DL-HAR: Deep Learning-Based Human Activity Recognition Framework for Edge Computing

Human activity recognition is commonly used in several Internet of Things applications to recognize different contexts and respond to them. Deep learning has gained momentum for identifying activities through sensors, smartphones or even surveillance cameras. However, it is often difficult to train deep learning models on constrained IoT devices. The focus of this paper is to propose an alternative model by constructing a Deep Learning-based Human Activity Recognition framework for edge computing, which we call DL-HAR. The goal of this framework is to exploit the capabilities of cloud computing to train a deep learning model and deploy it on lesspowerful edge devices for recognition. The idea is to conduct the training of the model in the Cloud and distribute it to the edge nodes. We demonstrate how the DL-HAR can perform human activity recognition at the edge while improving efficiency and accuracy. In order to evaluate the proposed framework, we conducted a comprehensive set of experiments to validate the applicability of DL-HAR. Experimental results on the benchmark dataset show a significant increase in performance compared with the state-of-the-art models.     

Hidden Two-Stream Collaborative Learning Network for Action Recognition

The two-stream convolutional neural network exhibits excellent performance in the video action recognition. The crux of the matter is to use the frames already clipped by the videos and the optical flow images pre-extracted by the frames, to train a model each, and to finally integrate the outputs of the two models. Nevertheless, the reliance on the pre-extraction of the optical flow impedes the efficiency of action recognition, and the temporal and the spatial streams are just simply fused at the ends, with one stream failing and the other stream succeeding. We propose a novel hidden twostream collaborative (HTSC) learning network that masks the steps of extracting the optical flow in the network and greatly speeds up the action recognition. Based on the two-stream method, the two-stream collaborative learning model captures the interaction of the temporal and spatial features to greatly enhance the accuracy of recognition. Our proposed method is highly capable of achieving the balance of efficiency and precision on large-scale video action recognition datasets.     

Using BlazePose on Spatial Temporal Graph Convolutional Networks for Action Recognition

The ever-growing available visual data (i.e., uploaded videos and pictures by internet users) has attracted the research community's attention in the computer vision field. Therefore, finding efficient solutions to extract knowledge from these sources is imperative. Recently, the BlazePose system has been released for skeleton extraction from images oriented to mobile devices. With this skeleton graph representation in place, a Spatial-Temporal Graph Convolutional Network can be implemented to predict the action. We hypothesize that just by changing the skeleton input data for a different set of joints that offers more information about the action of interest, it is possible to increase the performance of the Spatial-Temporal Graph Convolutional Network for HAR tasks. Hence, in this study, we present the first implementation of the BlazePose skeleton topology upon this architecture for action recognition. Moreover, we propose the Enhanced-BlazePose topology that can achieve better results than its predecessor. Additionally, we propose different skeleton detection thresholds that can improve the accuracy performance even further. We reached a top-1 accuracy performance of 40.1% on the Kinetics dataset. For the NTU-RGB+D dataset, we achieved 87.59% and 92.1% accuracy for Cross-Subject and Cross-View evaluation criteria, respectively.     

Adversarial Attacks on License Plate Recognition Systems

The license plate recognition system (LPRS) has been widely adopted in daily life due to its efficiency and high accuracy. Deep neural networks are commonly used in the LPRS to improve the recognition accuracy. However, researchers have found that deep neural networks have their own security problems that may lead to unexpected results. Specifically, they can be easily attacked by the adversarial examples that are generated by adding small perturbations to the original images, resulting in incorrect license plate recognition. There are some classic methods to generate adversarial examples, but they cannot be adopted on LPRS directly. In this paper, we modify some classic methods to generate adversarial examples that could mislead the LPRS. We conduct extensive evaluations on the HyperLPR system and the results show that the system could be easily attacked by such adversarial examples. In addition, we show that the generated images could also attack the black-box systems; we show some examples that the Baidu LPR system also makes incorrect recognitions. We hope this paper could help improve the LPRS by realizing the existence of such adversarial attacks.     

Human Action Recognition Based on Supervised Class-Specific Dictionary Learning with Deep Convolutional Neural Network Features

Human action recognition under complex environment is a challenging work. Recently, sparse representation has achieved excellent results of dealing with human action recognition problem under different conditions. The main idea of sparse representation classification is to construct a general classification scheme where the training samples of each class can be considered as the dictionary to express the query class, and the minimal reconstruction error indicates its corresponding class. However, how to learn a discriminative dictionary is still a difficult work. In this work, we make two contributions. First, we build a new and robust human action recognition framework by combining one modified sparse classification model and deep convolutional neural network (CNN) features. Secondly, we construct a novel classification model which consists of the representation-constrained term and the coefficients incoherence term. Experimental results on benchmark datasets show that our modified model can obtain competitive results in comparison to other state-of-the-art models.     

Dynamic Hand Gesture Recognition Using 3D-CNN and LSTM Networks

Recognition of dynamic hand gestures in real-time is a difficult task because the system can never know when or from where the gesture starts and ends in a video stream. Many researchers have been working on vision-based gesture recognition due to its various applications. This paper proposes a deep learning architecture based on the combination of a 3D Convolutional Neural Network (3D-CNN) and a Long Short-Term Memory (LSTM) network. The proposed architecture extracts spatial-temporal information from video sequences input while avoiding extensive computation. The 3D-CNN is used for the extraction of spectral and spatial features which are then given to the LSTM network through which classification is carried out. The proposed model is a light-weight architecture with only 3.7 million training parameters. The model has been evaluated on 15 classes from the 20BN-jester dataset available publicly. The model was trained on 2000 video-clips per class which were separated into 80% training and 20% validation sets. An accuracy of 99% and 97% was achieved on training and testing data, respectively. We further show that the combination of 3D-CNN with LSTM gives superior results as compared to MobileNetv2 + LSTM.     

基于多算法融合的跌倒行为识别

提出一种多算法融合的跌倒行为识别算法.首先,针对人体目标的特征对YOLOv3 tiny检测算法进行改进,有效框定人体动态目标区域,提取出目标前景;在此基础上利用AlphaPose姿态识别框架识别出人体骨骼关键点,得到人体主要关节图;最后以人体关节图坐标信息为输入,通过时空图卷积神经网络对跌倒等动作进行检测识别,满足对不...     

基于三维钣金模型的加工特征识别

研究了钣金数控折弯加工特征信息的识别方法.可将三维CAD模型映射表示为由特征节点构成的网络图,这一方法可以对钣金零件的折弯加工工序模拟、折弯模具以及折弯夹具进行有效分析.     

目标地震动信号的特征提取及识别研究

地面目标的地震动信号是目标识别的关键,本文研究了机动目标地震动特性,总结出目标的地震动信号的特征提取规律,并将神经网络方法用于目标的地震动信号的分类识别中。给出了识别结构及改进的BP算法,并将改进的BP算法用于实际目标的地震动信号的分类识别,得到令人满意的结果。     

基于三维模型的多姿态人脸识别

提出了一种利用三维人脸模型匹配二维人脸图像的分层人脸识别方法和基于模糊数学的人脸姿态角度估计算法.对多姿态二维图像进行姿态空间划分,利用主成分分析方法(PCA)形成多姿态特征脸.识别过程首先估计测试图像姿态和模糊姿态角,在估计的姿态空间内采用基于PCA的方法进行第一层识别得到候选个体,然后利用候选个体的三维模型结合模糊姿态角产生虚拟图像,利用相关进行第二层识别.实验结果表明,该方法对姿态的变化有较好的鲁棒性.     

基于局部纹理特征的三维掌纹识别研究

近年来,自动掌纹识别方法的研究吸引了越来越多的关注,已有的工作主要集中于二维掌纹识别。然而,二维掌纹图像存在着易伪造、抗噪能力差的缺陷,实际应用中会带来潜在的安全隐患。因此,三维掌纹识别被视为一种可行的解决方案来进一步提高识别的性能。基于局部纹理特征,本文提出一种有效的三维掌纹识别方法。该方法首先利用形状指数来描述三维掌纹的局部几何特征,接着提取形状指数图像的局部三值模式以及Gabor小波特征,最后在匹配分数层次上对这两种互补的局部纹理特征进行融合,随后的实验证明了融合特征较单独特征要好。在香港理工三维掌纹数据库上的实验结果表明,本文方法在识别率上要优于目前流行的其它三维掌纹识别方法,从而验证了本文方法的有效性。     

基于视觉感知的机器人工件识别方法研究

目的 解决定制化木门尺寸规格不统一、表面纹理多样而导致的堆垛分类困难、搬运效率低下等问题。方法 提出采用深度学习方法进行定制式木门工件检测,以YOLOV3网络为基本框架开展机器人工件识别方法研究。首先,通过图像数据增强和预处理,扩充定制式木门数据;然后,进行YOLO V3损失函数改进,并根据木门特征进行定制式木门数据集锚框尺度的重新聚类;最后,应用空间金字塔池化层进行YOLO V3中特征金字塔网络改进,并通过随机选取的测试集验证本文方法的有效性。结果 测试数据集的平均检测准确率均值达到98.05%,检测每张图片的时间为137 ms。结论 研究表明,本文方法能够满足木门生产线对准确率和实时性的要求,可大大提高定制化木门转线及堆垛效率。     

An Improved Deep Fusion CNN for Image Recognition

With the development of Deep Convolutional Neural Networks (DCNNs), the extracted features for image recognition tasks have shifted from low-level features to the high-level semantic features of DCNNs. Previous studies have shown that the deeper the network is, the more abstract the features are. However, the recognition ability of deep features would be limited by insufficient training samples. To address this problem, this paper derives an improved Deep Fusion Convolutional Neural Network (DF-Net) which can make full use of the differences and complementarities during network learning and enhance feature expression under the condition of limited datasets. Specifically, DF-Net organizes two identical subnets to extract features from the input image in parallel, and then a well-designed fusion module is introduced to the deep layer of DF-Net to fuse the subnet’s features in multi-scale. Thus, the more complex mappings are created and the more abundant and accurate fusion features can be extracted to improve recognition accuracy. Furthermore, a corresponding training strategy is also proposed to speed up the convergence and reduce the computation overhead of network training. Finally, DF-Nets based on the well-known ResNet, DenseNet and MobileNetV2 are evaluated on CIFAR100, Stanford Dogs, and UECFOOD-100. Theoretical analysis and experimental results strongly demonstrate that DF-Net enhances the performance of DCNNs and increases the accuracy of image recognition.     

基于神经网络的货物列车超偏载车号自动识别系统

基于一种基于人工神经网络的货物列车超、偏载车号自动识别系统、重点讨论了车号区域定位分割方法、智能字符切割技术,具有选择注意参数的模板匹配神经网络及采用多级混合集成分类器字符识别方案。实际应用表明,该系统性能良好,工作稳定,车号区域定位正确率大于９９．８％,字符识别正确率大于９６．５％。     

基于结构照明和BP神经网络的三维物体识别

提出一种具有旋转不变性的三维物体识别的新方法,该方法通过结构光照明的方法,使物体的高度分布以变形条纹的形式编码于二维强度图中,由于条纹图包含有物体的高度分布信息,因此对条纹的相关识别具有本征三维识别的特点.旋转不变性是通过BP神经网络实现的.计算机模拟结果表明,用二维强度像的基频分量做训练样本设计BP神经网络,选择训练样本和隐藏层神经元的数目,基于结构光编码的BP神经网络对三维物体具有良好的旋转不变识别效果.     

A Framework of Deep Optimal Features Selection for Apple Leaf Diseases Recognition

Identifying fruit disease manually is time-consuming, expert-required, and expensive; thus, a computer-based automated system is widely required. Fruit diseases affect not only the quality but also the quantity. As a result, it is possible to detect the disease early on and cure the fruits using computer-based techniques. However, computer-based methods face several challenges, including low contrast, a lack of dataset for training a model, and inappropriate feature extraction for final classification. In this paper, we proposed an automated framework for detecting apple fruit leaf diseases using CNN and a hybrid optimization algorithm. Data augmentation is performed initially to balance the selected apple dataset. After that, two pre-trained deep models are fine-tuning and trained using transfer learning. Then, a fusion technique is proposed named Parallel Correlation Threshold (PCT). The fused feature vector is optimized in the next step using a hybrid optimization algorithm. The selected features are finally classified using machine learning algorithms. Four different experiments have been carried out on the augmented Plant Village dataset and yielded the best accuracy of 99.8%. The accuracy of the proposed framework is also compared to that of several neural nets, and it outperforms them all.     

基于模板变形的三维人体头面部测点识别

目的人体测量项目是由测点定义的,在三维非接触人体测量中,测点识别是人体测量的关键。为快速有效地实现头面部测点的识别,本文研究提出了一种基于模板变形的三维人体头面部测点自动识别方法。方法建立了一个标注了50个测点的三维人体头面部三角网格模型作为模板网格,每个被测者的三维头面部扫描模型作为目标模型。首先通过自动查找模板网格和目标模型上对应的14个特征点作为约束进行初始变形,将模板网格变形为接近目标模型的最小二乘网格;然后进行精细配准,即在目标模型上不断增加与模板网格的顶点相对应的点进行变形配准。经过迭代计算,最终将模板网格变形为一个拓扑上与模板网格一致、几何上逼近目标模型的头部网格;最后,变形后的模板网格上测点即为目标模型的测点。结果对42名志愿者的三维扫描模型,将本方法所得到的测点与按照测点定义基于人体头面部几何特征所确定的测点进行对比。结果表明,以测点定义所确定的测点为圆心,用本方法所得到的测点,85%以上都落在半径为6mm圆内。结论本研究建立的方法实现了三维头面部测点的自动识别,对特征不明显的测点也能够达到较好的识别,对提高大样本三维头面部人体测量工作的效率有重要意义。     

基于径向基函数神经网络的滚动轴承故障模式的识别

径向基函数（RBF）神经网络是一种3层前馈性神经网络，它具有较强的函数逼近能力和分类能力。鉴于径向基函数神经网络的优点，在对滚动轴承振动信号特征分析的基础上，提出了采用时序方法对其建立AR模型，利用AR模型参数建立径向基函数神经网络，并用该网络对滚动轴承的故障模式进行了识别。理论和试验证明了该方法的有效性，且具有较高的识别精度。     

Smartphone User Authentication Based on Holding Position and Touch-Typing Biometrics

In this advanced age, when smart phones are the norm, people utilize social networking, online shopping, and even private information storage through smart phones. As a result, identity authentication has become the most critical security activity in this period of the intelligent craze. By analyzing the shortcomings of the existing authentication methods, this paper proposes an identity authentication method based on the behavior of smartphone users. Firstly, the sensor data and touch-screen data of the smart phone users are collected through android programming. Secondly, the eigenvalues of this data are extracted and sent to the server. Thirdly, the Support Vector Machine (SVM) and Recurrent Neural Network (RNN) are introduced to train the collected data on the server end, and the results are finally yielded by the weighted average. The results show that the method this paper proposes has great FRR (False Reject Rate) and FAR (False Accept Rate).