Existing three-dimensional(3D) imaging technologies have issues such as requiring active illumination, multiple exposures, or coding modulation. We propose a passive single 3D imaging method based on an ordinary imagi...Existing three-dimensional(3D) imaging technologies have issues such as requiring active illumination, multiple exposures, or coding modulation. We propose a passive single 3D imaging method based on an ordinary imaging system.Using the point spread function of the imaging system to realize the non-coding measurement on the target, the full-focus images and depth information of the 3D target can be extracted from a single two-dimensional(2D) image through the compressed sensing algorithm. Simulation and experiments show that this approach can complete passive 3D imaging based on an ordinary imaging system without any coding operations. This method can achieve millimeter-level vertical resolution under single exposure conditions and has the potential for real-time dynamic 3D imaging. It improves the efficiency of 3D information detection, reduces the complexity of the imaging system, and may be of considerable value to the field of computer vision and other related applications.展开更多
针对全卷积神经网络对单帧红外图像行人检测计算量大、检测率较低等问题,提出了一种改进的LeNet-7系统对红外图像行人检测的方法。该系统包含3个卷积层、3个池化层,通过错误率最小的试选法确定每层参数,以波士顿大学建立的BU-TIV数据库...针对全卷积神经网络对单帧红外图像行人检测计算量大、检测率较低等问题,提出了一种改进的LeNet-7系统对红外图像行人检测的方法。该系统包含3个卷积层、3个池化层,通过错误率最小的试选法确定每层参数,以波士顿大学建立的BU-TIV数据库训练系统。首先,以俄亥俄州立大学建立的OTCBVS和Terravic Motion IR Database红外数据库作为测试图像;然后,采用自适应阈值的垂直和水平投影法得到感兴趣区域(regions of interest,ROI);最后,将得到的ROI输入训练好的系统进行测试。3个测试集检测实验表明,本文方法具有良好的识别能力,与不同实验方法相比,本文方法能有效提高检测率。展开更多
基金Project supported by the National Key Research and Development Program of China (Grant No. 2018YFB0504302)Beijing Institute of Technology Research Fund Program for Young Scholars (Grant No. 202122012)。
文摘Existing three-dimensional(3D) imaging technologies have issues such as requiring active illumination, multiple exposures, or coding modulation. We propose a passive single 3D imaging method based on an ordinary imaging system.Using the point spread function of the imaging system to realize the non-coding measurement on the target, the full-focus images and depth information of the 3D target can be extracted from a single two-dimensional(2D) image through the compressed sensing algorithm. Simulation and experiments show that this approach can complete passive 3D imaging based on an ordinary imaging system without any coding operations. This method can achieve millimeter-level vertical resolution under single exposure conditions and has the potential for real-time dynamic 3D imaging. It improves the efficiency of 3D information detection, reduces the complexity of the imaging system, and may be of considerable value to the field of computer vision and other related applications.
文摘针对全卷积神经网络对单帧红外图像行人检测计算量大、检测率较低等问题,提出了一种改进的LeNet-7系统对红外图像行人检测的方法。该系统包含3个卷积层、3个池化层,通过错误率最小的试选法确定每层参数,以波士顿大学建立的BU-TIV数据库训练系统。首先,以俄亥俄州立大学建立的OTCBVS和Terravic Motion IR Database红外数据库作为测试图像;然后,采用自适应阈值的垂直和水平投影法得到感兴趣区域(regions of interest,ROI);最后,将得到的ROI输入训练好的系统进行测试。3个测试集检测实验表明,本文方法具有良好的识别能力,与不同实验方法相比,本文方法能有效提高检测率。
