针对复杂背景条件下较难完成掩埋式地雷目标红外图像分割的问题,利用地雷外形特征和雷场多个地雷目标相似的特点,提出了一种基于形态学和聚类算法的感兴趣区域(Region of Interest,ROI)选取方法。对原始图像消除噪声并通过差分形态滤波...针对复杂背景条件下较难完成掩埋式地雷目标红外图像分割的问题,利用地雷外形特征和雷场多个地雷目标相似的特点,提出了一种基于形态学和聚类算法的感兴趣区域(Region of Interest,ROI)选取方法。对原始图像消除噪声并通过差分形态滤波抑制背景后,缩小了目标所在区域的范围;再利用多目标在一定区域内的相似特征对可疑区域进行聚类过滤,进一步缩小目标所在范围并将其作为图像ROI分别进行阈值分割;最后根据目标的相关特征完成识别。对实测图像的处理结果表明,该方法对掩埋式多地雷目标具有较好的分割效果和较高的定位精度,同时算法的计算速度较快,能满足实际探雷需求。展开更多
A television based multistatic radar system is described. The commercial television transmitter is used as the illuminator in the multistatic radar system. The reflected commercial television signals are measured by ...A television based multistatic radar system is described. The commercial television transmitter is used as the illuminator in the multistatic radar system. The reflected commercial television signals are measured by an array of sensors. A data processing scheme is developed that adapts to the poor signal processing ability. The innovation is focused on the construction of the observation space, which could reduce the non linearity error. The new method leads to better system stability than the traditional one. Monte Carlo simulation is utilized and compared with the traditional method.展开更多
Due to the disturbances arising from the coherence of reflected waves and from echo noise,problems such as limitations,instability and poor accuracy exist with the current quantitative analysis methods.According to th...Due to the disturbances arising from the coherence of reflected waves and from echo noise,problems such as limitations,instability and poor accuracy exist with the current quantitative analysis methods.According to the intrinsic features of GPR signals and wavelet time–frequency analysis,an optimal wavelet basis named GPR3.3 wavelet is constructed via an improved biorthogonal wavelet construction method to quantitatively analyse the GPR signal.A new quantitative analysis method based on the biorthogonal wavelet(the QAGBW method)is proposed and applied in the analysis of analogue and measured signals.The results show that compared with the Bayesian frequency-domain blind deconvolution and with existing wavelet bases,the QAGBW method based on optimal wavelet can limit the disturbance from factors such as the coherence of reflected waves and echo noise,improve the quantitative analytical precision of the GPR signal,and match the minimum thickness for quantitative analysis with the vertical resolution of GPR detection.展开更多
Soil structure plays an important role in understanding soil attributes as well as hydrological processes. Effective method to obtain high quality soil map is therefore important for both soil science research and soi...Soil structure plays an important role in understanding soil attributes as well as hydrological processes. Effective method to obtain high quality soil map is therefore important for both soil science research and soil work ability improvement. However,traditional method such as digging soil pits is destructive and time-consuming. In this study, the structure of headwater hillslopes from Hemuqiao catchment(Taihu Basin, China) have been analyzed both by indirect(ground penetrating radar, GPR) and direct(excavation or soil auger) methods. Four transects at different locations of hillslopes in the catchment were selected for GPR survey. Three of them(#1, #2, and #3) were excavated to obtain fullscale soil information for interpreting radar images.We found that the most distinct boundary that can be detected by GPR is the boundary between soil and underlain bedrock. In some cases(e.g., 8-17 m in transect #2), in which the in situ soil was scarcely affected by colluvial process, different soil layers can be identified. This identification process utilized the sensitive of GPR to capture abrupt changes of soil characteristics in layer boundaries, e.g., surface organic layer(layer #1) and bamboo roots layer(layer#2, contain stone fragments), illuvial deposits layer(layer #3) and regolith layer(layer #4). However, in areas where stone fragments were irregularly distributed in the soil profile(highly affected bycolluvial and/or fluvial process), it was possible to distinguish which part contains more stone fragments in soil profile on the basis of reflection density(transect #3). Transect #4(unexcavated) was used to justify the GPR method for soil survey based on experiences from former transects. After that, O horizon thickness was compared by a hand auger.This work has demonstrated that GPR images can be of a potential data source for hydrological predictions.展开更多
The use of vehicle- or air-borne Ground Penetrating Synthetic Aperture Radar (GPSAR) to quickly detect landmines over large areas is becoming a trend. However, producing too many false alarms in GPSAR landmine detecti...The use of vehicle- or air-borne Ground Penetrating Synthetic Aperture Radar (GPSAR) to quickly detect landmines over large areas is becoming a trend. However, producing too many false alarms in GPSAR landmine detection is a major challenge in practical applications of GPSAR. Support Vector Machine (SVM), employing structural risk minimization theory, does not need large amounts of training data, which makes it suitable for solving the landmine detection problem. In this paper, a novel SVM with a hypersphere instead of a hyperplane classification boundary is proposed for landmine detection in GPSAR. The HyperSphere-SVM (HS-SVM) can be trained with both landmine and clutter data, or with landmine data only, which are called the two-class HS-SVM and the one-class HS-SVM, respectively. The HS-SVM has better generalization capability than the traditional HyperPlane-SVM (HP-SVM) with respect to varying operating conditions. Quantitative comparisons have been made using real data collected with the rail-GPSAR landmine detection system, which show that both the two-class and the one-class HS-SVMs have better detection performance than the HP-SVM.展开更多
This study consists to the detection of cavities that could be present over abandoned mines of Albania with the use of SP （self potential） and ERT （electrical resistance tomography）. In general, natural and artifi...This study consists to the detection of cavities that could be present over abandoned mines of Albania with the use of SP （self potential） and ERT （electrical resistance tomography）. In general, natural and artificial cavities represent an important investigation target in geotechnical, environmental and scientific studies. These studies could be engineering, archaeological or speleological. For the detection and localization of such cavities during the last 20 years, several geophysical studies have been used worldwide. In this field study, several geophysical methods could be used such as electrical, electromagnetic, gravimetric and seismic ones. Now days, the ground penetrating radar technique and ERT are widely used. Depending on geological formation conditions every used method is more or less effective. As a result of actual conditions of works on ore mines, the dynamic regime of the surroundings areas has undergone changes creating superficial cavities and funnels and as consequence the geological risk to the community is present. The detection of cavities is a challenge for geophysicists and in these cases the ambiguity on interpretation of geophysical data has to be solved properly. The simultaneous application of different geophysical methods and monitoring in time are necessary in order that the field data interpretation could be significant. Geophysical investigations were carried out as tests over galleries of ore mines of Albania. In this study, we present the SP and ERT results in two sites, in Dhrovjan and Perrenjas region. The effectiveness of the used geophysical methods was present.展开更多
文摘针对复杂背景条件下较难完成掩埋式地雷目标红外图像分割的问题,利用地雷外形特征和雷场多个地雷目标相似的特点,提出了一种基于形态学和聚类算法的感兴趣区域(Region of Interest,ROI)选取方法。对原始图像消除噪声并通过差分形态滤波抑制背景后,缩小了目标所在区域的范围;再利用多目标在一定区域内的相似特征对可疑区域进行聚类过滤,进一步缩小目标所在范围并将其作为图像ROI分别进行阈值分割;最后根据目标的相关特征完成识别。对实测图像的处理结果表明,该方法对掩埋式多地雷目标具有较好的分割效果和较高的定位精度,同时算法的计算速度较快,能满足实际探雷需求。
文摘A television based multistatic radar system is described. The commercial television transmitter is used as the illuminator in the multistatic radar system. The reflected commercial television signals are measured by an array of sensors. A data processing scheme is developed that adapts to the poor signal processing ability. The innovation is focused on the construction of the observation space, which could reduce the non linearity error. The new method leads to better system stability than the traditional one. Monte Carlo simulation is utilized and compared with the traditional method.
基金Projects(51678071,51278071)supported by the National Natural Science Foundation of ChinaProjects(14KC06,CX2015BS02)supported by Changsha University of Science&Technology,China
文摘Due to the disturbances arising from the coherence of reflected waves and from echo noise,problems such as limitations,instability and poor accuracy exist with the current quantitative analysis methods.According to the intrinsic features of GPR signals and wavelet time–frequency analysis,an optimal wavelet basis named GPR3.3 wavelet is constructed via an improved biorthogonal wavelet construction method to quantitatively analyse the GPR signal.A new quantitative analysis method based on the biorthogonal wavelet(the QAGBW method)is proposed and applied in the analysis of analogue and measured signals.The results show that compared with the Bayesian frequency-domain blind deconvolution and with existing wavelet bases,the QAGBW method based on optimal wavelet can limit the disturbance from factors such as the coherence of reflected waves and echo noise,improve the quantitative analytical precision of the GPR signal,and match the minimum thickness for quantitative analysis with the vertical resolution of GPR detection.
基金supported by the National Nature Science Foundation of China (Grants No. 41271040, 51190091)The Special Fund of State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering (Grant No. 20145028012)
文摘Soil structure plays an important role in understanding soil attributes as well as hydrological processes. Effective method to obtain high quality soil map is therefore important for both soil science research and soil work ability improvement. However,traditional method such as digging soil pits is destructive and time-consuming. In this study, the structure of headwater hillslopes from Hemuqiao catchment(Taihu Basin, China) have been analyzed both by indirect(ground penetrating radar, GPR) and direct(excavation or soil auger) methods. Four transects at different locations of hillslopes in the catchment were selected for GPR survey. Three of them(#1, #2, and #3) were excavated to obtain fullscale soil information for interpreting radar images.We found that the most distinct boundary that can be detected by GPR is the boundary between soil and underlain bedrock. In some cases(e.g., 8-17 m in transect #2), in which the in situ soil was scarcely affected by colluvial process, different soil layers can be identified. This identification process utilized the sensitive of GPR to capture abrupt changes of soil characteristics in layer boundaries, e.g., surface organic layer(layer #1) and bamboo roots layer(layer#2, contain stone fragments), illuvial deposits layer(layer #3) and regolith layer(layer #4). However, in areas where stone fragments were irregularly distributed in the soil profile(highly affected bycolluvial and/or fluvial process), it was possible to distinguish which part contains more stone fragments in soil profile on the basis of reflection density(transect #3). Transect #4(unexcavated) was used to justify the GPR method for soil survey based on experiences from former transects. After that, O horizon thickness was compared by a hand auger.This work has demonstrated that GPR images can be of a potential data source for hydrological predictions.
文摘The use of vehicle- or air-borne Ground Penetrating Synthetic Aperture Radar (GPSAR) to quickly detect landmines over large areas is becoming a trend. However, producing too many false alarms in GPSAR landmine detection is a major challenge in practical applications of GPSAR. Support Vector Machine (SVM), employing structural risk minimization theory, does not need large amounts of training data, which makes it suitable for solving the landmine detection problem. In this paper, a novel SVM with a hypersphere instead of a hyperplane classification boundary is proposed for landmine detection in GPSAR. The HyperSphere-SVM (HS-SVM) can be trained with both landmine and clutter data, or with landmine data only, which are called the two-class HS-SVM and the one-class HS-SVM, respectively. The HS-SVM has better generalization capability than the traditional HyperPlane-SVM (HP-SVM) with respect to varying operating conditions. Quantitative comparisons have been made using real data collected with the rail-GPSAR landmine detection system, which show that both the two-class and the one-class HS-SVMs have better detection performance than the HP-SVM.
文摘This study consists to the detection of cavities that could be present over abandoned mines of Albania with the use of SP （self potential） and ERT （electrical resistance tomography）. In general, natural and artificial cavities represent an important investigation target in geotechnical, environmental and scientific studies. These studies could be engineering, archaeological or speleological. For the detection and localization of such cavities during the last 20 years, several geophysical studies have been used worldwide. In this field study, several geophysical methods could be used such as electrical, electromagnetic, gravimetric and seismic ones. Now days, the ground penetrating radar technique and ERT are widely used. Depending on geological formation conditions every used method is more or less effective. As a result of actual conditions of works on ore mines, the dynamic regime of the surroundings areas has undergone changes creating superficial cavities and funnels and as consequence the geological risk to the community is present. The detection of cavities is a challenge for geophysicists and in these cases the ambiguity on interpretation of geophysical data has to be solved properly. The simultaneous application of different geophysical methods and monitoring in time are necessary in order that the field data interpretation could be significant. Geophysical investigations were carried out as tests over galleries of ore mines of Albania. In this study, we present the SP and ERT results in two sites, in Dhrovjan and Perrenjas region. The effectiveness of the used geophysical methods was present.
