难以平衡,算法模型体积较大,在中低性能设备中难以部署和实时运行的问题,提出了一种基于YOLO算法的轻量红外图像行人检测方法。在分析了MobileNet v3等轻量网络在YOLO v3算法上的性能和特点之后,该方法提出了引入注意力机制的轻量特征提取网络(CSPmini a)、特征融合模块和解耦检测端分类回归结构三种改进措施,在满足网络模型轻量的情况下保证了一定的检测精度。实验表明,该方法有效的实现了红外图像行人目标检测的准确性和快速性。     

基于神经网络的典型地物的偏振多光谱图像分类（特邀）

相比传统的多光谱成像探测,偏振多光谱成像探测方法可以探测目标表面的粗糙度、含水量等更多信息,给目标检测带来了很大便利,但目前主要用于目标探测,尚未广泛应用于目标分类。BP神经网络是目前常用的一种典型神经网络,可以建立从端到端的映射,在训练样本集足够大的前提下,训练完毕且效果良好的神经网络是一种高效、精确、快速的工具。首先,利用基于旋转偏振片和滤波片的偏振光谱成像探测系统获取了典型地物的偏振多光谱图像,对图像进行了预处理,建立了数据集;其次,在该数据集上进行了神经网络的训练,训练后的神经网络可以处理未知的偏振多光谱图像,并实现了对几种典型地物的分类;最后,对神经网络分类的效果进行了评价,并与其他几种典型分类方法的效果进行了对比,发现神经网络方法具有更好的分类精度和效果,相比典型的最大似然分类算法,其总体分类精度可从91.7%提升至94.2%,Kappa系数可从0.851提升至0.898。研究结果表明:基于神经网络的偏振光谱图像分类方法对于改进和优化现有的偏振多光谱图像数据处理方法具有一定的研究意义。     

A new deep spatial transformer convolutional neural network for image saliency detection

In this paper we propose a novel deep spatial transformer convolutional neural network (Spatial Net) framework for the detection of salient and abnormal areas in images. The proposed method is general and has three main parts: (1) context information in the image is captured by using convolutional neural networks (CNN) to automatically learn high-level features; (2) to better adapt the CNN model to the saliency task, we redesign the feature sub-network structure to output a 6-dimensional transformation matrix for affine transformation based on the spatial transformer network. Several local features are extracted, which can effectively capture edge pixels in the salient area, meanwhile embedded into the above model to reduce the impact of highlighting background regions; (3) finally, areas of interest are detected by means of the linear combination of global and local feature information. Experimental results demonstrate that Spatial Nets obtain superior detection performance over state-of-the-art algorithms on two popular datasets, requiring less memory and computation to achieve high performance.     

基于改进Faster R-CNN的车辆乘员数量检测方法

针对现有以雷达技术和红外热成像技术为代表的HOV（High occupancy vehiclelane）车道车辆乘员数量检测方法可靠性差、准确率低等问题，提出一种基于多光谱红外图像与改进Faster R-CNN（Region-Convolutional Neural Networks）的车辆乘员数量检测方法。通过多光谱红外成像系统获得汽车内部空间图像，结合Faster R-CNN深度学习算法实现乘员数量检测，通过采用全卷积网络结构、多尺度特征预测、使用ROI-Align代替ROI-Pooling等方式增强网络的泛化能力。通过对样据进行K-means聚类得到目标框长宽几何比例先验分布，提高区域生成（region proposal network，RPN）网络训练速度和位置回归准确性。测试结果表明，获得的汽车内部空间图像较为清晰，算法可以实现对乘员数量的检测。经过改进，网络的泛化能力得到增强，单乘员检测的准确率达到88.6%，相比于改进前提高了13.8%，能够满足行业规定大于80%的要求。     

红外与可见光图像注意力生成对抗融合方法研究

目前,基于深度学习的融合方法依赖卷积核提取局部特征,而单尺度网络、卷积核大小以及网络深度的限制无法满足图像的多尺度与全局特性.为此,本文提出了红外与可见光图像注意力生成对抗融合方法.该方法采用编码器和解码器构成的生成器以及两个判别器.在编码器中设计了多尺度模块与通道自注意力机制,可以有效提取多尺度特征,并建立特征通道长...     

Color correction and restoration based on multi-scale recursive network for underwater optical image

Underwater image processing has played an important role in various fields such as submarine terrain scanning, submarine communication cable laying, underwater vehicles, underwater search and rescue. However, there are many difficulties in the process of acquiring underwater images. Specifically, the water body will selectively absorb part of the light when light travels through the water, resulting in color degradation of underwater images. At the same time, due to the influence of floating substances in the water, the light has a certain degree of scattering, which will bring serious problems such as blurred details and low contrast to underwater images. Therefore, using image processing technology to restore the real appearance of underwater images has a high practical value. In order to solve the above problems, we combine the color correction method with the deblurring network to improve the quality of underwater images in this paper. Firstly, aiming at the problem of insufficient number and diversity of underwater image samples, a network combined with depth image reconstruction and underwater image generation is proposed to simulate underwater images based on the style transfer method. Secondly, for the problem of color distortion, we propose a dynamic threshold color correction method based on image global information combined with the loss law of light propagation in water. Finally, in order to solve the problem of image blurring caused by scattering and further improve the overall image clarity, the color-corrected image is reconstructed by a multi-scale recursive convolutional neural network. Experiment results show that we can obtain images closer to underwater style with shorter training time. Compared with several latest underwater image processing methods, the proposed method has obvious advantages in multiple underwater scenes. Simultaneously, we can restore the color information, remove blurring and boost detail for underwater images.     

基于卷积神经网络的超声红外热图像分类

在超声红外热像技术应用中,从红外热图像来判断被测对象是否含有裂纹,通常需要先基于人工经验,从红外热图像中提取特征再采用某种模式识别方法进行分类,裂纹的识别与定位过程繁琐且识别率较低。为此,提出一种基于卷积神经网络技术的超声红外热图像裂纹检测与识别方法,其特点是可以直接从超声红外图像中学习特征进而实现是否含有裂纹红外热图像的分类。通过实验得到的含裂纹和不含裂纹金属平板试件的红外热图像,建立卷积神经网络模型对图像中是否含有裂纹进行分类,研究结果表明,参数优化后的卷积神经网络模型对超声红外热图像的有无裂纹分类准确率达到98.7%。     

Detection of GAN generated image using color gradient representation

With the development of generative adversarial network (GANs) technology, the technology of GAN generates images has evolved dramatically. Distinguishing these GAN generated images is challenging for the human eye. Moreover, the GAN generated fake images may cause some behaviors that endanger society and bring great security problems to society. Research on GAN generated image detection is still in the exploratory stage and many challenges remain. Motivated by the above problem, we propose a novel GAN image detection method based on color gradient analysis. We consider the difference in color information between real images and GAN generated images in multiple color spaces, and combined the gradient information and the directional texture information of the generated images to extract the gradient texture features for GAN generated images detection. Experimental results on PGGAN and StyleGAN2 datasets demonstrate that the proposed method achieves good performance, and is robust to other various perturbation attacks.     

基于CNN的金属疲劳裂纹超声红外热像检测与识别方法研究

传统超声红外热像检测与识别金属疲劳裂纹主要是通过图像处理算法提取红外热图像的相关热特征,并与裂纹特征进行匹配,其过程过于繁琐,识别率较低且需要人工筛选有效特征。结合主动红外热成像技术以及卷积神经网络（Convolutional Neural Network,CNN）在金属结构无损检测与缺陷自动识别中的优势,提出了一种基于CNN的金属疲劳裂纹超声红外热像检测与识别方法。通过超声红外热成像装置对实验对象（文中为金属平板试件）进行检测,获取红外热图像并制作图像数据集。运用设计的卷积神经网络对不同尺寸裂纹的超声红外热图像进行特征提取与识别分类。此外,对所提出的方法与两种常见图像分类网络模型以及支持向量机的分类结果进行对比。实验结果表明,设计的卷积神经网络在该数据集上识别分类准确率为100%,优于其他网络模型和支持向量机的识别分类,可以有效检测与识别金属疲劳裂纹。     

一种微光与红外图像彩色融合方法

微光夜视仪和红外热像仪这两种图像传感器互补的成像特性可以使它们在几乎任何条件渊昼/夜/烟/雾）下观察场景。针对微光与红外图像,提出了一种彩色融合算法,可以使融合图像有相对自然真实的颜色感觉。首先用中心-环绕拮抗彩色融合算法产生彩色源图像,然后在YCbCr 颜色空间中让源图像的直方图与参考图像的相匹配。为了增强融合图像的对比度,可以先用灰度融合图像代替亮度分量,然后进行直方图匹配。仿真结果表明文中提出的方法可以使融合图像接近自然真实的颜色感觉,易于分辨识别目标,从而提高观察者或机器视觉系统的工作效率,增强对总体形势的意识能力。     

Using genetic algorithms and neural networks for surface land minedetection

Knowledge based techniques have been used to automatically detect surface land mines present in thermal and multispectral images. Polarization-sensitive infrared sensing is used to highlight the polarization signature of man-made targets such as land mines over natural features in the image. Processing the thermal polarization images using a background-discrimination algorithm, we were able to successfully identify eight of the nine man-made targets, three of which were mines, with only three false targets. A digital camera is used to collect a number of multispectral bands of the test mine area containing three surface land mines with natural and man-made clutter. Using a supervised and unsupervised neural network technique on the textural and spectral characteristics of selected multispectral bands (using a genetic algorithm tool), we successfully identified the three surface mines but obtained numerous false targets with varying degrees of accuracy. Finally, to further improve our detection of land mines, we use a fuzzy rule-based fusion technique on the processed polarization resolved image together with the output results of the two best classifiers. Fuzzy rule-based fusion identified the locations of all three land mines and reduced the number of false alarms from seven (as obtained by the polarization resolved image) to two. Additional experiments on several other images have also produced favorable results at this early stage in testing the algorithm and comparing it with an existing commercial system