The development of an efficient moving target detection algorithm in IR-image sequence is considered one of the most critical research fields in modern IRST (Infrared Search and Track) systems, especially when dealing...The development of an efficient moving target detection algorithm in IR-image sequence is considered one of the most critical research fields in modern IRST (Infrared Search and Track) systems, especially when dealing with moving dim point targets. In this paper we propose a new approach in processing of the Infrared image sequence for moving dim point targets detection built on the transformation of the IR-image sequence into 4-vectors for each frame in the sequence. The results of testing the proposed approach on a set of frames having a simple single pixel target performing a different motion patterns show the validity of the approach for detecting the motion, with simplicity in calculation and low time consumption.展开更多
Dim target detection from sea clutter is one of the difficult topics in ocean remote sensing application. By aiming at the shortcoming of false alarms when using track before detect （TBD） based on dynamic programmin...Dim target detection from sea clutter is one of the difficult topics in ocean remote sensing application. By aiming at the shortcoming of false alarms when using track before detect （TBD） based on dynamic programming, a new discrimination method called statistics of direction histogram （SDH） is proposed, which is based on different features of trajectories between the true target and false one. Moreover, a new series of discrimination schemes of SDH and Local Extreme Value method （LEV） are studied and applied to simulate the actually measured radar data. The results show that the given discrimination is effective to reduce false alarms during dim targets detection.展开更多
The performance of the three-dimensional differential geometric guidance law with proportional navigation formation against a target maneuvering arbitrarily with time-varying normal acceleration is thoroughly analyzed...The performance of the three-dimensional differential geometric guidance law with proportional navigation formation against a target maneuvering arbitrarily with time-varying normal acceleration is thoroughly analyzed using the Lyapunov-like approach.The validation of this guidance law is firstly proved,and then the performance issues such as capturability,heading error control efficiency,line of sight rate convergence,and commanded acceleration requirement are analyzed,under the condition that the missile is initially flying toward the target with a speed advantage.It is proved that an intercept can occur and the line of sight rate and missile commanded acceleration can be limited in certain ranges,if the initial heading error is small and the navigation gain is sufficiently large.The nonlinear relative dynamics between the missile and the target is taken into full account,and the analysis process is simple and intuitive,due to the use of a convenient line of sight rotating coordinate system.Finally,the new theoretical findings are validated by numerical simulations.展开更多
多视觉传感器协同对空实现全区域覆盖的弱小目标检测,在近距离防空领域中具有重要意义。现有的全区域覆盖方法存在覆盖率低、随机性差等问题,弱小目标检测算法存在模型大、定位及分类准确性低等问题。提出了一种高效的对空全区域覆盖算...多视觉传感器协同对空实现全区域覆盖的弱小目标检测,在近距离防空领域中具有重要意义。现有的全区域覆盖方法存在覆盖率低、随机性差等问题,弱小目标检测算法存在模型大、定位及分类准确性低等问题。提出了一种高效的对空全区域覆盖算法和轻量级弱小目标检测算法,通过结合最大面积优先法和最小曼哈顿离法改善存在覆盖死角和随机性差等问题。提出密集通道扩展网络(dense and channel expand network,DCENet)模型,基于轻量级稠密拼接和自适应尺寸通道扩展方法,在弱小目标数据集上获得了比原算法更有竞争力的平均精度结果。展开更多
针对复杂背景下红外场景对比度低、特征不足、细节不清而导致的目标检测效率低的问题,在YOLOv5s模型基础上通过创建TCC(two-way convolution and Concat)模块并引入华为Ghost模块,提出了一种基于改进YOLOv5s模型的红外弱小目标检测方法...针对复杂背景下红外场景对比度低、特征不足、细节不清而导致的目标检测效率低的问题,在YOLOv5s模型基础上通过创建TCC(two-way convolution and Concat)模块并引入华为Ghost模块,提出了一种基于改进YOLOv5s模型的红外弱小目标检测方法。首先,结合红外图像的低级语义特征,采取二路卷积和多尺度思想创建了TCC模块,提升了特征提取的全面性;接着,为进一步简化网络结构、减少网络参数量,引入轻量化Ghost模块改进了SPP池化层和CSP2卷积网络;最后,以无人机为实验对象,构建了白天和夜间不同背景条件下的红外弱小目标数据集,实验验证了本文改进算法的有效性。结果表明:改进后的YOLOv5s模型在较少损失帧频的情况下,检测精度提升了1.34%,平均精度均值(mean average precision, mAP)提升了2.26%,优于YOLOv4-tiny和YOLOv7-tiny两种轻量化模型,并与YOLOv8s模型精度相当,但模型参数量仅为YOLOv8s模型的53%,完全可以满足嵌入式设备部署的需求。展开更多
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...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。展开更多
文摘The development of an efficient moving target detection algorithm in IR-image sequence is considered one of the most critical research fields in modern IRST (Infrared Search and Track) systems, especially when dealing with moving dim point targets. In this paper we propose a new approach in processing of the Infrared image sequence for moving dim point targets detection built on the transformation of the IR-image sequence into 4-vectors for each frame in the sequence. The results of testing the proposed approach on a set of frames having a simple single pixel target performing a different motion patterns show the validity of the approach for detecting the motion, with simplicity in calculation and low time consumption.
基金supported by the National Natural Science Foundation of China(Grant No.61001137)the Pre-Research Foundation(Grant No.9140A07020311HK0116)
文摘Dim target detection from sea clutter is one of the difficult topics in ocean remote sensing application. By aiming at the shortcoming of false alarms when using track before detect （TBD） based on dynamic programming, a new discrimination method called statistics of direction histogram （SDH） is proposed, which is based on different features of trajectories between the true target and false one. Moreover, a new series of discrimination schemes of SDH and Local Extreme Value method （LEV） are studied and applied to simulate the actually measured radar data. The results show that the given discrimination is effective to reduce false alarms during dim targets detection.
基金This work was co-supported by the National Natural Science Foundation of China(Grant Nos.61690210 and 61690213)the National Basic Research Program of China(“973”Program,Grant No.2013CB733100).
文摘The performance of the three-dimensional differential geometric guidance law with proportional navigation formation against a target maneuvering arbitrarily with time-varying normal acceleration is thoroughly analyzed using the Lyapunov-like approach.The validation of this guidance law is firstly proved,and then the performance issues such as capturability,heading error control efficiency,line of sight rate convergence,and commanded acceleration requirement are analyzed,under the condition that the missile is initially flying toward the target with a speed advantage.It is proved that an intercept can occur and the line of sight rate and missile commanded acceleration can be limited in certain ranges,if the initial heading error is small and the navigation gain is sufficiently large.The nonlinear relative dynamics between the missile and the target is taken into full account,and the analysis process is simple and intuitive,due to the use of a convenient line of sight rotating coordinate system.Finally,the new theoretical findings are validated by numerical simulations.
文摘多视觉传感器协同对空实现全区域覆盖的弱小目标检测,在近距离防空领域中具有重要意义。现有的全区域覆盖方法存在覆盖率低、随机性差等问题,弱小目标检测算法存在模型大、定位及分类准确性低等问题。提出了一种高效的对空全区域覆盖算法和轻量级弱小目标检测算法,通过结合最大面积优先法和最小曼哈顿离法改善存在覆盖死角和随机性差等问题。提出密集通道扩展网络(dense and channel expand network,DCENet)模型,基于轻量级稠密拼接和自适应尺寸通道扩展方法,在弱小目标数据集上获得了比原算法更有竞争力的平均精度结果。
文摘针对复杂背景下红外场景对比度低、特征不足、细节不清而导致的目标检测效率低的问题,在YOLOv5s模型基础上通过创建TCC(two-way convolution and Concat)模块并引入华为Ghost模块,提出了一种基于改进YOLOv5s模型的红外弱小目标检测方法。首先,结合红外图像的低级语义特征,采取二路卷积和多尺度思想创建了TCC模块,提升了特征提取的全面性;接着,为进一步简化网络结构、减少网络参数量,引入轻量化Ghost模块改进了SPP池化层和CSP2卷积网络;最后,以无人机为实验对象,构建了白天和夜间不同背景条件下的红外弱小目标数据集,实验验证了本文改进算法的有效性。结果表明:改进后的YOLOv5s模型在较少损失帧频的情况下,检测精度提升了1.34%,平均精度均值(mean average precision, mAP)提升了2.26%,优于YOLOv4-tiny和YOLOv7-tiny两种轻量化模型,并与YOLOv8s模型精度相当,但模型参数量仅为YOLOv8s模型的53%,完全可以满足嵌入式设备部署的需求。
文摘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。
