基于时空的弱点状运动目标检测技术

如何在复杂背景下持续有效地检测目标位置,一直是研究者们需要面对的主要挑战。本文在研究红外点状移动目标特征的基础上,根据目标无纹理,无形状的特性,提出一种改进的形态学目标增强算法,并利用目标连续时空不变性检测目标。首先,建立多尺度的图像金字塔,在每层上采用改进的形态学算法快速、粗糙定位小目标。然后进一步的根据目标在时空上的位置相关性,提出基于目标运动特征分析的精确检测方法。得到精确稳定的检测结果。最后实验结果表明与经典的形态学检测算法及其他算法相比,该技术能更有效地检测弱小目标,具有更高的鲁棒性。     

电磁精细探测法在隐伏型导水地质裂缝勘探中的应用

针对传统隐伏型导水地质裂缝勘探方法存在勘测精度较差的问题,提出电磁精细探测法探析隐伏型导水地质裂缝。依照屏蔽系数、实测场强和理论场强数据绘制综合曲线图,通过该图获取隐伏型导水地质裂缝所处位置几何阴影范围,采用层析成像法得到网格化的工作面,获取隐伏型导水地质图像。通过图像直接观测隐伏型导水地质工作面裂缝所处位置,在此基础上,观测四个电磁场分量,采用正交电磁场分量计算介质视电阻率,依据计算视电阻率数值和视电阻率分布状态研究裂缝发育情况和裂缝富水程度。结果表明:采用该方法能较为精准地获取隐伏型导水地质裂缝位置。通过裂缝位置进一步检测出隐伏型导水地质裂缝最大发育高度为63.5 m。当视电阻数值不断增加时,隐伏型导水地质裂缝和裂缝富水性逐渐减小,与实际情况较为相符,说明该种方法探析效果较好。     

Change detection in synthetic aperture radar images based on unsupervised artificial immune systems

In this paper, we propose a novel change detection method for synthetic aperture radar images based on unsupervised artificial immune systems. After generating the difference image from the multitemporal images, we take each pixel as an antigen and build an immune model to deal with the antigens. By continuously stimulating the immune model, the antigens are classified into two groups, changed and unchanged. Firstly, the proposed method incorporates the local information in order to restrain the impact of speckle noise. Secondly, the proposed method simulates the immune response process in a fuzzy way to get an accurate result by retaining more image details. We introduce a fuzzy membership of the antigen and then update the antibodies and memory cells according to the membership. Compared with the clustering algorithms we have proposed in our previous works, the new method inherits immunological properties from immune systems and is robust to speckle noise due to the use of local information as well as fuzzy strategy. Experiments on real synthetic aperture radar images show that the proposed method performs well on several kinds of difference images and engenders more robust result than the other compared methods.     

Visual Detection of Adenosine Triphosphate by Taylor Rising: A Simple Point-of-Care Testing Method Based on Rolling Circle Amplification

Rapid and sensitive point-of-care testing (POCT) is an extremely critical mission in practical applications, especially for rigorous military medicine, home health care, and in the third world. Here, we report a visual POCT method for adenosine triphosphate (ATP) detection based on Taylor rising in the corner of quadratic geometries between two rod surfaces. We discuss the principle of Taylor rising, demonstrating that it is significantly influenced by contact angle, surface tension, and density of the sample, which are controlled by ATP-dependent rolling circle amplification (RCA). In the presence of ATP, RCA reaction effectively suppresses Taylor-rising behavior, due to the increased contact angle, density, and decreased surface tension. Without addition of ATP, untriggered RCA reaction is favorable for Taylor rising, resulting in a significant height. With this proposed method, visual sensitive detection of ATP without the aid of other instruments is realized with only a 5 μL droplet, which has good selectivity and a low detection limit (17 nM). Importantly, this visual method provides a promising POCT tool for user-friendly molecular diagnostics.     

ECG heart beat classification method based on modified ABC algorithm

Electrocardiogram is the most commonly used tool for the diagnosis of cardiologic diseases. In order to help cardiologists to diagnose the arrhythmias automatically, new methods for automated, computer aided ECG analysis are being developed. In this paper, a Modified Artificial Bee Colony (MABC) algorithm for ECG heart beat classification is introduced. It is applied to ECG data set which is obtained from MITBIH database and the result of MABC is compared with seventeen other classifier's accuracy.In classification problem, some features have higher distinctiveness than others. In this study, in order to find higher distinctive features, a detailed analysis has been done on time domain features. By using the right features in MABC algorithm, high classification success rate (99.30%) is obtained. Other methods generally have high classification accuracy on examined data set, but they have relatively low or even poor sensitivities for some beat types. Different data sets, unbalanced sample numbers in different classes have effect on classification result. When a balanced data set is used, MABC provided the best result as 97.96% among all classifiers.Not only part of the records from examined MITBIH database, but also all data from selected records are used to be able to use developed algorithm on a real time system in the future by using additional software modules and making adaptation on a specific hardware.     

The implementation of a smartphone-based fall detection system using a high-level fuzzy Petri net

The falling down problem has become one of the very important issues of global public health in an aging society. The specific equipment was adopted as the detection device of falling-down in the early studies, but it is inconvenient for the elderly and difficult for future application. The smart phone more commonly used than the specific fall detection equipment is selected as a mobile device for human fall detection, and a fall detection algorithm is developed for this purpose. What the user has to do is to put the smart phone in his/her thigh pocket for falling down detection. The signals detected by the tri-axial G-sensor are converted into signal vector magnitudes as the basis of detecting a human body in a stalling condition. The Z-axis data sets are captured for identification of human body inclination and the occurrence frequencies at the peak of the area of use are used as the input parameters. A high-level fuzzy Petri net is used for the analysis and the development of identifying human actions, including normal action, exercising, and falling down. The results of this study can be used in the relevant equipments or in the field of home nursing.     

Classification and regression models of audio and vibration signals for machine state monitoring in precision machining systems

We present a data-driven method for monitoring machine status in manufacturing processes. Audio and vibration data from precision machining are used for inference in two operating scenarios: (a) variable machine health states (anomaly detection); and (b) settings of machine operation (state estimation). Audio and vibration signals are first processed through Fast Fourier Transform and Principal Component Analysis to extract transformed and informative features. These features are then used in the training of classification and regression models for machine state monitoring. Specifically, three classifiers (K-nearest neighbors, convolutional neural networks and support vector machines) and two regressors (support vector regression and neural network regression) were explored, in terms of their accuracy in machine state prediction. It is shown that the audio and vibration signals are sufficiently rich in information about the machine that 100% state classification accuracy could be accomplished. Data fusion was also explored, showing overall superior accuracy of data-driven regression models.     

深度学习识别光网络单元故障的设计与应用

为解决依赖装维上门鉴别光网络单元故障带来的不便,可以从机器视觉入手实现自动化故障识别。近年,ImageNet挑战赛的成功推动了物体识别技术的跨越式发展,特别是基于卷积的深度学习技术在视觉识别方面已经达到人类水平,为光网络单元故障的自动识别提供了技术基础。文章对识别光网络单元的工作状态进行了研究,将设备工作状态分为7个场景,提出了利用手机APP采集图片识别故障的解决方案并投入了实际生产;重点阐述了深度学习模块的设计与实现,提出一种通过算法整合的方式综合运用物体检测和图像分类算法,分3阶段逐步求精,解决了图片过滤,光网络单元型号和状态识别等问题,实现了基于计算机视觉自动识别光网络单元故障。从数据上看产品的端到端准确率超过84%,识别速度达到10 FPS,月均提供服务超过1万人次,在减少用户等待的同时节约了人力资源。     

Moderate lameness leads to marked behavioral changes in dairy cows

Lameness is one of the most prevalent diseases affecting the welfare of cows in modern dairy production. Lameness leads to behavioral changes in severely lame cows, which have been investigated in much detail. For early detection of lameness, knowledge of the effects of moderate lameness on cow behavior is crucial. Therefore, the behavior of nonlame and moderately lame cows was compared on 17 Swiss dairy farms. On each farm, 5 to 11 nonlame (locomotion score 1 of 5) and 2 to 7 moderately lame (locomotion score 3 of 5) cows were selected for data collection in two 48-h periods (A, B) separated by an interval of 6 to 10 wk. Based on visual locomotion scoring, 142 nonlame and 66 moderately lame cows were examined in period A and 128 nonlame and 53 moderately lame cows in period B. Between these 2 periods, the cows underwent corrective hoof trimming. Lying behavior, locomotor activity, and neck activity were recorded by accelerometers (MSR145 data logger, MSR Electronics GmbH, Seuzach, Switzerland), and feeding and rumination behaviors by noseband sensors (RumiWatch halter, ITIN + HOCH GmbH, Liestal, Switzerland). Furthermore, visits to the brush and the concentrate feeder, and the milking order position were recorded. In comparison with nonlame cows, moderately lame cows had a longer lying duration, a longer average lying bout duration, and a greater lateral asymmetry in lying duration. Average locomotor activity, locomotor activity during 1 h after feed delivery or push-ups, and average neck activity were lower in moderately lame cows. Eating time and the number of eating chews (jaw movements) were reduced in moderately lame compared with nonlame cows, whereas no effect of moderate lameness was evident for ruminating time, number of ruminating chews and boluses, and average number of ruminating chews per bolus. Moderately lame cows visited the concentrate feeder and the brush less frequently, and they were further back in the milking order compared with nonlame cows. In conclusion, nonlame and moderately lame cows differed in a biologically relevant way in many of the behavioral variables investigated in this study. Therefore, the use of these behavioral changes seems to be promising to develop a tool for early lameness detection.     

Graph-based video fingerprinting using double optimal projection

A double optimal projection method that involves projections for intra-cluster and inter-cluster dimensionality reduction are proposed for video fingerprinting. The video is initially set as a graph with frames as its vertices in a high-dimensional space. A similarity measure that can compute the weights of the edges is then proposed. Subsequently, the video frames are partitioned into different clusters based on the graph model. Double optimal projection is used to explore the optimal mapping points in a low-dimensional space to reduce the video dimensions. The statistics and geometrical fingerprints are generated to determine whether a query video is copied from one of the videos in the database. During matching, the video can be roughly matched by utilizing the statistics fingerprint. Further matching is thereafter performed in the corresponding group using geometrical fingerprints. Experimental results show the good performance of the proposed video fingerprinting method in robustness and discrimination.