基于MM YOLOv4的无人机目标检测算法

针对当前无人机目标图像检测方法精度较低和检测速度过慢的问题,提出一种结合轻量级网络和改进多尺度结构的目标检测算法。首先采用MobileNetV3轻量级网络替换YOLOv4的主干网络,减少模型复杂度,提升检测速度;其次,引入改进多尺度结构的PANet网络,增强高维图像特征和低维定位特征的流动叠加,提升对小目标的分类和定位精度;最后,利用K means方法对目标锚框进行参数优化,提升检测效率。同时结合公开数据集和自主拍摄方式构建一个新的无人机目标图像数据集Drone dataset,并基于数据增强的方法开展算法性能实验。实验结果表明,该算法的mAP达到了91.58%,FPS达到了55帧/s,参数量为44.39 M仅是YOLOv4算法的1/6,优于主流的SSD、YOLO系列算法和Faster R CNN算法,实现了对多尺度无人机目标的快速检测。     

Distance estimation in ultrasound images using specific decorrelation curves

Speckle decorrelation algorithm is a method using decorrelation curves to estimate the distance between two neighboring ultrasound images. In this paper, we propose a new method to obtain specific decorrelation curves for distance estimation. First, several datasets of synthetic ultrasound(US) images are obtained by scanning different scatters. Second, based on the US datasets, we compute low-order moments and the elevational decorrelation curves. Finally, low-order moments are used to classify different scattering conditions. The suitable decorrelation curves can be acquired when the scattering style has been determined. With these steps, the relationship between low order moments and the decorrelation curves is established by the scattering conditions. This relationship proves to be efficient and applicable in the experiment section. The decorrelation curves chosen according to the relationship also perform well in the distance estimation test.     

Absolute ruin problems for the risk processes with interest and a constant dividend barrier

In this paper,the absolute ruin in the compound Poisson risk model with interest and a constant dividend barrier is investigated.First,integro-differential equations satisfied by the expected discounted dividend payments are derived.The explicit expressions are obtained when the individual claim size is expo-nential distributed.Second,the moment generating function of the discounted dividends is considered,and integro-differential equations satisfied by the moment generating function of the discounted dividends are derived.Third,by a "differential" argument,the time to recovery to zero from a given negative surplus is considered.Finally,how long it takes for the surplus process to reach the dividend barrier is discussed.     

对电周期信号作计算机实时测量的通用接口

本文提出一个可对电周期信号进行测量的通用接口,它由INTEL8253芯片并配以少量电子器件所组成。该接口具有精度高、量程宽、响应快等优点,可满足常见生产过程、科学实验中对电周期信号作测量的要求。文章对接口的组成、工作原理及主要技术指标作了简明的分析,最后附有一个实用的程序以供参考。     

Multiple constraints QoS multicast routing optimization algorithm in MANET based on GA

Usually multiple quality of service （QoS） guarantees are required in most multicast applications. This paper presents a multiple con-straints algorithm for multicast traffic engineering in mobile ad hoc networks （MANET）. The proposed algorithm is a new version of multiple constraints QoS multicast routing optimization algorithm in MANET based on genetic algorithm （MQMGA）. The proposed MQMGA can optimize the maximum link utilization, the cost of the multicast tree, the selection of the long-life path, the average delay and the maximum end-to-end delay. Experimental result shows that the approach is efficient, has promising performance in multicast traffic engineering and for evaluating the route stabilitv in dvnamic mobile networks.     

深大基坑自动化监测及智能预警平台

针对深大基坑人工监测中监测不及时、监测数据精度低、监测数据少等问题,以武汉某基坑工程为依托,利用自动化监测与采集设备获得了基坑变形、受力等监测数据,利用前端开发工具Visual Studio Code和后端开发工具IntelliJ构建了深基坑自动化监测与智能预警云平台。研究结果表明,支护桩最大水平位移在0.4倍支护桩长位置处,地表沉降随基坑开挖深度增加而增大,支撑轴力随基坑开挖深度增加而线性增大且轴力增长速率随后续支撑施加而降低。深大基坑自动化监测及智能预警平台实现了基坑施工全过程中自动化监测、智能动态预测与风险评估。     

Multiple constraints QoS multicast routing optimization algorithm in MANET based on GA

Usually multiple quality of service (QoS) guarantees are required in most multicast applications. This paper presents a multiple constraints algorithm for multicast traffic engineering in mobile ad hoc networks (MANET). The proposed algorithm is a new version of multiple constraints QoS multicast routing optimization algorithm in MANET based on genetic algorithm (MQMGA). The proposed MQMGA can optimize the maximum link utilization, the cost of the multicast tree, the selection of the long-life path, the average delay and the maximum end-to-end delay. Experimental result shows that the approach is efficient, has promising performance in multicast traffic engineering and for evaluating the route stability in dynamic mobile networks.     

Region-based classification by combining MS segmentation and MRF for POLSAR images

Speckle effects on classification results can be suppressed to some extent by introducing the contextual information.An unsupervised classification algorithm is proposed for polarimetric synthetic aperture radar(POLSAR) images based on the mean shift(MS) segmentation and Markov random field(MRF).First,polarimetric features are exacted by target decomposition for MS segmentation.An initial classification is executed by using the target decomposition and the agglomerative hierarchical clustering algorithm.Thereafter,a classification step based on MRF is performed by using the mean coherence matrices obtained for each segment.Under the MRF framework,the smoothness term is defined according to the distance between neighboring areas.By using POLSAR images acquired by the German Aerospace Centre and National Aeronautics and Space Administration/Jet Propulsion Laboratory,the experimental results confirm that the proposed method has higher accuracy and better regional connectivity than other classification methods.     

Segmentation of tumor ultrasound image via region-based Ncut method

To segment the tumor region precisely is a prerequisite for ultrasound navigation and treatment. In this paper, a normalized cut method to segment tumor ultrasound image is proposed by means of simple linear iterative clustering for presegmentation procedure. The first step, we use simple linear iterative clustering algorithm to divide the image into a number of homogeneous over-segmented regions. Then, these regions are regarded as nodes, and a similarity matrix is constructed by comparing the histograms of each two regions. Finally, we apply the Ncut method to merging the over-segmented regions, then the image segmentation process is completed. The results show that the proposed segmentation scheme handles the strong speckle noise, low contrast, and weak edges well in ultrasound image. Our method has high segmentation precision and computation efficiency than the pixel-based Ncut method.     

浅议南水北调的几个前提性问题

鉴于我国水资源时空分布与社会经济发展布局以及与资源开发利用不能很好匹配，我国北方水危机已成为国内外广大公众关注的焦点。但如何客观认识南水北调，仍是一个值得探讨的大问题。从近几年来又有人提出种种大胆的西线南水北调方案，及中央领导的相关批示来看，南水北调研究论证工作势将进入一个新时期。值此之际，笔者想在此谈一点对南水北调论证工作的看法。一、过去的南水北调研究论证的方向值得商榷，一些带根本性的问题，也缺乏研究　　１．开源供水的增长已难以抵消浪费与污染破坏的后果当前水资源开发利用程度已达到一定水平，各地…