Fast Random‐Forest‐Based Human Pose Estimation Using a Multi‐scale and Cascade Approach

Since the recent launch of Microsoft Xbox Kinect, research on 3D human pose estimation has attracted a lot of attention in the computer vision community. Kinect shows impressive estimation accuracy and real‐time performance on massive graphics processing unit hardware. In this paper, we focus on further reducing the computation complexity of the existing state‐of‐the‐art method to make the real‐time 3D human pose estimation functionality applicable to devices with lower computing power. As a result, we propose two simple approaches to speed up the random‐forest‐based human pose estimation method. In the original algorithm, the random forest classifier is applied to all pixels of the segmented human depth image. We first use a multi‐scale approach to reduce the number of such calculations. Second, the complexity of the random forest classification itself is decreased by the proposed cascade approach. Experiment results for real data show that our method is effective and works in real time (30 fps) without any parallelization efforts.     

基于空间转换网络的端到端车牌检测与识别

在复杂场景中,许多现有的车牌检测和识别方面 的研究方法存在数据集单一且有限、算法复杂等问题。因此提出了一个端到端的统一网络: 残差-空间变换-连接时序分类融合的 车辆号牌检测识别网络(LPDR-RSCNet)。该网络结合残差神经网络、空间变压器网络和连 接主义者时间分类,联合训练检测和识别模块,以减少中间错误积累。通过在残差神经网络 提取特征过程中引入空间变换网络,使特征提取器具有平移不变性、旋转不变性和缩放不变 性;在分类器引入连接时序分类,可以自动识别图片标签和特征之间的关系。同时,还可以 适应可变长度序列的识别。在中国城市停车场数据集(CCPD)上进行了比较实验,CCPD是一 个大规模、多样的中文车牌数据集。实验证明LPDR-RSCNet模型在实际应用中可实现98.8％ 的识别精度和34 fps的速度,并且相较于YOLO9000、Faster-RCNN、SSD300, 具有更好的检测准确度,可满足智能交通系统中对移动车辆实时车牌检测和识别的要求。     

Principal visual word discovery for automatic license plate detection

License plates detection is widely considered a solved problem, with many systems already in operation. However, the existing algorithms or systems work well only under some controlled conditions. There are still many challenges for license plate detection in an open environment, such as various observation angles, background clutter, scale changes, multiple plates, uneven illumination, and so on. In this paper, we propose a novel scheme to automatically locate license plates by principal visual word (PVW), discovery and local feature matching. Observing that characters in different license plates are duplicates of each other, we bring in the idea of using the bag-of-words (BoW) model popularly applied in partial-duplicate image search. Unlike the classic BoW model, for each plate character, we automatically discover the PVW characterized with geometric context. Given a new image, the license plates are extracted by matching local features with PVW. Besides license plate detection, our approach can also be extended to the detection of logos and trademarks. Due to the invariance virtue of scale-invariant feature transform feature, our method can adaptively deal with various changes in the license plates, such as rotation, scaling, illumination, etc. Promising results of the proposed approach are demonstrated with an experimental study in license plate detection.     

DDoS protection with stateful software‐defined networking

Distributed denial of service (DDoS) attacks represent one of the most critical security challenges facing network operators. Software‐defined networking (SDN) permits fast reactions to such threats by dynamically enforcing simple forwarding/blocking rules as countermeasures. However, the centralization of the control plane requires that the SDN controller, besides network management operations, should also collect information to identify and mitigate the security menaces. A major drawback of this approach is that it may overload the controller and the control channel. On the other hand, stateful SDN represents a new concept, developed to improve reactivity and offload the controller by delegating local treatments to the switches. In this article, we embrace this paradigm to protect end‐hosts from DDoS attacks. We propose StateSec, a novel approach based on in‐switch processing capabilities to detect and mitigate flooding threats. StateSec monitors packets matching configurable traffic features without resorting to the controller. By feeding an entropy‐based detection algorithm with such monitoring features, it detects and mitigates several threats such as (D)DoS with high accuracy. We implemented StateSec in an SDN platform comparing it with state‐of‐the‐art approaches. We show that StateSec is far more efficient: It achieves very accurate detection levels, reducing at the same time the control plane overhead. We have also evaluated the memory footprint of StateSec for a possible use in production. Finally, we deployed StateSec over a real network to tune its parameters and assess its suitability to real‐world deployments.     

Context‐aware Android applications through transportation mode detection techniques

In this paper, we study the problem of how to detect the current transportation mode of the user from the smartphone sensors data, because this issue is considered crucial for the deployment of a multitude of mobility‐aware systems, ranging from trace collectors to health monitoring and urban sensing systems. Although some feasibility studies have been performed in the literature, most of the proposed systems rely on the utilization of the GPS and on computational expensive algorithms that do not take into account the limited resources of mobile phones. On the opposite, this paper focuses on the design and implementation of a feasible and efficient detection system that takes into account both the issues of accuracy of classification and of energy consumption. To this purpose, we propose the utilization of embedded sensor data (accelerometer/gyroscope) with a novel meta‐classifier based on a cascading technique, and we show that our combined approach can provide similar performance than a GPS‐based classifier, but introducing also the possibility to control the computational load based on requested confidence. We describe the implementation of the proposed system into an Android framework that can be leveraged by third‐part mobile applications to access context‐aware information in a transparent way. Copyright © 2016 John Wiley & Sons, Ltd.     

3T‐FASDM: Linear discriminant analysis‐based three‐tier face anti‐spoofing detection model using support vector machine

In recent years, to solve the problem of face spoofing, momentous work has been done in this field, but still, there is a need for establishing counter measures to the biometric spoofing attacks. Although trained and evaluated on different databases, impressive results have been achieved in existing face anti‐spoofing techniques, but biometric authentication is a very significant problem as imposters are using lots of reconstructed samples or fake synthetic material or structure that can be used for various attack purposes. For the first time, to the best of our knowledge, this paper explains the security for face anti‐spoofing detection using linear discriminant analysis and validates the results by calculating HTER and accuracy on different databases (i.e., REPLAY ATTACK and CASIA). The proposed model, that is, three‐tier face anti‐spoofing detection model (3T‐FASDM), is used for the detection of the fake biometric user and works well for real‐time applications. The proposed methods tested on a set of state‐of‐the‐art anti‐spoofing features for the face mode gives a very low degree of complexity as 26 general image quality measures are applied to differentiate among legitimate and imposter samples. The outcomes obtained from publically available data show that this technique has improved performance and accuracy by analyzing the HTER and machine learning classifiers that are helpful to differentiate among real and fake traits.     

计算机多尺度辅助定位车牌算法

违法占道拍摄出的单帧车辆图像具有数据量大、时效性强,检测环境复杂等特点.对其检测需要花费大量的人力与物力.并且人们在定位过程中,无法避免因经验、疲劳等方面的干扰,导致遗漏和错误定位.为此本文从视觉感知角度提出计算机多尺度辅助定位车牌算法.模拟视觉感知原理,从车辆特征、纹理特征、颜色特征尺度,逐次聚焦至车牌所在区域.提出了完整的单帧图像车牌定位流程.并且提出基于边界对的车牌区域准确定位算法.通过对实拍的交通图像实验,表明本算法对于正对的车辆有较高的准确率,符合人类视觉感知的过程可实时的对图像进行车牌检测,可同时检测单幅图片的多个车牌.但对于光线过暗、过强或者颜色失真的情况,仍需要进一步的研究.     

Gender Classification of Low‐Resolution Facial Image Based on Pixel Classifier Boosting

In face examinations, gender classification (GC) is one of several fundamental tasks. Recent literature on GC primarily utilizes datasets containing high‐resolution images of faces captured in uncontrolled real‐world settings. In contrast, there have been few efforts that focus on utilizing low‐resolution images of faces in GC. We propose a GC method based on a pixel classifier boosting with modified census transform features. Experiments are conducted using large datasets, such as Labeled Faces in the Wild and The Images of Groups, and standard protocols of GC communities. Experimental results show that, despite using low‐resolution facial images that have a 15‐pixel inter‐ocular distance, the proposed method records a higher classification rate compared to current state‐of‐the‐art GC algorithms.     

多特征级联筛选的高鲁棒车牌检测

现有的车牌检测算法在车牌较模糊时往往难于取得很好的检测效果.针对监控图像的特点,首先提取清晰和模糊车牌所共有的归一化梯度特征,进行初步车牌检测;然后结合车牌区域的颜色直方图特征,进行级联筛选、去除非车牌样本,得到一种高鲁棒的车牌检测方法.基于真实监控图像的实验结果表明,此方法具有较高的稳定性和鲁棒性,尤其对模糊车牌具有明显优于已有方法的召回率.     

基于注意力机制的车牌快速检测方法研究

针对光照、车辆密集和低分辨率等复杂场景下车牌定位困难、检测速度慢和准确率 低等问题,提出了一种基于注意力机制的车牌快速检测方法。首先,综合车牌的特征,设计 了轻量级网络单元LeanNet,并使用该单元构建一种计算量低且精准的骨干网络。其次,设 计了MLA(muti-scale light attention)模块,用于引导网络关注不同尺度的车牌,生成 基 于车牌的局部显著图,抑制背景噪声。最后,设计了一个四尺度预测网络,其中的FSPF(fo ur scale pyramid fusion)模块能够生成四尺度特征金字塔,有利于实现不同尺度车牌的检测 。 实验结果表明,本文方法在CCPD(Chinese city parking dataset)数据集中的准确识别率 为 99.12%,与最新的YOLOv4(you only look once v4)检测方法相比,准确率提高了1.9%,运行速度提高了6倍,能 够在嵌入式设备中实现复杂场景下的车牌检测。     

Temporal matching prior network for vehicle license plate detection and recognition in videos

In real‐world intelligent transportation systems, accuracy in vehicle license plate detection and recognition is considered quite critical. Many algorithms have been proposed for still images, but their accuracy on actual videos is not satisfactory. This stems from several problematic conditions in videos, such as vehicle motion blur, variety in viewpoints, outliers, and the lack of publicly available video datasets. In this study, we focus on these challenges and propose a license plate detection and recognition scheme for videos based on a temporal matching prior network. Specifically, to improve the robustness of detection and recognition accuracy in the presence of motion blur and outliers, forward and bidirectional matching priors between consecutive frames are properly combined with layer structures specifically designed for plate detection. We also built our own video dataset for the deep training of the proposed network. During network training, we perform data augmentation based on image rotation to increase robustness regarding the various viewpoints in videos.     

Delay‐aware privacy‐preserving location‐based services under spatiotemporal constraints

The ubiquitous use of location‐based services (LBS) through smart devices produces massive amounts of location data. An attacker, with an access to such data, can reveal sensitive information about users. In this paper, we study location inference attacks based on the probability distribution of historical location data, travel time information between locations using knowledge of a map, and short and long‐term observation of privacy‐preserving queries. We show that existing privacy‐preserving approaches are vulnerable to such attacks. In this context, we propose a novel location privacy‐preserving approach, called KLAP, based on the three fundamental obfuscation requirements: minimum k ‐locations, l ‐diversity, and privacy a rea p reservation. KLAP adopts a personalized privacy preference for sporadic, frequent, and continuous LBS use cases. Specifically, it generates a secure concealing region (CR) to obfuscate the user's location and directs that CR to the service provider. The main contribution of this work is twofold. First, a CR pruning technique is devised to establish a balance between privacy and delay in LBS usage. Second, a new attack model called a long‐term obfuscated location tracking attack, and its countermeasure is proposed and evaluated both theoretically and empirically. We assess KLAP with two real‐world datasets. Experimental results show that it can achieve better privacy, reduced delay, and lower communication costs than existing state‐of‐the‐art methods.     

雾霾环境下基于PLATE-YOLO的车牌检测方法

针对目前车牌识别领域中，雾霾环境下车牌检测准确率低的问题，本文提出一种基于深度学习的抗雾霾车牌检测方法，该方法能够检测民用车牌和机场民航车辆车牌。该方法首先利用一种基于卷积神经网络的去雾算法对车牌图片进行去雾预处理，然后将处理过的无雾霾图片送入PLATE-YOLO网络中检测车牌的位置。该PLATE-YOLO网络是本文针对车牌检测的特点，对YOLOv3网络做了修改后得到的适用于车牌检测的网络。主要改进点有两处:第一，提出了一种基于层次聚类算法的锚盒(anchor box)个数和初始簇中心的计算方法；第二，针对车牌目标较大的特点，对网络的多尺度特征融合做了优化。优化后的PLATE-YOLO网络更适合于车牌检测，且提高了检测速度。实验证明，PLATE-YOLO网络检测车牌的速度较YOLOv3提高了5 FPS；在雾霾环境下，经去雾预处理的 PLATE-YOLO车牌检测方法比未经去雾处理的车牌检测方法准确率提高了9.2%。      

ROUTE: run‐time robust reducer workload estimation for MapReduce

MapReduce has become a popular model for large‐scale data processing in recent years. Many works on MapReduce scheduling (e.g., load balancing and deadline‐aware scheduling) have emphasized the importance of predicting workload received by individual reducers. However, because the input characteristics and user‐specified map function of a given job are unknown to the MapReduce framework before the job starts, accurately predicting workload of reducers can be a difficult challenge. To address this challenge, we present ROUTE, a run‐time robust reducer workload estimation technique for MapReduce. ROUTE progressively samples the partition size of the early completed mappers, allowing ROUTE to perform estimation at run time yet fulfilling the accuracy requirement specified by users. Moreover, by using robust estimation and bootstrapping resampling techniques, ROUTE can achieve high applicability to a wide variety of applications. Through experiments using both real and synthetic data on an 11‐node Hadoop cluster, we show ROUTE can achieve high accuracy with error rate no more than 10.92% and an improvement of 40.6% in terms of error rate while compared with the state‐of‐the‐art solution. Besides, through simulations using synthetic data, we show that ROUTE is robust to a variety of skewed distributions. Finally, we apply ROUTE to existing load balancing and deadline‐aware scheduling frameworks and show ROUTE significantly improves the performance of these frameworks. Copyright © 2016 John Wiley & Sons, Ltd.     

Real‐Time Apartment Building Detection and Tracking with AdaBoost Procedure and Motion‐Adjusted Tracker

In this letter, we propose a novel approach to detecting and tracking apartment buildings for the development of a video‐based navigation system that provides augmented reality representation of guidance information on live video sequences. For this, we propose a building detector and tracker. The detector is based on the AdaBoost classifier followed by hierarchical clustering. The classifier uses modified Haar‐like features as the primitives. The tracker is a motion‐adjusted tracker based on pyramid implementation of the Lukas‐Kanade tracker, which periodically confirms and consistently adjusts the tracking region. Experiments show that the proposed approach yields robust and reliable results and is far superior to conventional approaches.     

一种基于连通域分析的车牌定位方法

复杂背景中车牌定位技术,是车牌识别过程中的技术难点,提出了一种基于连通域分析的车牌定位方法。该方法通过边缘检测方法进行车牌粗定位,再对粗定位图像进行连通域标记,然后利用级联分类器筛选车牌字符连通域,最后结合车牌模板确定车牌位置。实验表明,该方法定位车牌的准确率高,能够适用于国内现行的多种规格民用汽车牌照的定位。     

基于HSV模型和改进AdaBoost算法的车牌检测

提出了一种基于HSV颜色模型和改进AdaBoost算法的车牌检测方法。针对传统AdaBoost算法在训练过程中出现的过配现象和检测率偏低问题,文中在传统AdaBoost算法的基础上对其权值更新规则和弱分类器加权参数做了改进,并通过利用HSV颜色模型构建第一层强分类器,并构建成级联分类器应用于车牌检测。实验证明使用该方法得到的车牌检测器不仅提高了车牌检测率和检测速度,并在一定程度上避免了过配现象产生     

Multinational vehicle license plate detection in complex backgrounds

Many methods for multinational License Plate Detection (LPD) have been proposed in recent times but most of them are not sophisticated enough to handle complex backgrounds. Moreover, their ability to handle various environmental and illumination conditions has been limited and still needs improvement. In this paper, we propose a novel technique to detect license plates of vehicles regardless of their color, size, and content. As the rear vehicle lights are an essential part of any vehicle, we reduce the image processing area to eliminate the complex background by detecting the rear-lights as the license plates are in a certain range of these lights. Heuristic Energy Map (HEM) of the vertical edge information in the Region of Interest (ROI) is calculated and area with the dense edges is selected using a unique histogram approach which is considered to be the license plate. The proposed algorithm is tested on 855 images from various countries including China, Pakistan, Serbia, Italy and various states of America. Experimental results show that the proposed method is able to detect license plates 90.4% of times despite of complex backgrounds in 0.25 s on average that can achieve real time performance.     

Robust Multi‐person Tracking for Real‐Time Intelligent Video Surveillance

We propose a novel multiple‐object tracking algorithm for real‐time intelligent video surveillance. We adopt particle filtering as our tracking framework. Background modeling and subtraction are used to generate a region of interest. A two‐step pedestrian detection is employed to reduce the computation time of the algorithm, and an iterative particle repropagation method is proposed to enhance its tracking accuracy. A matching score for greedy data association is proposed to assign the detection results of the two‐step pedestrian detector to trackers. Various experimental results demonstrate that the proposed algorithm tracks multiple objects accurately and precisely in real time.     

复杂光照下的车牌图像二值化新方法

为解决车牌识别系统中,车牌区域由于受到光照过度、不足和不均等复杂光照的影响,使得车牌图像的二值化效果不理想的问题,文中提出一种复杂光照车牌图像的二值化新方法。根据国内车牌颜色特点,重新分配R、G、B颜色分量的权重来构造新灰度图,并设计不同颜色车牌灰度图转化的规则。采用全局和局部阈值相结合的双阈值方法实现车牌图像二值化,同时利用空域同态滤波进一步提高图像对光照的鲁棒性。实验结果表明,文中方法运算时间仅为传统方法的61.95%,同时能更有效地克服不均匀光照对车牌图像二值化的干扰,使二值图像的汉字和字符更清晰,鲁棒性更好。