发明人：杨鹏，刘明，赵晶，董立泉，褚旭红，孔令琴，赵跃进

申请日期：2023.11.15

摘要：本发明公开了一种全像素自动对焦生成方法、装置、设备及介质，属于图像处理技术领域，主要涉及针对整幅图像的全部像素实现自动对焦的问题。该方法通过将图像应用全像素回归模型确定所选对焦区域内由离焦产生的弥散圆半径，依据三角形相似性原理计算出图像采集装置的位移量。最后，编程控制电控平移台按照上述位移量移动图像 ...

发明人：赵航，赵跃进，谭永，董立泉，刘明，孔令琴，褚旭红，许靖

申请日期：2022.10.27

摘要：本发明公开了一种样品中太赫兹脉冲群速度的测量系统和方法，涉及太赫兹波段光学测量技术领域。其中，该光学系统包括设置在光路上的激光器、分光镜、光参量放大器、斩波器、太赫兹产生晶体，太赫兹滤波片、第一离轴抛物面反射镜、第二离轴抛物面反射镜、第三离轴打孔抛物面反射镜、光学延迟装置、第一凸透镜、被测样品、第二 ...

作者：Zhang, Lu¹; Zhao, Weirui¹; Zhao, Yuejin¹; Liu, Juan¹; Chu, Chunyan¹; （¹Beijing Key Laboratory for Precision Optoelectronic Measurement Instrument and Technology, School of Optics and Photonics, Beijing Institute of Technology, Beijing; 100081, China）

出处：SSRN 2022

摘要：Piston errors can be extracted from the modulation transfer function (MTF) side-lobe by setting a mask with a sparse multi-sub-aperture configuration ...

作者：Fan, Zhongyi¹;Liu, Ming¹;Zhao, Yuejin¹;Dong, Liquan¹;Hui, Mei¹;Kong, Lingqin¹;Yang, Qikun¹; （¹Beijing Institute of Technology, Beijing, China）

出处：Proceedings of SPIE - The International Society for Optical Engineering 2022

关键词：3D Deep Learning;Human Reconstruction;Image-based Rendering;Neural Radiance Field;Novel View Synthesis;Voxel Grid

摘要：Novel view synthesis is a long-standing problem. Despite the rapid development of neural radiance field (NeRF), in terms of rendering dynamic human bo ...

作者：Qi, YunPei¹;Dong, Liquan¹;Liu, Ming¹;Kong, Lingqin¹;Hui, Mei¹;Zhao, Yuejin¹; （¹Beijing Key Laboratory of Photoelectric Measuring Instrument and Technology, School of Optics and Photonics, Beijing Institute of Technology, Beijing, 100081, China）

出处：Proceedings of SPIE - The International Society for Optical Engineering 2022

关键词：Convolutional neural network;Deep learning;High-frequency information;Infrared image;Super-resolution

摘要：Image super-resolution technology successfully overcomes the limitation of excessively large pixel size in infrared detectors and meets the increasing ...

作者：Liu, Jia¹;Liu, Ming¹;Zhao, Yuejin¹;Dong, Liquan¹;Hui, Mei¹;Kong, Lingqin¹; （¹School of Optics and Photonics, Beijing Institute of Technology, Beijing, 100081, China Beijing Key Laboratory for Precision Optoelectronic Measurement Instrument and Technology, Beijing, 100081, China Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing, 314019, China）

出处：Proceedings of SPIE - The International Society for Optical Engineering 2022

关键词：Deep Learning;Infrared Image;Template Matching;Visible Light Image

摘要：In the field of computer vision, template matching technology is an important research direction. This technique compares the template image with the ...

作者：Yan, Yuzhang¹;Liu, Ming¹;Hui, Mei¹;Zhao, Yuejin¹;Dong, Liquan¹;Kong, Lingqin¹; （¹Beijing Key Laboratory of Precision Photoelectric Measuring Instrument and Technology, School of Optics and Photonics, Beijing Institute of Technology, Beijing, 100081, China）

出处：Proceedings of SPIE - The International Society for Optical Engineering 2022

关键词：camera calibration;turntable

摘要：Camera calibration is the bridge between 2D image and 3D world and is the basis of 3D stereo vision. Camera calibration can establish the mapping betw ...

作者：Chen, Yifan¹;Liu, Ming¹;Dong, Liquan¹;Zhao, Yuejin¹;Hui, Mei¹;Kong, Lingqin¹; （¹Beijing Key Laboratory of Precision Photoelectric Measuring Instrument and Technology, School of Optics and Photonics, Beijing Institute of Technology, Beijing, 100081, China）

出处：Proceedings of SPIE - The International Society for Optical Engineering 2022

关键词：Automatic tracking;representation learning;target tracking;trajectory prediction

摘要：Moving target trajectory prediction is a typical multidisciplinary research issue involving intelligent science and technology and transportation engi ...

作者：Zhang, Shuo¹;Liu, Ming¹;Zhao, Yuejin¹;Dong, Liquan¹;Kong, Lingqin¹; （¹Beijing Key Laboratory of Precision Photoelectric Measuring Instrument and Technology, School of Optics and Photonics, Beijing Institute of Technology, Beijing, 100081, China）

出处：Proceedings of SPIE - The International Society for Optical Engineering 2022

关键词：Computer Vision;Information Fusion;Pose Conversion;Pose Estimation;Tracking Shooting

摘要：3D human pose estimation refers to recovering the pose of the human body in the three-dimensional space from the image, which is estimating the coordi ...

作者：Liang, Haiyun¹;Liu, Ming¹;Hui, Mei¹;Zhao, Yuejin¹;Dong, Liquan¹;Kong, Lingqin¹; （¹Beijing Key Laboratory of Precision Photoelectric Measuring Instrument and Technology, School of Optics and Photonics, Beijing Institute of Technology, Beijing, 100081, China）

出处：Proceedings of SPIE - The International Society for Optical Engineering 2022

关键词：attention mechanism;densenet module;monocular vision system;multi-view stereo

摘要：With the progress of technology, 3D printing technology has gradually developed and matured, and has been widely used in aerospace, game artifacts, me ...