基于单列深度时空卷积神经网络的人群计数

突发性人群聚集会给人们的人身安全带来隐患,因此,对高风险区域进行有效的人群计数具有重要意义.针对多列神经网络结构臃肿、冗余信息多及耗时长等问题,提出了一种基于单列深度时空卷积神经网络的人群计数模型,并对模型进行改进,以满足视频图像计数的需要.首先,在全卷积神经网络(FCN)中加入空洞卷积和跳级连接特征融合,以提高网络提...     

基于VDNet卷积神经网络的羊群计数

为了避免传统羊群计数任务中,羊只之间相互遮挡带来的干扰,提高羊群计数的准确度,采用了视觉几何群(VGG-16)与空洞卷积(DC)相结合的VDNet神经网络羊群计数方法.该方法在网络前端采用去除了全连接层的VGG-16网络提取2-D特征,后端采用6层具有不同空洞率的DC提取更多的高级特征;DC在保持分辨率不变的同时扩大了...     

基于多模型深度卷积网络融合的人群计数算法

为了避免景深和遮挡的干扰, 提高人群计数的准确性, 采用了LeNet-5, AlexNet和VGG-16 3种模型, 提取图像中不同景深目标的特性, 调整上述模型的卷积核尺寸和网络结构, 并进行了模型融合。构造出一种基于多模型融合的深度卷积神经网络结构, 网络最后两层采用卷积核大小为1×1的卷积层取代传统的全连接层, 对提取的特征图进行信息整合并输出密度图, 极大地降低了网络参量且取得了一定提升的数据, 兼顾了算法效率和精度, 进行了理论分析和实验验证。结果表明, 在公开人群计数数据集shanghaitech两个子集和UCF_CC_50子集上, 本文中计数方法的平均绝对误差和均方误差分别是97.99和158.02, 23.36和41.86, 354.27和491.68, 取得比现有传统人群计数方法更好的性能; 通过迁移实验证明所提出的人群计数模型具有良好的泛化能力。该研究对人群计数精度的提高是有帮助的。     

基于单列特征融合卷积神经网络的人群计数技术

为了提高人群计数精度,设计一种基于单列特征融合卷积神经网络的人群计数技术。该网络包含前端网络、中端网络以及后端网络三个部分。前端网络采用VGG16网络的前十层并使用特征金字塔池化来融合基础特征;中端网络采用小尺寸卷积层堆叠以及特征融合的方法来提取多尺度特征;后端网络采用不同空洞率的空洞卷积层来提高感受野,从而得到人群密度图。实验在ShanghaiTech数据集上进行,结果表明,该网络在人群计数上具有良好的准确性与鲁棒性。     

基于轻量级神经网络的人群计数模型设计

针对传统的卷积神经网络应用在人群计数过程中的参数众多、计算消耗大,难以在轻量级平台上实现的问题,提出一种基于轻量级神经网络的人群计数模型。模型以人群的特征提取为导向,对VGG-16网络重新部署。利用GPU完成训练,在容器化开发环境下,利用深度学习的方法进行压缩量化编码,生成轻量级神经网络,提高资源利用效率。将轻量级网络模型部署到FPGA上,完成软硬件协同推断。在Mall Dataset数据集支持下进行系统验证,实验结果表明,该系统轻量化后的均方误差可达到18.4,能效比由在PC上的0.35提高到在FPGA上的1.13,实现了轻量级神经网络的准确性及低功耗性。     

基于全卷积神经网络的非对称并行语义分割模型

针对RGB图像具有丰富的色彩细节特征,红外图像对目标轮廓、尺寸、边界等外形特征有较高敏感度的特点,提出了一种非对称并行语义分割模型APFCN（Asymmetric Parallelism Fully Convolutional Networks）.APFCN上路设计了一个卷积核尺寸非统一的五层空洞卷积网络来提取红外图像目标高层轮廓特征;下路沿用卷积加池化网络提取RGB图像三个尺度上的细节特征;后端将红外图像高层特征与RGB图像三个尺度的细节特征进行融合,并将4倍上采样后的融合特征作为语义分割输出.结果表明,APFCN在像素精度和交并比等方面均优于FCN（输入为RGB图像或红外图像）,适用于背景一致下地面目标的语义分割任务.     

基于深度卷积神经网络的红外场景理解算法

采用深度学习的方法实现红外图像场景语义理解.首先,建立含有4类别前景目标和1个类别背景的用于语义分割研究的红外图像数据集.其次,以深度卷积神经网络为基础,结合条件随机场后处理优化模型,搭建端到端的红外语义分割算法框架并进行训练.最后,在可见光和红外测试集上对算法框架的输出结果进行评估分析.实验结果表明,采用深度学习的方法对红外图像进行语义分割能实现图像的像素级分类,并获得较高的预测精度.从而可以获得红外图像中景物的形状、种类、位置分布等信息,实现红外场景的语义理解.     

基于卷积神经网络的场景图像文本定位研究

针对由于自然场景的复杂性,从自然场景图像中提取出文本信息较困难的问题,文中提出了一种基于深度学习卷积神经网络的文本定位算法。通过对场景图像进行预处理得到候选文本区域,在此基础上结合深度学习中的卷积神经网络来自动提取文本特征进行进一步的定位。通过实验验证,定位的准确率可达86%,综合性能较好。     

基于深度对抗式网络的人群计数方法

对人群密度大、遮挡严重以及分不均等因素造成人群计数困难的问题,本文提出了一 种深度对抗式网络的人群计数模型, 该模型主要分为生成器网络和判别器网络。首先利用具有良好的迁移能力和特征提取能力VG G16的前十层作为前端模块,以初 步提取特征;然后,为应对人群遮挡严重以及分布不均的情况,使用我们设计的深度扩张卷 积模块来聚合人群信息,并将浅层与 深层人头特征进行融合,以增强网络对人群的适应能力。并在此过程中,使用扩张卷积代替 传统的卷积层,在不损失图像分辨率 的情况下对图像进行特征提取;最后,将密度图与标签密度图输入判别器网络进行判别,目 的是生成与标签密度图更为相似的密 度图,提高人群计数的准确性。实验结果表明,与其他方法相比,本文方法无论是在客观指 标或者主管视觉方面,均具有较好的效果。     

CDADNet: Context-guided dense attentional dilated network for crowd counting

Crowd counting is a conspicuous task in computer vision owing to scale variations, perspective distortions, and complex backgrounds. Existing research usually adopts the dilated convolution network to enlarge the receptive fields to solve the problem of scale variations. However, these methods easily bring background information into the large receptive fields to generate poor quality density maps. To address this problem, we propose a novel backbone called Context-guided Dense Attentional Dilated Network (CDADNet). CDADNet contains three components: an attentional module, a context-guided module and a dense attentional dilated module. The attentional module is used to provide attention maps which can remove background information, while the context-guided module is proposed to extract multi-scale contextual information. Moreover, the dense attentional dilated module aims to generate high-granularity density maps and the cascaded strategy is used to preserve information from changing scales. To verify the feasibility of our method, we compare it to the existing approaches on five crowd counting datasets (ShanghaiTech (Part_A and Part_B), WorldEXPO’10, UCSD, UCF_CC_50). The comparison results demonstrate that CDADNet is effective and robust for various scenes.     

Dense crowd counting from still images with convolutional neural networks

For reasons of public security, modeling large crowd distributions for counting or density estimation has attracted significant research interests in recent years. Existing crowd counting algorithms rely on predefined features and regression to estimate the crowd size. However, most of them are constrained by such limitations: (1) they can handle crowds with a few tens individuals, but for crowds of hundreds or thousands, they can only be used to estimate the crowd density rather than the crowd count; (2) they usually rely on temporal sequence in crowd videos which is not applicable to still images. Addressing these problems, in this paper, we investigate the use of a deep-learning approach to estimate the number of individuals presented in a mid-level or high-level crowd visible in a single image. Firstly, a ConvNet structure is used to extract crowd features. Then two supervisory signals, i.e., crowd count and crowd density, are employed to learn crowd features and estimate the specific counting. We test our approach on a dataset containing 107 crowd images with 45,000 annotated humans inside, and each with head counts ranging from 58 to 2201. The efficacy of the proposed approach is demonstrated in extensive experiments by quantifying the counting performance through multiple evaluation criteria.     

Study on traffic scene semantic segmentation method based on convolutional neural network

In order to improve the semantic segmentation accuracy of traffic scene,a segmentation method was proposed based on RGB-D image and convolutional neural network.Firstly,on the basis of semi-global stereo matching algorithm,the disparity map was obtained,and the sample library was established by fusing the disparity map D and RGB image into the four-channel RGB-D image.Then,with two different structures,the networks were trained by using two different learning rate adjustment strategy respectively.Finally,the traffic scene semantic segmentation test was carried out with RGB-D image as the input,and the results were compared with the segmentation method based on RGB image.The experimental results show that the proposed traffic scene segmentation algorithm based on RGB-D image can achieve higher semantic segmentation accuracy than that based on RGB image.     

基于卷积神经网络的手势识别

手势识别是人机交互,智能语义识别和远程人机 交流领域的热门研究课题。目前基于 视觉的手势识别问题仍是研究的难点,在多变背景下的手势姿态识别仍然存在较大问题。近 年来,随着深度神经网络技术的快速发展,利用网络自主学习的方法来提取手势姿态有关特 征得到了广泛关注。由于卷积神经网络具有较强的学习能力和个体特征的表达能力,本文针 对传统手势识别算法精度低,鲁棒性差的问题,提出了基于卷积神经网络的TensorFlow框架 下加入扁平卷积模块的FD-CNN网络手势识别算法。在预处理数据集后,基于FD-CNN网络的 手 势识别方法可以直接将预处理后的图像输入网络进行训练,最终输出测试结果的识别精度为 99.0％。与传统方法和经典卷积神经网络方法相比,本文方法提高了 网 络系统对样本数据的多样性和复杂性的有效识别,具有较高的识别率和较好的鲁棒性效果。     

Attention guided feature pyramid network for crowd counting

Crowd counting has become a hot topic because of its wide applications in video surveillance and public security. However, one main problem of the deep learning methods for crowd counting is that the location information about the crowd is degraded irreversibly due to the spatial down-sampling of convolutional neural networks, which degrades the quality of generated density maps. To remedy the above problem, we propose an attention guided feature pyramid network (AG-FPN) for crowd counting, which can adaptively generate a high-quality density map with accurate spatial locations by combining the high- and low-level features. An attention block is added to each encoder layer to further emphasize the crowd regions and suppress the background clutters in feature extraction. Experimental results on the ShanghaiTech, UCF_CC_50, WorldExpo’10 and UCF-QNRF datasets demonstrate the superiority of the proposed method over state-of-the-art approaches.     

Incentive mechanism based on auction model for mobile crowd sensing network

The selfishness and uncertainty of user behaviors in the mobile crowd sensing network make them unwilling to participate in sensing activities,which may result to a lower sensing task completion rate.To deal with these problems,an incentive mechanism based on auction model was proposed.In order to maximize the utility of each user,the proposed incentive method based on reverse auction (IMRA) leveraged a task-centric method to choose winners,and payed them according to a critical-price strategy.Furthermore,the proposed user-bidirectional interaction incentive mechanism (UBIM) helped drop-out users (buyers) to transfer their unfinished tasks to new users.Simulation results show that,compared with TRAC and IMC-SS,IMRA can achieve a better performance in terms of average user utility and tasks coverage ratio,and the task completion ratio can also be improved by UBIM.     

Multi-Scale and spatial position-based channel attention network for crowd counting

Crowd counting algorithms have recently incorporated attention mechanisms into convolutional neural networks (CNNs) to achieve significant progress. The channel attention model (CAM), as a popular attention mechanism, calculates a set of probability weights to select important channel-wise feature responses. However, most CAMs roughly assign a weight to the entire channel-wise map, which makes useful and useless information being treat indiscriminately, thereby limiting the representational capacity of networks. In this paper, we propose a multi-scale and spatial position-based channel attention network (MS-SPCANet), which integrates spatial position-based channel attention models (SPCAMs) with multiple scales into a CNN. SPCAM assigns different channel attention weights to different positions of channel-wise maps to capture more informative features. Furthermore, an adaptive loss, which uses adaptive coefficients to combine density map loss and headcount loss, is constructed to improve network performance in sparse crowd scenes. Experimental results on four public datasets verify the superiority of the scheme.     

基于卷积神经网络的网络隐写分析方法研究

针对现有网络隐写分析算法特征提取难度大、算法适用范围单一的问题,文章提出了一种基于卷积神经网络的网络隐写分析方法。对网络数据流进行预处理,将所有数据包处理成大小相同的矩阵,最大限度地保留数据特征完整性;使用异构卷积进行特征提取,减少模型计算量及参数数量,加快模型收敛速度;取消池化层,提高模型训练效率。与传统网络隐写分析方法相比,模型能够自动提取数据特征,识别多种网络隐写算法。