Moving target detection based on improved ghost suppression and adaptive visual background extraction

Visual background extraction algorithm(ViBe)uses the first frame image to initialize the background model,which can easily introduce the“ghost”.Because ViBe uses the fixed segmentation threshold to achieve the foreground and background segmentation,the detection results in many false detections for the highly dynamic background.To solve these problems,an improved ghost suppression and adaptive Visual Background Extraction algorithm is proposed in this paper.Firstly,with the pixel’s temporal and spatial information,the historical pixels of a certain combination are used to initialize the background model in the odd frames of the video sequence.Secondly,the background sample set combined with the neighborhood pixels are used to determine a complex degree of the background,to acquire the adaptive segmentation threshold.Thirdly,the update rate is adjusted based on the complexity of the background.Finally,the detected result goes through a post-processing to achieve better detection results.The experimental results show that the improved algorithm will not only quickly suppress the“ghost”,but also have a better detection in a complex dynamic background.

Indoor Human Detection Based on Thermal Array Sensor Data and Adaptive Background Estimation

Low Resolution Thermal Array Sensors are widely used in several applications in indoor environments. In particular, one of these cheap, small and unobtrusive sensors provides a low-resolution thermal image of the environment and, unlike cameras;it is capable to detect human heat emission even in dark rooms. The obtained thermal data can be used to monitor older seniors while they are performing daily activities at home, to detect critical situations such as falls. Most of the studies in activity recognition using Thermal Array Sensors require human detection techniques to recognize humans passing in the sensor field of view. This paper aims to improve the accuracy of the algorithms used so far by considering the temperature environment variation. This method leverages an adaptive background estimation and a noise removal technique based on Kalman Filter. In order to properly validate the system, a novel installation of a single sensor has been implemented in a smart environment: the obtained results show an improvement in human detection accuracy with respect to the state of the art, especially in case of disturbed environments.

Adaptive moving target detection algorithm based on Gaussian mixture model

In order to enhance the reliability of the moving target detection, an adaptive moving target detection algorithm based on the Gaussian mixture model is proposed. This algorithm employs Gaussian mixture distributions in modeling the background of each pixel. As a result, the number of Gaussian distributions is not fixed but adaptively changes with the change of the pixel value frequency. The pixels of the difference image are divided into two parts according to their values. Then the two parts are separately segmented by the adaptive threshold, and finally the foreground image is obtained. The shadow elimination method based on morphological reconstruction is introduced to improve the performance of foreground image＇s segmentation. Experimental results show that the proposed algorithm can quickly and accurately build the background model and it is more robust in different real scenes.

An improved ViBe algorithm based on adaptive detection of moving targets

There exists a Ghost region in the detection result of the traditional visual background extraction(ViBe)algorithm,and the foreground extraction is prone to false detection or missed detection due to environmental changes.Therefore,an improved ViBe algorithm based on adaptive detection of moving targets was proposed.Firstly,in the background model initialization process,the real background could be obtained by setting adjusting parameters in mean background modeling,and the ViBe background model was initialized by using the background.Secondly,in the foreground detection process,an adaptive radius threshold was introduced according to the scene change to adaptively detect the foreground.Finally,mathematical morphological close operation was used to fill the holes in the detection results.The experimental results show that the improved method can effectively suppress the Ghost region and detect the foreground target more completely under the condition of environmental changes.Compared with the traditional ViBe algorithm,the detection accuracy is improved by more than 10%,the false detection rate and the missed detection rate are reduced by 20% and 7% respectively.In addition,the improved method satisfies the real-time requirements.

基于贝塞尔曲面拟合的子光斑背景噪声去除方法

受天光背景影响,夏克-哈特曼波前传感器子光斑图像背景光增强,导致子光斑质心位置无法准确提取,使得波前传感器探测精度下降。为提高强天光背景影响下波前传感器探测精度,提出了一种基于贝塞尔曲面拟合的背景噪声去除算法。该算法利用贝塞尔曲面拟合背景噪声,不受拟合基函数约束,实现背景噪声与目标光斑信号的有效分离。仿真和实验结果均表明,所提方法对背景噪声的拟合精度不受目标光斑信号的影响,在保证目标光斑信号完整的前提下,能有效拟合非均匀分布背景噪声,相比传统阈值法、加窗法等,在背信比范围为30至120的强天光背景干扰下,将波前探测精度提升约33%。

基于改进ViBe的自适应运动目标检测算法

针对ViBe算法无法去除动态背景,易出现鬼影及不能自适应光照变化的问题,提出一种复杂环境自适应的ViBe改进算法。通过计算区域的复杂度、闪烁波动度,对分类半径R和更新率T进行动态调整,对样本点进行有效性权重的计算,更高效地过滤背景噪声和适应光照渐变;在检测物体状态变化时,动态调整R和T,通过融合前景点计数和帧差法优化鬼影消除;通过识别最小外接矩阵区域差异加快去除鬼影;利用帧差法实时检测光照突变,及时进行重新初始化,避免大量误检。实验结果表明,改进ViBe算法在适应动态背景、光照变化及抑制鬼影等方面比原算法均有更好检测效果,检测精度平均提升了40.7%。

基于自适应导数-高斯寻峰算法的自动稳谱研究

航空γ能谱仪在高空测量过程中由于本底计数率较低,容易产生稳谱周期长、受温度影响较大等因素造成的谱线漂移问题,严重影响了测量结果的准确性。因此,本文提出了一种自适应导数-高斯联合寻峰算法,以达到航空γ能谱仪在低本底环境下快速寻峰、稳峰的目的。首先对导数寻峰算法的过程进行了优化,算法根据限定条件自动确定峰位道址及其左右边界,实现高斯寻峰算法的自适应变换本底窗宽扣除,然后使用高斯寻峰结果与导数寻峰结果进行对比验证,确保寻峰结果的准确性。实际测量结果表明:自适应导数-高斯联合寻峰算法计算速度快,准确率高,1024道航空γ能谱仪在-20~50℃范围内40K峰实测最大谱漂不超过±3道,为低本底环境下的航空γ能谱准确测量提供了新的稳谱方法。

融合背景先验信息及自适应采样的显著性检测

为了提高计算机视觉系统对视觉场景中显著目标的检测精度,提出了融合背景先验信息及自适应采样视觉显著性检测方法.利用超像素分割提取图像边缘获取场景先验信息,将频域高斯差分特征谱图映射到空间域生成灰度密度散点图,使采样窗口根据散点图自适应移动到前景区域,实现自适应采样.该过程模拟了人的眼动追踪检测显著目标,并采用主成分分析法融合背景先验信息和自适应采样得到的特征,综合提取前景信息获得分辨率更高的显著图.实验结果表明,与其他采样机制的对比,自适应采样方法具有高效性,在ECSSD、HUK-IS、MSRA-5K、SOD公开数据集上与其他13种显著性检测算法对比显示,在各个数据集上MAE平均减少0.01~0.04,F-measure平均提高0.01~0.04,IoU平均提高0.02~0.08,验证了所提算法在显著目标检测的准确性方面具有优势.

一种快速检测红外小目标的形态学方法

红外小目标检测是一项具有挑战性的任务,传统形态学算法在小目标检测中容易受到复杂背景噪声的影响,检测效果不佳,且结构元素大小的选择容易影响检测效果。为解决该问题,通过结合多重的形态学算子,设置自适应加权的形态学算子,提出一种高效的小目标检测算法,最后在真实红外图像上进行测试。实验结果表明,所提出的方法在定量和定性方面都优于现有技术。

一种对称帧差分约束的车辆自适应分割算法

为实现交通视频车辆目标的准确检测,提升交通事故的预防效果,提出一种对称帧差分约束下的交通视频车辆分割算法。首先,采用对称差分思想将相邻的三帧连续图像进行两次差分,提出基于自适应分布数约束的混合高斯模型背景选择更新方法,采用跳跃度和稳定度两个视频图像参数判断某一像素是否属于虚假目标点,通过背景选择更新机制实现前景目标的检测,利用自适应分布数的混合高斯模型算法提高高斯混合模型的计算效率,实现道路前景目标的准确分离。其次,对于结果图像,利用车辆阴影的特征和车辆边缘信息,提出一种基于车辆边缘修正的阴影检测与去除算法,增强复杂背景的车辆分割检测特征;然后,对于运动车辆目标通过自适应阈值进行分割,本研究在考虑类间方差的同时,考虑视频前景目标类的内聚性,将其作为阈值选取的一个标准,采用“最大方差比”自适应阈值选取算法,同时对于静止车辆目标通过背景更新筛选进行分割。最后,试验结果和对比分析表明,本研究提出算法可以将不同交通状态的车辆目标较完整、准确地分割出来,有效提高了交通场景下的不同状态车辆目标检测精度。

基于视觉理论的动态点云剔除算法

针对动态场景下构建的点云地图中包含大量动态目标的错误点云问题,提出一种基于视觉理论将三维点云转换视觉图像的动态点云剔除算法。通过对当前帧和包含动态点云的噪声地图做点云的地面分割和高度分割,将点云的深度信息转换成视觉可用的图像信息,利用视觉理论中的背景差分法对当前帧和噪声地图进行深度图像对比,筛选出初始动态点云并计算动态分数;根据动态分数对初始动态点云进行自适应最近邻搜索以剔除动态目标。实验结果表明,所提算法的动态点云剔除率可达94%以上,整体得分为96.34,能有效剔除场景中的动态目标。

国际中文教育视角下留学生跨文化适应研究——基于霍夫斯泰德文化维度理论

聚焦国际中文教育国内教学课堂,围绕跨文化适应性的文化背景因素,基于霍夫斯泰德文化维度理论分析泰国和南非来华留学生与中国学生文化背景的差异性及对教学的影响,说明国际中文教学课堂的独特性,并为提升留学生跨文化适应性的教学活动提出建议。

一种混响背景下的目标信号检测方法

研究了一种混响背景下的目标信号检测方法。通过分析相邻波束之间的相关性,在自适应干扰对消器的基础上,提出使用相邻波束作为参考的自适应混响抵消器,并使用混响数据进行仿真,验证了自适应混响抵消器在混响背景下具有良好的目标信号检测效果。

面向网络通信背景噪声的自适应滤波技术

针对网络通信背景噪声影响信号传输质量的问题,研究一种基于自适应Kalman滤波器的优化方法。首先,分析网络通信背景噪声的产生机制和特征;其次,针对传统Kalman滤波在噪声抑制中的局限性,提出一种改进的自适应Kalman滤波算法;最后,采用NS-3仿真工具构建总线通信模型,并采用所提方法对信号进行处理与分析。实验结果表明,该方法的信噪比和均方误差均优于传统Kalman滤波器,能够更准确地恢复原始信号的特征。

解耦融合机制的金属表面缺陷小样本分割网络

精准的金属表面缺陷小样本分割是工业生产制造和成本控制的重要基础.但主流遵循元学习范式的小样本分割算法利用单一原型编码特征,难以表示缺陷样本前景-背景的复杂分布,因此建立一个缓解前景-背景感知模糊的模型仍是目前的难点问题.针对上述问题,提出一个基于解耦融合机制的小样本分割网络DFMNet(decoupling fusion mechanism-based network).将缺陷分割任务解耦为已知类(缺陷区域)和基类(背景区域)2个语义分割子任务,利用基于图推理的元解析模块产生已知类的粗分割掩码,以及基于背景描述子的基类引导模块输出基类的粗分割掩码,实现对应子任务目标.引入基于解耦融合策略的信息融合模块处理两个子任务的粗预测结果,缓解前景-背景不平衡的问题,实现更精细地分割.引入基于Gram矩阵的自适应调整因子,使模型更多关注场景差异所带来的特征变化,提高模型的泛化能力.在金属表面缺陷数据集上进行实验,与现有多种小样本分割网络进行了广泛的对比分析和消融实验.结果表明,该方法有效缓解了前景-背景感知模糊的问题,达到了最先进的效果.

SPLIT-ADC BASED DIGITAL BACKGROUND CALIBRATION FOR TIME-INTERLEAVED ADC

A novel Time-Interleaved Analog-to-Digital Converter (TIADC) digital background calibration for the mismatches of offsets, gain errors, and timing skews based on split-ADC is proposed. Firstly, the split-ADC channels in present TIADC architecture are designed to convert input signal at two different channel sampling rates so that redundant channel to facilitate pair permutation is avoided. Secondly, a high-order compensation scheme for correction of timing skew error is employed for effective calibration to preserve high-resolution when input frequency is high. Numerical simulation performed by MATLAB for a 14-bit TIADC based on 7 split-ADC channels shows that Signal-to-Noise and Distortion Ratio (SNDR) and Spurious Free Dynamic Range (SFDR) of the TIADC achieve 86.2 dBc and 106 dBc respectively after calibration with normalized input frequency near Nyquist frequency.

Nonparametric VSS-APA based on precise background noise power estimate

The adaptive algorithm used for echo cancellation(EC) system needs to provide 1) low misadjustment and 2) high convergence rate. The affine projection algorithm(APA) is a better alternative than normalized least mean square(NLMS) algorithm in EC applications where the input signal is highly correlated. Since the APA with a constant step-size has to make compromise between the performance criteria 1) and 2), a variable step-size APA(VSS-APA) provides a more reliable solution. A nonparametric VSS-APA(NPVSS-APA) is proposed by recovering the background noise within the error signal instead of cancelling the a posteriori errors. The most problematic term of its variable step-size formula is the value of background noise power(BNP). The power difference between the desired signal and output signal, which equals the power of error signal statistically, has been considered the BNP estimate in a rough manner. Considering that the error signal consists of background noise and misalignment noise, a precise BNP estimate is achieved by multiplying the rough estimate with a corrective factor. After the analysis on the power ratio of misalignment noise to background noise of APA, the corrective factor is formulated depending on the projection order and the latest value of variable step-size. The new algorithm which does not require any a priori knowledge of EC environment has the advantage of easier controllability in practical application. The simulation results in the EC context indicate the accuracy of the proposed BNP estimate and the more effective behavior of the proposed algorithm compared with other versions of APA class.

面向单一背景的改进RetinaNet目标检测方法研究

基于深度学习的目标检测算法在工业缺陷检测领域得到了充分推广与应用,但少有适用于工业检测场景中单一背景的算法。文中以工业检测场景中具有大量简单重复背景为出发点,对RetinaNet算法进行了如下改进:1)引入难负样本挖掘策略,减小了大量简单重复负样本对对模型拟合正样本的影响;2)设计了自适应忽略样本选择策略,避免与正样本交并比高的样本混入负样本而混淆模型训练;3)简化了RetinaNet的分类子网络,降低了模型改进后的过拟合风险。在公开的PCB缺失孔数据集及自建的LED气泡数据集上,相比RetinaNet算法,改进后的方法在召回率上分别提升了14.1%和1.8%,在精确率上分别提升了3.6%和0.4%,表明改进后的方法能显著提升单一背景下的目标检测水平。

基于引导滤波和分块自适应阈值的单帧红外弱小目标检测

为了在有效地检测复杂场景下红外弱小目标的同时保持较低虚警率,在满足算法实现实时性的前提下,提出一种基于引导滤波和分块自适应阈值的单帧红外弱小目标检测。首先,为缓解边缘杂波干扰,采用具有保边特性的引导滤波对图像进行背景估计;然后,利用弱小目标具备的局部灰度最大特性,提出基于软阈值非极大值抑制的九宫格滤波计算目标的概率。通过加权的方式进一步剔除背景,抑制结果中不满足目标特性的区域;最后,针对复杂场景目标检测虚警率和漏检率高的问题,提出一种分块自适应阈值分割方法提取候选目标。实验结果表明,在公开数据集上与Top-Hat、LCM和Max-Median等经典方法相比,所提方法性能优于其他方法,恒虚警下不同复杂度场景的召回率分别达到87.97%、84.93%和86.22%,可有效抑制背景,增强目标信号,提高红外弱小目标检测的召回率,且具有更好的场景鲁棒性。

层次卷积滤波红外弱小目标检测方法

针对单帧复杂背景红外图像点目标检测算法存在复杂背景下处理效果不理想、处理时间长的问题,提出了一种层次卷积滤波检测算法。主要分为两个部分:第一,根据红外小目标特性,设计一种层次卷积滤波的算子,对图像进行滤波处理,实现图像中小目标的增效和背景抑制的效果;第二,采用基于最大值的自适应阈值方法,对图像进行二值化操作,过滤背景杂波,最终提取到待检测的目标。在大量不同背景红外图像中进行实验,论文算法在背景抑制因子和信噪比增益的性能量化结果上优于现有5种典型红外弱小目标检测算法的性能结果,且平均处理时间仅为高斯拉普拉斯(Laplacian of Gaussian,LoG)滤波算法的30.42%。通过实验对比,表明该层次卷积滤波算法可以有效解决在不同复杂背景下的红外图像中对小目标检测的问题。