Overlooking the issue of false alarm suppression in heterogeneous change detection leads to inferior detection per-formance.This paper proposes a method to handle false alarms in heterogeneous change detection.A light...Overlooking the issue of false alarm suppression in heterogeneous change detection leads to inferior detection per-formance.This paper proposes a method to handle false alarms in heterogeneous change detection.A lightweight network of two channels is bulit based on the combination of convolutional neural network(CNN)and graph convolutional network(GCN).CNNs learn feature difference maps of multitemporal images,and attention modules adaptively fuse CNN-based and graph-based features for different scales.GCNs with a new kernel filter adaptively distinguish between nodes with the same and those with different labels,generating change maps.Experimental evaluation on two datasets validates the efficacy of the pro-posed method in addressing false alarms.展开更多
The detection of outliers and change points from time series has become research focus in the area of time series data mining since it can be used for fraud detection, rare event discovery, event/trend change detectio...The detection of outliers and change points from time series has become research focus in the area of time series data mining since it can be used for fraud detection, rare event discovery, event/trend change detection, etc. In most previous works, outlier detection and change point detection have not been related explicitly and the change point detections did not consider the influence of outliers, in this work, a unified detection framework was presented to deal with both of them. The framework is based on ALARCON-AQUINO and BARRIA's change points detection method and adopts two-stage detection to divide the outliers and change points. The advantages of it lie in that: firstly, unified structure for change detection and outlier detection further reduces the computational complexity and make the detective procedure simple; Secondly, the detection strategy of outlier detection before change point detection avoids the influence of outliers to the change point detection, and thus improves the accuracy of the change point detection. The simulation experiments of the proposed method for both model data and actual application data have been made and gotten 100% detection accuracy. The comparisons between traditional detection method and the proposed method further demonstrate that the unified detection structure is more accurate when the time series are contaminated by outliers.展开更多
A performance assisted enhancement Kalman filtering algorithm(PAE-KF) for GPS/INS integration navigation in urban areas was presented in this work. The aim of this PAE-KF algorithm was to prevent "deep contaminat...A performance assisted enhancement Kalman filtering algorithm(PAE-KF) for GPS/INS integration navigation in urban areas was presented in this work. The aim of this PAE-KF algorithm was to prevent "deep contamination" caused by error GPS data. This filtering algorithm effectively combined fault estimation of raw GPS data and nonholonomic constraint of vehicle. In fault estimation, a change point detection algorithm based on abrupt change model was proposed. Statistical tool was then used to infer the future bound of GPS data, which can detect faults in GPS raw data. If any kinds of faults were detected, dead reckoning mechanism begins to compute current position. Nonholonomic constraint condition of vehicle was used to estimate velocity of vehicle and change point detection was added into classic Kalman filtering structure. Experiment on vehicle shows that even when the GPS signals are unavailable for a period of time, this method can also output high accuracy data.展开更多
Coherent change detection(CCD) is an effective method to detect subtle scene changes that occur between temporal synthetic aperture radar(SAR) observations. Most coherence estimators are obtained from a Hermitian prod...Coherent change detection(CCD) is an effective method to detect subtle scene changes that occur between temporal synthetic aperture radar(SAR) observations. Most coherence estimators are obtained from a Hermitian product based on local statistics. Increasing the number of samples in the local window can improve the estimation bias, but cause the loss of the estimated images spatial resolution. The limitations of these estimators lead to unclear contour of the disturbed region, and even the omission of fine change targets. In this paper, a CCD approach is proposed to detect fine scene changes from multi-temporal and multi-angle SAR image pairs. Multi-angle CCD estimator can improve the contrast between the change target and the background clutter by jointly accumulating singleangle alternative estimator results without further loss of image resolution. The sensitivity of detection performance to image quantity and angle interval is analyzed. Theoretical analysis and experimental results verify the performance of the proposed algorithm.展开更多
Constrained by complex imaging mechanism and extraordinary visual appearance,change detection with synthetic aperture radar(SAR)images has been a difficult research topic,especially in urban areas.Although existing st...Constrained by complex imaging mechanism and extraordinary visual appearance,change detection with synthetic aperture radar(SAR)images has been a difficult research topic,especially in urban areas.Although existing studies have extended from bi-temporal data pair to multi-temporal datasets to derive more plentiful information,there are still two problems to be solved in practical applications.First,change indicators constructed from incoherent feature only cannot characterize the change objects accurately.Second,the results of pixel-level methods are usually presented in the form of the noisy binary map,making the spatial change not intuitive and the temporal change of a single pixel meaningless.In this study,we propose an unsupervised man-made objects change detection framework using both coherent and incoherent features derived from multi-temporal SAR images.The coefficients of variation in timeseries incoherent features and the man-made object index(MOI)defined with coherent features are first combined to identify the initial change pixels.Afterwards,an improved spatiotemporal clustering algorithm is developed based on density-based spatial clustering of applications with noise(DBSCAN)and dynamic time warping(DTW),which can transform the initial results into noiseless object-level patches,and take the cluster center as a representative of the man-made object to determine the change pattern of each patch.An experiment with a stack of 10 TerraSAR-X images in Stripmap mode demonstrated that this method is effective in urban scenes and has the potential applicability to wide area change detection.展开更多
Synthetic aperture radar(SAR) is able to detect surface changes in urban areas with a short revisit time, showing its capability in disaster assessment and urbanization monitoring.Most presented change detection metho...Synthetic aperture radar(SAR) is able to detect surface changes in urban areas with a short revisit time, showing its capability in disaster assessment and urbanization monitoring.Most presented change detection methods are conducted using couples of SAR amplitude images. However, a prior date of surface change is required to select a feasible image pair. We propose an automatic spatio-temporal change detection method by identifying the temporary coherent scatterers. Based on amplitude time series, χ^(2)-test and iterative single pixel change detection are proposed to identify all step-times: the moments of the surface change. Then the parameters, e.g., deformation velocity and relative height, are estimated and corresponding coherent periods are identified by using interferometric phase time series. With identified temporary coherent scatterers, different types of temporal surface changes can be classified using the location of the coherent periods and spatial significant changes are identified combining point density and F values. The main advantage of our method is automatically detecting spatio-temporal surface changes without prior information. Experimental results by the proposed method show that both appearing and disappearing buildings with their step-times are successfully identified and results by ascending and descending SAR images show a good agreement.展开更多
多编码器和单解码器(multi encoder and single decoder,MESD)架构在变化检测中取得了成功,但在编码过程中平衡全局和局部特征方面面临挑战,导致特征表示不足。此外,这些方法通常依赖于单一解码器来解释来自多个编码器的信息,这可能无...多编码器和单解码器(multi encoder and single decoder,MESD)架构在变化检测中取得了成功,但在编码过程中平衡全局和局部特征方面面临挑战,导致特征表示不足。此外,这些方法通常依赖于单一解码器来解释来自多个编码器的信息,这可能无法充分利用所提供的丰富多样的信息,从而影响最终变化检测结果的准确性和精度。针对这些问题,提出一种交互式多编码器和多解码器网络,该网络利用交互式编码器来提取局部和全局特征,交互式编码器由卷积神经网络(convolutional neural network,CNN)和Transformer组成,并通过特征通信模块增强它们的交互。全局和局部差异解码器分别处理来自双时相图像的局部和全局特征,专注于特定类型的差异特征。最后,设计了空间-通道差异融合模块在空间和通道维度上自适应地融合局部和全局解码器获取的差异特征,以增强相关变化。与现有基于MESD网络的先进方法(ChangeForm)相比,该文所提算法在LEVIR-CD、WHU-CD和DESIF-CD数据集上分别获得了1.14%、5.68%和6.5%的F1分数提升。展开更多
智能车辆人机协作的关键是以人为核心,换道作为最基本的驾驶任务之一,准确高效预测驾驶人换道意图对人机协作拟人化发展至关重要。本文基于驾驶人认知决策空间的理论,设计了驾驶人换道意图预测试验,分析了车辆操纵数据、驾驶人视觉特性...智能车辆人机协作的关键是以人为核心,换道作为最基本的驾驶任务之一,准确高效预测驾驶人换道意图对人机协作拟人化发展至关重要。本文基于驾驶人认知决策空间的理论,设计了驾驶人换道意图预测试验,分析了车辆操纵数据、驾驶人视觉特性与驾驶场景之间的关系,生成了驾驶人注视区与驾驶场景拓扑关系图,构建了不同时间窗口的驾驶人换道意图预测模型数据集,基于ConvNeXt(convolutional network)模型的逆残差深度可分离卷积,结合注意力机制ECA(efficient channel attention)、ConvLSTM(convolutional long short term memory)网络以及GCN(graph convolutional networks)图神经网络等结构,构建了基于注意力机制的驾驶人换道意图预测模型。结果表明,数据集时间宽度为3 s时模型的预测准确率表现最佳,为91.15%,通过对比试验、消融试验充分验证了所提出的基于注意力机制的驾驶人换道意图预测模型的优越性能。展开更多
基金This work was supported by the Natural Science Foundation of Heilongjiang Province(LH2022F049).
文摘Overlooking the issue of false alarm suppression in heterogeneous change detection leads to inferior detection per-formance.This paper proposes a method to handle false alarms in heterogeneous change detection.A lightweight network of two channels is bulit based on the combination of convolutional neural network(CNN)and graph convolutional network(GCN).CNNs learn feature difference maps of multitemporal images,and attention modules adaptively fuse CNN-based and graph-based features for different scales.GCNs with a new kernel filter adaptively distinguish between nodes with the same and those with different labels,generating change maps.Experimental evaluation on two datasets validates the efficacy of the pro-posed method in addressing false alarms.
基金Project(2011AA040603) supported by the National High Technology Ressarch & Development Program of ChinaProject(201202226) supported by the Natural Science Foundation of Liaoning Province, China
文摘The detection of outliers and change points from time series has become research focus in the area of time series data mining since it can be used for fraud detection, rare event discovery, event/trend change detection, etc. In most previous works, outlier detection and change point detection have not been related explicitly and the change point detections did not consider the influence of outliers, in this work, a unified detection framework was presented to deal with both of them. The framework is based on ALARCON-AQUINO and BARRIA's change points detection method and adopts two-stage detection to divide the outliers and change points. The advantages of it lie in that: firstly, unified structure for change detection and outlier detection further reduces the computational complexity and make the detective procedure simple; Secondly, the detection strategy of outlier detection before change point detection avoids the influence of outliers to the change point detection, and thus improves the accuracy of the change point detection. The simulation experiments of the proposed method for both model data and actual application data have been made and gotten 100% detection accuracy. The comparisons between traditional detection method and the proposed method further demonstrate that the unified detection structure is more accurate when the time series are contaminated by outliers.
基金Projects(90820302,60805027)supported by the National Natural Science Foundation of ChinaProject(2011BAK15B06)supported by the National Science and Technology Support Program,China+1 种基金Project(2013M541003)supported by the China Postdoctoral Science FoundationProject(2012YQ090208)supported by the Special-Funded Program on National Key Scientific Instruments and Equipment Development
文摘A performance assisted enhancement Kalman filtering algorithm(PAE-KF) for GPS/INS integration navigation in urban areas was presented in this work. The aim of this PAE-KF algorithm was to prevent "deep contamination" caused by error GPS data. This filtering algorithm effectively combined fault estimation of raw GPS data and nonholonomic constraint of vehicle. In fault estimation, a change point detection algorithm based on abrupt change model was proposed. Statistical tool was then used to infer the future bound of GPS data, which can detect faults in GPS raw data. If any kinds of faults were detected, dead reckoning mechanism begins to compute current position. Nonholonomic constraint condition of vehicle was used to estimate velocity of vehicle and change point detection was added into classic Kalman filtering structure. Experiment on vehicle shows that even when the GPS signals are unavailable for a period of time, this method can also output high accuracy data.
文摘Coherent change detection(CCD) is an effective method to detect subtle scene changes that occur between temporal synthetic aperture radar(SAR) observations. Most coherence estimators are obtained from a Hermitian product based on local statistics. Increasing the number of samples in the local window can improve the estimation bias, but cause the loss of the estimated images spatial resolution. The limitations of these estimators lead to unclear contour of the disturbed region, and even the omission of fine change targets. In this paper, a CCD approach is proposed to detect fine scene changes from multi-temporal and multi-angle SAR image pairs. Multi-angle CCD estimator can improve the contrast between the change target and the background clutter by jointly accumulating singleangle alternative estimator results without further loss of image resolution. The sensitivity of detection performance to image quantity and angle interval is analyzed. Theoretical analysis and experimental results verify the performance of the proposed algorithm.
基金supported by the National Natural Science Foundation of China(41774006)the Comparative Study of Geo-environment and Geohazards in the Yangtze River Delta and the Red River Delta Projectthe Shanghai Science and Technology Development Foundation(20dz1201200)。
文摘Constrained by complex imaging mechanism and extraordinary visual appearance,change detection with synthetic aperture radar(SAR)images has been a difficult research topic,especially in urban areas.Although existing studies have extended from bi-temporal data pair to multi-temporal datasets to derive more plentiful information,there are still two problems to be solved in practical applications.First,change indicators constructed from incoherent feature only cannot characterize the change objects accurately.Second,the results of pixel-level methods are usually presented in the form of the noisy binary map,making the spatial change not intuitive and the temporal change of a single pixel meaningless.In this study,we propose an unsupervised man-made objects change detection framework using both coherent and incoherent features derived from multi-temporal SAR images.The coefficients of variation in timeseries incoherent features and the man-made object index(MOI)defined with coherent features are first combined to identify the initial change pixels.Afterwards,an improved spatiotemporal clustering algorithm is developed based on density-based spatial clustering of applications with noise(DBSCAN)and dynamic time warping(DTW),which can transform the initial results into noiseless object-level patches,and take the cluster center as a representative of the man-made object to determine the change pattern of each patch.An experiment with a stack of 10 TerraSAR-X images in Stripmap mode demonstrated that this method is effective in urban scenes and has the potential applicability to wide area change detection.
基金supported by the National Natural Science Foundation of China (42074022)。
文摘Synthetic aperture radar(SAR) is able to detect surface changes in urban areas with a short revisit time, showing its capability in disaster assessment and urbanization monitoring.Most presented change detection methods are conducted using couples of SAR amplitude images. However, a prior date of surface change is required to select a feasible image pair. We propose an automatic spatio-temporal change detection method by identifying the temporary coherent scatterers. Based on amplitude time series, χ^(2)-test and iterative single pixel change detection are proposed to identify all step-times: the moments of the surface change. Then the parameters, e.g., deformation velocity and relative height, are estimated and corresponding coherent periods are identified by using interferometric phase time series. With identified temporary coherent scatterers, different types of temporal surface changes can be classified using the location of the coherent periods and spatial significant changes are identified combining point density and F values. The main advantage of our method is automatically detecting spatio-temporal surface changes without prior information. Experimental results by the proposed method show that both appearing and disappearing buildings with their step-times are successfully identified and results by ascending and descending SAR images show a good agreement.
文摘多编码器和单解码器(multi encoder and single decoder,MESD)架构在变化检测中取得了成功,但在编码过程中平衡全局和局部特征方面面临挑战,导致特征表示不足。此外,这些方法通常依赖于单一解码器来解释来自多个编码器的信息,这可能无法充分利用所提供的丰富多样的信息,从而影响最终变化检测结果的准确性和精度。针对这些问题,提出一种交互式多编码器和多解码器网络,该网络利用交互式编码器来提取局部和全局特征,交互式编码器由卷积神经网络(convolutional neural network,CNN)和Transformer组成,并通过特征通信模块增强它们的交互。全局和局部差异解码器分别处理来自双时相图像的局部和全局特征,专注于特定类型的差异特征。最后,设计了空间-通道差异融合模块在空间和通道维度上自适应地融合局部和全局解码器获取的差异特征,以增强相关变化。与现有基于MESD网络的先进方法(ChangeForm)相比,该文所提算法在LEVIR-CD、WHU-CD和DESIF-CD数据集上分别获得了1.14%、5.68%和6.5%的F1分数提升。
文摘智能车辆人机协作的关键是以人为核心,换道作为最基本的驾驶任务之一,准确高效预测驾驶人换道意图对人机协作拟人化发展至关重要。本文基于驾驶人认知决策空间的理论,设计了驾驶人换道意图预测试验,分析了车辆操纵数据、驾驶人视觉特性与驾驶场景之间的关系,生成了驾驶人注视区与驾驶场景拓扑关系图,构建了不同时间窗口的驾驶人换道意图预测模型数据集,基于ConvNeXt(convolutional network)模型的逆残差深度可分离卷积,结合注意力机制ECA(efficient channel attention)、ConvLSTM(convolutional long short term memory)网络以及GCN(graph convolutional networks)图神经网络等结构,构建了基于注意力机制的驾驶人换道意图预测模型。结果表明,数据集时间宽度为3 s时模型的预测准确率表现最佳,为91.15%,通过对比试验、消融试验充分验证了所提出的基于注意力机制的驾驶人换道意图预测模型的优越性能。
