Candidate region correlation for video action detection

The rapid development of deep learning has prompted the development of video action detection technology. However, the accuracy of current video action detection algorithms can be improved further. Previous work has improved feature extraction by optimizing the network structure. In addition, the features of the candidate regions have been optimized by changing the representation of the regions. Although these methods have achieved promising results, they fail to consider the correlation among different candidate regions, generating uninformative (even redundant) candidate regions, and thus usually decrease the detection performance in practice. To address this problem, in this paper we propose a self-attention mechanism for candidate regions, which can help pursue the most informative regions. We obtain the region correlation by simultaneously determining the spatial and temporal correlation among different candidate regions. In addition, we focus on how to apply the correlation to optimize the original candidate region features and improve video action detection accuracy. The experimental results show the promising improvement achieved by our method over the state-of-the-art solutions.     

Saliency-based dense trajectories for action recognition using low-rank matrix decomposition

Dense trajectory methods have recently been proved to be successful in recognizing actions in realistic videos. However, their performance is still limited due to the uniform dense sampling, which does not discriminate between action-related areas and background. This paper proposes to improve the dense trajectories for recognizing actions captured in realistic scenes, especially in the presence of camera motion. Firstly, based on the observation that the motion in action-related areas is usually much more irregular than the camera motion in background, we recover the salient regions in a video by implementing low-rank matrix decomposition on the motion information and use the saliency maps to indicate action-related areas. Considering action-related regions are changeable but continuous with time, we temporally split a video into subvideos and compute the salient regions subvideo by subvideo. In addition, to ensure spatial continuity, we spatially divide a subvideo into patches and arrange the vectorized optical flow of all the spatial patches to collect the motion information for salient region detection. Then, after the saliency maps of all subvideos in a video are obtained, we incorporate them into dense tracking to extract saliency-based dense trajectories to describe actions. To evaluate the performance of the proposed method, we conduct experiments on four benchmark datasets, namely, Hollywood2, YouTube, HMDB51 and UCF101, and show that the performance of our method is competitive with the state of the art.     

A supervised learning approach to automate the acquisition of knowledge in surveillance systems

This paper presents a machine learning-based method to build knowledge bases used to carry out surveillance tasks in environments monitored with video cameras. The method generates three sets of rules for each camera that allow to detect objects’ anomalous behaviours depending on three parameters: object class, object position, and object speed. To deal with uncertainty and vagueness inherent in video surveillance we make use of fuzzy logic. Thanks to this approach we are able to generate a set of rules highly interpretable by security experts. Besides, the simplicity of the surveillance system offers high efficiency and short response time. The process of building the knowledge base and how to apply the generated sets of fuzzy rules is described in depth for a real environment.     

浅析警戒探测系统

利用作战平台上多种探测设备的探测数据进行多层次的融合从而获得全面、完整、精确的战场态势是警戒探测系统的主要目标。本文分析了警戒探测系统的构成、工作方式及主要应用模式。     

机场跑道异物检测系统设计与研究

对机场跑道异物FOD（foreign object debris）快速精确的检测与告警已经成为保障飞机飞行安全急需解决的重大问题,一个有效的智能机场跑道安全检测系统是机场飞行安全保障体系应有的组成部分。依据FAA对FOD检测系统的性能要求,借鉴国外现有探测系统,提出了一种新的跑道安全检测系统方案,重点分析FOD探测系统中毫米波雷达、光学系统的关键技术及其他系统间的数据交互定义,并开展了系统软件界面设计。系统最终可以对FOD全天时、全天候、全自动的检测,具有异物分类识别及告警能力,可以有效的预防和降低跑道异物对机场跑道安全的威胁。     

Enhancing IoT anomaly detection performance for federated learning

Federated Learning (FL) with mobile computing and the Internet of Things (IoT) is an effective cooperative learning approach. However, several technical challenges still need to be addressed. For instance, dividing the training process among several devices may impact the performance of Machine Learning (ML) algorithms, often significantly degrading prediction accuracy compared to centralized learning. One of the primary reasons for such performance degradation is that each device can access only a small fraction of data (that it generates), which limits the efficacy of the local ML model constructed on that device. The performance degradation could be exacerbated when the participating devices produce different classes of events, which is known as the class balance problem. Moreover, if the participating devices are of different types, each device may never observe the same types of events, which leads to the device heterogeneity problem. In this study, we investigate how data augmentation can be applied to address these challenges and improving detection performance in an anomaly detection task using IoT datasets. Our extensive experimental results with three publicly accessible IoT datasets show the performance improvement of up to 22.9% with the approach of data augmentation, compared to the baseline (without relying on data augmentation). In particular, stratified random sampling and uniform random sampling show the best improvement in detection performance with only a modest increase in computation time, whereas the data augmentation scheme using Generative Adversarial Networks is the most time-consuming with limited performance benefits.     

视频与AIS信息融合的海上目标检测

提出了一种视频与AIS信息融合的海上船只目标检测方法。首先结合AIS信息确定船只所在区域,提取小范围图像,然后对图像进行高频加强滤波处理,增强船只目标与海面背景的对比度,利用显著性区域检测方法生成显著性图像,随之采用双阈值分割提取高显著性目标,最后通过形态学处理判断船只目标。实验结果表明,该方法适应性强,能够准确快速地实现船只目标提取。     

Semi-supervised multi-layered clustering model for intrusion detection

A Machine Learning (ML)-based Intrusion Detection and Prevention System (IDPS) requires a large amount of labeled up-to-date training data to effectively detect intrusions and generalize well to novel attacks. However, the labeling of data is costly and becomes infeasible when dealing with big data, such as those generated by Internet of Things applications. To this effect, building an ML model that learns from non-labeled or partially labeled data is of critical importance. This paper proposes a Semi-supervised Multi-Layered Clustering ((SMLC)) model for the detection and prevention of network intrusion. SMLC has the capability to learn from partially labeled data while achieving a detection performance comparable to that of supervised ML-based IDPS. The performance of SMLC is compared with that of a well-known semi-supervised model (tri-training) and of supervised ensemble ML models, namely RandomForest, Bagging, and AdaboostM1 on two benchmark network-intrusion datasets, NSL and Kyoto 2006+. Experimental results show that SMLC is superior to tri-training, providing a comparable detection accuracy with 20% less labeled instances of training data. Furthermore, our results demonstrate that our scheme has a detection accuracy comparable to that of the supervised ensemble models.     

Vision‐based garbage dumping action detection for real‐world surveillance platform

In this paper, we propose a new framework for detecting the unauthorized dumping of garbage in real‐world surveillance camera. Although several action/behavior recognition methods have been investigated, these studies are hardly applicable to real‐world scenarios because they are mainly focused on well‐refined datasets. Because the dumping actions in the real‐world take a variety of forms, building a new method to disclose the actions instead of exploiting previous approaches is a better strategy. We detected the dumping action by the change in relation between a person and the object being held by them. To find the person‐held object of indefinite form, we used a background subtraction algorithm and human joint estimation. The person‐held object was then tracked and the relation model between the joints and objects was built. Finally, the dumping action was detected through the voting‐based decision module. In the experiments, we show the effectiveness of the proposed method by testing on real‐world videos containing various dumping actions. In addition, the proposed framework is implemented in a real‐time monitoring system through a fast online algorithm.     

A super-resolution-based license plate recognition method for remote surveillance

With the continuous development of deep learning, neural networks have made great progress in license plate recognition (LPR). Nevertheless, there is still room to improve the performance of license plate recognition for low-resolution and relatively blurry images in remote surveillance scenarios. When it is difficult to enhance the recognition algorithm, we choose super-resolution (SR) to improve the quality of license plate images and thereby provide clearer input for the subsequent recognition stage. In this paper, we propose an automatic super-resolution license plate recognition (SRLPR) network which consists of four parts separately: license plate detection, character detection, single character super-resolution, and recognition. In the training stage, firstly, LP detection model needs to be trained alone and then its detection results will be used to successively train the three subsequent modules. During the test phase, for each input image, the network can get its LP number automatically. We also collect an applicable and challenging LPR dataset called SRLP, which is collected from real remote traffic surveillance. The experimental results demonstrate that our method achieves comprehensive quality of SR images and higher recognition accuracy compared with state-of-the-art methods. The SRLP dataset and the code for training and testing SRLPR network are available at https://pan.baidu.com/s/1vnhRa-c-dBj6jlfBZV5w4g.     

A novel recurrent hybrid network for feature fusion in action recognition

Action recognition in video is one of the most important and challenging tasks in computer vision. How to efficiently combine the spatial-temporal information to represent video plays a crucial role for action recognition. In this paper, a recurrent hybrid network architecture is designed for action recognition by fusing multi-source features: a two-stream CNNs for learning semantic features, a two-stream single-layer LSTM for learning long-term temporal feature, and an Improved Dense Trajectories (IDT) stream for learning short-term temporal motion feature. In order to mitigate the overfitting issue on small-scale dataset, a video data augmentation method is used to increase the amount of training data, as well as a two-step training strategy is adopted to train our recurrent hybrid network. Experiment results on two challenging datasets UCF-101 and HMDB-51 demonstrate that the proposed method can reach the state-of-the-art performance.     

一种基于机器视觉的铝管缺陷检测系统

针对铝管生产过程中对准确、可量化的自动缺陷检测系统的迫切需要,本文引入一种由图像采集、缺陷检测、缺陷处理等模块组成的铝管缺陷检测系统。平板探测器获取由X光高压电源产生,穿过铝管的X射线并把所形成的数字图像通过USB端口发送至检测服务器。检测服务器使用机器视觉算法检测图像中的缺陷。当服务器检测到缺陷时,会向PCI板上指定位输出信号,报警装置接到信号后报警提醒工作人员。实验表明该系统能够自动、准确的标记出铝管中存在的缺陷,达到了系统的设计目标。     

A boosting approach for intrusion detection

Intrusion detection can be essentially regarded as a classification problem, namely, distinguishing normal profiles from intrusive behaviors. This paper introduces boosting classification algorithm into the area of intrusion detection to learn attack signatures. Decision tree algorithm is used as simple base learner of boosting algorithm. Furthermore, this paper employs the Principle Component Analysis （PCA） approach, an effective data reduction approach, to extract the key attribute set from the original high-dimensional network traffic data. KDD CUP 99 data set is used in these experiments to demonstrate that boosting algorithm can greatly improve the classification accuracy of weak learners by combining a number of simple ＂weak learners＂. In our experiments, the error rate of training phase of boosting algorithm is reduced from 30.2% to 8% after 10 iterations. Besides, this paper also compares boosting algorithm with Support Vector Machine （SVM） algorithm and shows that the classification accuracy of boosting algorithm is little better than SVM algorithm＇s. However, the generalization ability of SVM algorithm is better than boosting algorithm.     

提高航管二次雷达近程目标跟踪稳定性的方法

针对相控阵体制航管二次雷达系统在雷达近程探测空域内无法稳定监视目标的问题,提出了一种提高航管二次雷达系统对近程目标跟踪稳定性的方法。基于现有航管二次雷达系统的硬件架构,设计了在对监视空域进行航管扫描询问过程中密集插入对近程目标跟踪询问的工作方式,并给出了航管近程跟踪询问流程和波位随机同步跳转控制时序的详细设计方法以及对航管近程跟踪能力的估算方法。仿真计算结果验证了该方法的可行性和有效性。     

一种直升机避障电力线检测方法

电力线是一类形状细长、特征稀疏、随着视角的变化容易混淆在大量背景信息中的特殊障碍物,常规电力线检测识别算法得到的目标框对电力线所在位置的估计不够准确.为此,提出了一种相对角度估计方法,基于常规电力线目标检测与识别算法,并结合电力线相对角度估计,从而提高电力线的检测识别过程中所在位置的精度.相比电力线绝对角度回归的方法,...     

DroidEnemy: Battling adversarial example attacks for Android malware detection

In recent years, we have witnessed a surge in mobile devices such as smartphones, tablets, smart watches, etc., most of which are based on the Android operating system. However, because these Android-based mobile devices are becoming increasingly popular, they are now the primary target of mobile malware, which could lead to both privacy leakage and property loss. To address the rapidly deteriorating security issues caused by mobile malware, various research efforts have been made to develop novel and effective detection mechanisms to identify and combat them. Nevertheless, in order to avoid being caught by these malware detection mechanisms, malware authors are inclined to initiate adversarial example attacks by tampering with mobile applications. In this paper, several types of adversarial example attacks are investigated and a feasible approach is proposed to fight against them. First, we look at adversarial example attacks on the Android system and prior solutions that have been proposed to address these attacks. Then, we specifically focus on the data poisoning attack and evasion attack models, which may mutate various application features, such as API calls, permissions and the class label, to produce adversarial examples. Then, we propose and design a malware detection approach that is resistant to adversarial examples. To observe and investigate how the malware detection system is influenced by the adversarial example attacks, we conduct experiments on some real Android application datasets which are composed of both malware and benign applications. Experimental results clearly indicate that the performance of Android malware detection is severely degraded when facing adversarial example attacks.     

Vulnerable objects detection for autonomous driving: A review

Object detection performed by Autonomous Vehicles (AV)s is a crucial operation that comes ahead of various autonomous driving tasks, such as object tracking, trajectories estimation, and collision avoidance. Dynamic road elements (pedestrians, cyclists, vehicles) impose a greater challenge due to their continuously changing location and behaviour. This paper presents a comprehensive review of the state-of-the-art object detection technologies focusing on both the sensory systems and algorithms used. It begins with a brief introduction on the autonomous driving operations and challenges. Then, different sensory systems employed on existing AVs are elaborated while illustrating their advantages, limitations and applications. Also, sensory systems employed by different research are reviewed. Moreover, due to the significant role Deep Neural Networks (DNN)s are playing in object detection tasks, different DNN-based networks are also highlighted. Afterwards, previous research on dynamic objects detection performed by AVs are reviewed in tabular forms. Finally, a conclusion summarizes the outcomes of the review and suggests future work towards the development of vehicles with higher automation levels.