检索结果-内蒙古大学图书馆

CorNet: Enhancing Motion Deblurring in Challenging Scenarios Using correlation image sensor

IEEE ACCESS 2025年 13卷 33834-33848页

作者： Wang, Pan Kurihara, Toru Yu, Jun Kochi Univ Technol Sch Informat Kami 7828502 Japan

Motion deblurring in scenes involving small moving objects or low-illumination conditions is challenging. This paper presents an effective deep-learning solution that utilizes correlation images as key auxiliaries to address the problem. The correlation image, produced by a three-phase correlation image sensor (3PCIS), is a temporal correlation between incident light and reference signals within a frame time, which encodes intensity changes of incident light over the exposure time. Since correlation images explicitly record motion information lost during the blurring process during exposure, they can be used for accurately identifying the location and degree of blur, especially in low-illumination conditions and scenarios with small moving objects. Therefore, we combine correlation images and motion-blurred images as inputs and build a two-stream network for motion deblurring. Two key designs in our model are 1) Shared-gated Block (SGB), which enables information exchange between the two encoders and selectively allows useful information to pass through the network to obtain high-quality output;2) a Motion-guided Block (MGB), decoding process that can draw more attention to the blurred areas in the image, thereby achieving clearer textures and details restoration in the blurred areas. The experimental results show that our model not only can successfully eliminate the motion blur in the above challenging scenarios, but also achieves a state-of-the-art 36.02dB in Peak Signal-to-Noise Ratio (PSNR) on the GoPro dataset with simulated correlation images.

关键词： correlation image sensor image deblurring image deblurring two-stream model two-stream model deep learning deep learning deep learning

来源：评论

学校读者我要写书评

暂无评论

Recovering a sequence of clear frames from a single motion-blurred image using correlation image sensor and temporal progressive learning strategy

引用

SICE JOURNAL OF CONTROL MEASUREMENT AND SYSTEM INTEGRATION 2025年第1期18卷

作者： Wang, Pan Kurihara, Toru Kochi Univ Technol Sch Informat Kochi Japan

Motion-blurred images are the result of an integration process, where instant light intensity is accumulated over the exposure time. Unfortunately, reversing this process is nontrivial. Firstly, integration destroys the temporal ordering of motion, resulting in ambiguity in the motion direction within a single motion-blurred image. Secondly, unlike conventional single-image deblurring, restoring a sequence of frames can divert the neural network's attention to each individual frame, which results in a decrease in the overall restoration quality of the entire sequence. To address the first problem, we leverage a crucial clue: the correlation image, generated by the three-phase correlation image sensor (3PCIS). This image effectively expresses motion information over the exposure time, which is essential for determining the motion direction of moving objects. We design a two-stream network to restore a sequence of sharp frames from a pair of motion-blurred images and their corresponding correlation images. For the second problem, we propose a temporal progressive learning (TPL) strategy that mitigates the performance degradation caused by network distraction by gradually increasing the number of restored clear frames during training. Experimental results demonstrate that our proposed method surpasses previous state-of-the-art methods on the GoPro public dataset and in real scenes.

关键词： correlation image sensor motion blur temporal super-resolution two-stream network progressive learning

来源：评论

学校读者我要写书评

暂无评论

correlation image sensor-Assisted Single-Frame Optical Flow Estimation in Motion-Blurred Scenes

引用

IEEE ACCESS 2024年 12卷 65856-65868页

作者： Wang, Pan Kurihara, Toru Yu, Jun Kochi Univ Technol Sch Informat Kami 7828502 Japan

Single-frame optical flow estimation is a more challenging task than predicting the optical flow between adjacent frames in a video. This paper presents a two-stream network that combines motion information from correlation images with appearance information from intensity images to estimate optical flow in a single-frame manner. The correlation image generated by a three-phase correlation image sensor (3PCIS) records changes in incident intensity during the exposure time and conveys motion information about moving objects. This is crucial to assist motion-blurred images in estimating the motion state of moving objects. Due to the lack of directly available datasets to train our network, we generate a synthetic dataset. Importantly, we introduce a definition that describes optical flow on a single motion-blurred image, which is essential for creating reasonable ground truth. Our experimental results demonstrate that 1) network trained on our synthetic dataset achieves an average End Point Error (EPE) of 0.357 and generalizes well to real-world scenes;2) our proposed single-frame method outperforms conventional two-frame-based methods in motion-blurred scenes.

关键词： correlation Optical sensors Feature extraction Estimation Optical flow Synthetic data image sensors Deep learning correlation image sensor deep learning synthetic dataset two-stream network optical flow

来源：评论

学校读者我要写书评

暂无评论

Real-Time Phase-Stamp Range Finder Using correlation image sensor

引用

IEEE sensorS JOURNAL 2009年第12期9卷 1784-1792页

作者： Kimachi, Akira Ando, Shigeru Osaka Electrocommun Univ Fac Informat & Commun Engn Dept Informat Engn Osaka 5728530 Japan Univ Tokyo Grad Sch Informat Sci & Technol Dept Informat Phys & Comp Bunkyo Ku Tokyo 1138656 Japan

This paper proposes the phase-stamp range finder (PSRF) for real-time three-dimensional (3-D) imaging. The PSRF consists of a time-domain correlation image sensor (CIS) proposed by us, a scanning sheet of light (SOL), and three-phase reference signals supplied to the CIS. After the SOL was scanned over the object during a frame period, the CIS records the "phase stamp" of the reference signals at the moment when the SOL reflected on the object arrived at each pixel. The range image is then reconstructed at the frame rate by converting the phase stamp image from the CIS pixel-wise to the projection angle of the SOL and then applying triangulation. An experimental system is constructed with a 200 x 200-pixel CIS camera and a light-sectioning laser projection system. Experimental results confirm that the constructed system outputs range images at 12.5 frames/s, achieves measurement accuracy of less than 1 mm in standard deviation for imaging distance of 300-500 mm, and is robust to time-varying, spatially nonuniform ambient illumination and fine surface texture of objects.

关键词： correlation image sensor light sectioning phase-stamp imaging real-time range finder

来源：评论

学校读者我要写书评

暂无评论

Continuously trackable PIV (particle image velocimetry) with correlation image sensor

Continuously trackable PIV (particle image velocimetry) with...

引用

Conference on sensors, Cameras, and Systems for Scientific/Industrial Applications IX

作者： Kurihara, Toru Ando, Shigeru Univ Tokyo Grad Sch Informat Sci & Technol Bunkyo Ku Tokyo 1138656 Japan

ISBN: (纸本)9780819469885

In this paper, we propose a new measurement scheme, called phase-stamp imaging using correlation image sensor(CIS). The correlation image sensor, developed by us, is the device which outputs the temporal correlation between incident light intensity and three reference signals which is common among whole pixel. By using the correlation image sensor with the single frequency reference signals, the time at which light spot is getting through is embedded in the form of the phase of the reference signals in each pixel. It provides single frame high resolution measurement of the 2D velocity field, and also good time resolution for transient phenomenon. We apply this scheme to fluid flow measurement. We show some experimental results and confirmed its performance.

关键词： PIV fluid flow velocimetry correlation image sensor

来源：评论

学校读者我要写书评

暂无评论

Real-time vibration amplitude and phase imaging with heterodyne interferometry and correlation image sensor

Real-time vibration amplitude and phase imaging with heterod...

引用

Conference on Interferometry XIV - Techiques and Analysis

作者： Sato, Seichi Kurihara, Toru Ando, Shigeru Univ Tokyo Tokyo 1138654 Japan

ISBN: (纸本)9780819472830

We propose a new out-of-plane vibration imaging technique for micro-structured solid-state devices such as MEMS (micro-electro mechanical systems) microphones or resonators. The technique is based on the longitudinally scanning optical interferometry and an integrated image sensor device which we call the correlation image sensor (CIS). The CIS is able to extract an arbitrary frequency, component from time-varying incident light and produce a complex correlation image including amplitude and phase ill addition to a conventional intensity image. In heterodyne interferometry of vibrating objects, the vibration information is encoded ill several frequency components generated by mutual modulation of longitudinal scan and vibration. In this paper, combination of newly, developed multi-channel CIS and the scanning heterodyne technique enable its to obtain the multiple frequency components simultaneously, and reconstruct the vibration amplitude and phase distributions in real-time. As all example, vibration modes of a MEMS acoustic sensor are shown to be reconstructed at, video rate. A theoretical possibility for the imaging of higher than GHz vibration combining other optical heterodyne techniques is also discussed.

关键词： heterodyne interferometry vibration measurement correlation image sensor

来源：评论

学校读者我要写书评

暂无评论

Spectral matching imager using correlation image sensor and AM-coded multispectral illumination

Spectral matching imager using correlation image sensor and ...

引用

Conference on sensors and Camera Systems for Scientific, Industrial, and Digital Photography Applications IV

作者： Kimachi, A Ikuta, H Fujiwara, Y Matsuyama, H Osaka Electrocommun Univ Neyagawa Osaka 5728530 Japan

ISBN: (纸本)0819448176

In Electronic imaging 2002 we proposed the,spectral mathing imager;which detects an object having a particular spectral property out of a scene in real time using the correlation image sensor: This paper proposes another type of spectral matching imager that employs AM-coded multispectral illumination, instead of the variable wavelength monochrome illumination used previously;in order to increase power efficiency of the illumination. The AM-coded multispectral illumination consists of lights from LEDs with different illuminant spectra, which are also amplitude-modulated with orthogonal carrier signals. The reference signal to the correlation image sensor is created as a weighted sum of the AM signals with weights given by the values of a reference spectrum sampled at the peak wavelengths of the, LED spectra. Owing to the orthogonality of the AM carrier signals, the correlation image sensor outputs the pixelwise spectral correlation between the imaged object and a reference material in every frame. The theory and an implementation of the AM-coded spectral matching imager are described and preliminary experimental results on a set of oxide-doped colored glass pieces are given.

关键词： correlation image sensor spectroscopy matched filter colorimetry watermarking image-based material identification

来源：评论

学校读者我要写书评

暂无评论

EXACT ALGEBRAIC METHOD OF OPTICAL FLOW DETECTION VIA MODULATED INTEGRAL IMAGING Theoretical Formulation and Real-time Implementation using correlation image sensor

EXACT ALGEBRAIC METHOD OF OPTICAL FLOW DETECTION VIA MODULAT...

引用

4th International Conference on Computer Vision Theory and Applications

作者： Ando, Shigeru Kurihara, Toru Wei, Dabi Univ Tokyo Dept Informat Phys & Comp Tokyo Japan Tokyo Inst Technol Dept Control & Syst Engn Tokyo Japan

ISBN: (纸本)9789898111692

A novel mathematical method and a sensing system that detects velocity vector distribution on an optical image with a pixel-wise spatial resolution and a frame-wise temporal resolution is proposed. It is provided by the complex sinusoidally-modulated imaging using the three-phase correlation image sensor (3PCIS) and the exact algebraic inversion method based on the optical flow identity (OFI) satisfied by an intensity image and a complex-sinusoidally modulated image captured by the 3PCIS. Since the 0171 is free from time derivatives, any limitations on the object velocity and inaccuracies due to approximated time derivatives is thoroughly avoided. An experimental system was constructed with a 320 x 256 pixel 3PCIS device and a standard PC for inversion operations and display. Several experimental results are shown including the dense motion capture of face and gesture and the particle image velocimetry of water vortices.

关键词： Optical flow equation Weighted integral method Modulated imaging correlation image sensor Computer vision Velocity field measurement Particle image velocimetry

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Solution for Temporal Super Resolution using correlation image sensor

Deep Learning Solution for Temporal Super Resolution using C...

引用

2024 Society of Instrument and Control Engineers Festival with Annual Conference

作者： Wang, Pan Kurihara, Toru Kochi Univ Technol Sch Informat Kochi Japan

ISBN: (纸本)9798331544461;9784907764838

Motion-blurred images are the result of an integration process, where instant light intensity (which can also be understood as an instant scene) is accumulated over the exposure time. Unfortunately, reversing this process faces two main challenges. Firstly, integration destroys the temporal ordering of motion, resulting in ambiguity in the motion direction within a single motion-blurred image. Secondly, restoring sharp texture is a blind deconvolution task, which is highly ill-posed. To address the first challenge, we leverage a crucial clue: the correlation image, generated by the three-phase correlation image sensor (3PCIS). This image effectively expresses motion information over the exposure time, which is essential for determining the motion direction of moving objects. To tackle the second challenge, we adopt a supervised deep-learning scheme to address the ill-posedness of deblurring. Overall, we propose a two-stream network that restores a sequence of sharp frames from a pair of motion-blurred images and their corresponding correlation images. Experimental results demonstrate that our proposed method surpasses previous state-of-the-art methods on the GoPro public dataset and in real scenes.

关键词： correlation image sensor motion blur temporal super-resolution

来源：评论

学校读者我要写书评

暂无评论

Novel time- and depth-stamped imaging for 3D-PIV (particle image velocimetry) using correlation image sensor

Novel time- and depth-stamped imaging for 3D-PIV (particle i...

引用

Conference on Three-Dimensional image Processing (3DIP) and Applications II

作者： Komiya, Kenji Kurihara, Toru Ando, Shigeru Univ Tokyo Dept Informat Phys & Comp Bunkyo Ku Tokyo 1138656 Japan

ISBN: (纸本)9780819489371

We propose a novel and extremely efficient scheme of 3D-Particle image Velocimetry (3D-PIV), simultaneous time-stamped and depth-stamped imaging, using correlation image sensor (CIS) and a structured illumination. In conventional PIV measurements, 3-D positions of numerous tiny particles inserted in a fluid field must be detected using multiple high-speed cameras. Resultant huge amount of data volume increases the computational cost and reduces the reliability of velocity field estimation. These problems can be solved if a single-frame 4D (3D position and time) trajectory imaging can be realized. The CIS developed by us is the device which outputs the temporal correlation between incident light intensity and two sets of three-phase (3P) reference signal common for whole pixels. When particles are imaged in a frame using a 3P reference signal, CIS records the time information as a phase distribution along their trajectories. CIS can also capture the depth information by exploiting the structured illumination and another 3P reference signal. Combination of these methods provides the time-and depth-stamped imaging. We describe the principle, theoretical foundations, and analysis algorithms. Several experimental results for evaluating accuracy and resolution are shown.

关键词： PIV 3D-measurement correlation image sensor

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：