- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - Krakow, Poland (2018.10.16-2018.10.18)] 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - Virtual Video Synthesis for Personalized Training
摘要： Online personal training allows users to work out from the comfort of their own homes using workout videos designed by fitness instructors. Users of such applications can use their device (PC, laptop, smart TV, etc.) camera and work out with others in a group setting, enabling plethora of intertwined benefits. In order to enhance training efficiency, it could be helpful for the trainee to superimpose his/her human silhouette, giving the differences of his/her exercise over the trainer’s movements. One way to proceed towards this direction is to have a camera recording the video of the trainee during the exercise, which should be presented in contrast to the instructor’s video on the device screen. In this work, we explore this direction and present traditional background estimation approaches in combination with foreground extraction techniques using videos recorded with static cameras. It is shown that none of the presented methods is able to efficiently face all possible challenges, like slow moving object (foreground) or presence of the moving object at the phase of background initialization, problems that mainly appear in in yoga exercise. As an alternative, we propose a series of techniques including an initial background reconstruction method followed by a selective updating scheme. In this way, the background image adaptively converges to the ground truth data enabled by the merging of from detected moving regions (temporal processing) and color-based regions (spatial processing) of the video segment. Finally, we also apply the proposed method in space surveillance applications, using surveillance cameras, in order to evaluate the generality and efficiency of the proposed approach.
关键词： image background reconstruction,silhouette extraction,fusion of temporal and spatial information,motion tracking,video processing
更新于2025-09-09 09:28:46
-
[IEEE 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Chongqing (2018.6.27-2018.6.29)] 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - NCC Feature Matching Optimized Algorithm Based on Constraint Fusion
摘要： In this paper, a binocular stereo vision three-dimensional (3D) reconstruction algorithm is proposed. In order to reduce the computation in feature extraction process, it begins with selecting candidate corner points, and then uses this as the center to establish the search area. Finally, scale invariant feature transform (SIFT) algorithm is used to extract corner points. In the process of stereo matching, the rough matching point pairs obtained from the Normal Cross Correlation (NCC) algorithm are applied to feature constraints to get the precise matching point pairs so that the final experiment realizes the 3D reconstruction of objects.
关键词： binocular stereo vision,3D reconstruction,corner extraction,feature constraint
更新于2025-09-09 09:28:46
-
[IEEE 2018 24th International Conference on Pattern Recognition (ICPR) - Beijing, China (2018.8.20-2018.8.24)] 2018 24th International Conference on Pattern Recognition (ICPR) - Adaptive Albedo Compensation for Accurate Phase-Shift Coding
摘要： Among structured light strategies, the ones based on phase shift are considered to be the most adaptive with respect to the features of the objects to be captured. Inter alia, the theoretical invariance to signal strength and the absence of discontinuities in intensity, make phase shift an ideal candidate to deal with complex surfaces of unknown geometry, color and texture. However, in practical scenarios, unexpected artifacts could still result due to the characteristics of real cameras. This is the case, for instance, with high contrast areas resulting from abrupt changes in the albedo of the captured objects. In fact, the not negligible size of pixels and the presence of blur can produce a mix of signal integration from adjacent areas with different albedo. This, in turn, would result in a bias in the phase recovery and, consequentially, in an inaccurate 3D reconstruction of the surface. While this problem affects most structure light methods based on phase shift or derived techniques, little effort has been put in addressing it. With this paper we propose a model for the phase corruption and a theoretically sound correction step to be adopted to compensate the bias. The practical effectiveness of our approach is well demonstrated by a complete set of experimental evaluations.
关键词： structured light,phase shift,albedo compensation,3D reconstruction
更新于2025-09-09 09:28:46
-
[IEEE 2018 24th International Conference on Pattern Recognition (ICPR) - Beijing, China (2018.8.20-2018.8.24)] 2018 24th International Conference on Pattern Recognition (ICPR) - Neighborhood-Based Recovery of Phase Unwrapping Faults
摘要： Among several structured light approaches, phase shift is the most widely adopted in real-world 3D reconstruction devices. This is mainly due to its high accuracy, strong resilience to noise and straightforward implementation. However, Phase shift also exhibits an inherent weakness, that is the spatial ambiguity resulting from the periodicity of the sinusoidal wave adopted. Of course many phase unwrapping methods have been proposed to solve such ambiguity. One of the most promising methods exploits additional signals of mutually prime periods, in order to observe a distinct combination of phases for each spatial point. Unfortunately, for such combination to be properly recognized, a very high accuracy in phase recovery must be attained for each signal. In fact, even modest errors could lead to unwrapping faults, making the overall approach much less resilient to noise than plain phase shift. With this paper we introduce a feasible and effective fault recovery method that can be directly applied to multi-period phase shift. The combined pipeline offers an optimal accuracy and coverage even with high noise conditions, overcoming the setbacks of the original method. The performance of such pipeline is established by means of an in depth set of experimental evaluations and comparison, both with real and synthetically generated data.
关键词： structured light,noise resilience,3D reconstruction,phase unwrapping,phase shift
更新于2025-09-09 09:28:46
-
Image Reconstruction Using Analysis Model Prior
摘要： The analysis model has been previously exploited as an alternative to the classical sparse synthesis model for designing image reconstruction methods. Applying a suitable analysis operator on the image of interest yields a cosparse outcome which enables us to reconstruct the image from undersampled data. In this work, we introduce additional prior in the analysis context and theoretically study the uniqueness issues in terms of analysis operators in general position and the specific 2D finite difference operator. We establish bounds on the minimum measurement numbers which are lower than those in cases without using analysis model prior. Based on the idea of iterative cosupport detection (ICD), we develop a novel image reconstruction model and an effective algorithm, achieving significantly better reconstruction performance. Simulation results on synthetic and practical magnetic resonance (MR) images are also shown to illustrate our theoretical claims.
关键词： cosparsity,iterative cosupport detection,magnetic resonance imaging,analysis model,image reconstruction
更新于2025-09-09 09:28:46
-
Automated Neuron Reconstruction from 3D Fluorescence Microscopy Images Using Sequential Monte Carlo Estimation
摘要： Microscopic images of neuronal cells provide essential structural information about the key constituents of the brain and form the basis of many neuroscientific studies. Computational analyses of the morphological properties of the captured neurons require first converting the structural information into digital tree-like reconstructions. Many dedicated computational methods and corresponding software tools have been and are continuously being developed with the aim to automate this step while achieving human-comparable reconstruction accuracy. This pursuit is hampered by the immense diversity and intricacy of neuronal morphologies as well as the often low quality and ambiguity of the images. Here we present a novel method we developed in an effort to improve the robustness of digital reconstruction against these complicating factors. The method is based on probabilistic filtering by sequential Monte Carlo estimation and uses prediction and update models designed specifically for tracing neuronal branches in microscopic image stacks. Moreover, it uses multiple probabilistic traces to arrive at a more robust, ensemble reconstruction. The proposed method was evaluated on fluorescence microscopy image stacks of single neurons and dense neuronal networks with expert manual annotations serving as the gold standard, as well as on synthetic images with known ground truth. The results indicate that our method performs well under varying experimental conditions and compares favorably to state-of-the-art alternative methods.
关键词： Sequential Monte Carlo estimation,Bayesian filtering,Neuron reconstruction,Fluorescence microscopy,Particle filtering
更新于2025-09-04 15:30:14
-
[IEEE ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Calgary, AB (2018.4.15-2018.4.20)] 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Image Reconstruction for Quanta Image Sensors Using Deep Neural Networks
摘要： Quanta Image Sensor (QIS) is a single-photon image sensor that oversamples the light field to generate binary measurements. Its single-photon sensitivity makes it an ideal candidate for the next generation image sensor after CMOS. However, image reconstruction of the sensor remains a challenging issue. Existing image reconstruction algorithms are largely based on optimization. In this paper, we present the first deep neural network approach for QIS image reconstruction. Our deep neural network takes the binary bitstream of QIS as input, learns the nonlinear transformation and denoising simultaneously. Experimental results show that the proposed network produces significantly better reconstruction results compared to existing methods.
关键词： single-photon imaging,Quanta Image Sensor,deep neural networks,image reconstruction
更新于2025-09-04 15:30:14
-
Digital Image Correlation for discontinuous displacement measurement using subset segmentation
摘要： Deformation measurement is normally achieved by using Digital Image Correlation (DIC) technique when deformation is not discontinuous. However, the presence of discontinuities makes the deformation process very challenging and DIC fails. An innovative technique is proposed in this study which splits the subset (segment) of an image into multiple parts and use segmented subset of the image for correlation process. The performance of the proposed technique is evaluated using di?erent experiments where di?erent types of discontinuities are introduced in the deformation process at di?erent angles and having di?erent discontinuity opening sizes. The obtained results are compared with the recently proposed Discontinuous Digital Image Correlation (DDIC) technique. The results show that the proposed technique is more reliable and having high accuracy which reaches upto 1/100th of a pixel under favorable circumstances.
关键词： Deformation measurement,Discontinuous displacement measurement,Digital image correlation,Reconstruction of displacement ?elds,DIC,Subset segmentation
更新于2025-09-04 15:30:14
-
Time-of-flight spectrometry of ultra-short, polyenergetic proton bunches
摘要： A common approach for spectrum determination of polyenergetic proton bunches from laser-ion acceleration experiments is based on the time-of-flight (TOF) method. However, spectra obtained using this method are typically given in relative units or are estimated based on some prior assumptions on the energy distribution of the accelerated ions. In this work, we present a new approach using the TOF method that allows for an absolute energy spectrum reconstruction from a current signal acquired with a sub-nanosecond fast and 10 μm thin silicon detector. The reconstruction is based on solving a linear least-squares problem, taking into account the response function of the detection system. The general principle of signal generation and spectrum reconstruction by setting up an appropriate system response matrix is presented. Proof-of-principle experiments at a 12 MV Tandem accelerator using different nanosecond-short (quasi-)monoenergetic and polyenergetic proton bunches at energies up to 20 MeV were successfully performed. Within the experimental uncertainties of 2.4% and 12.1% for energy and particle number, respectively, reconstructed energy distributions were found in excellent agreement with the spectra calculated using Monte Carlo simulations and measured by a magnetic spectrometer. This TOF method can hence be used for absolute online spectrometry of laser-accelerated particle bunches.
关键词： silicon detector,time-of-flight spectrometry,energy spectrum reconstruction,polyenergetic proton bunches,laser-ion acceleration
更新于2025-09-04 15:30:14
-
[IEEE 2018 Conference Grid, Cloud & High Performance Computing in Science (ROLCG) - Cluj-Napoca, Romania (2018.10.17-2018.10.19)] 2018 Conference Grid, Cloud & High Performance Computing in Science (ROLCG) - Charged Particle Trajectory Reconstruction Algorithms for Cathode Strip Chambers of the CMS Experiment
摘要： The Large Hadron Collider is delivering a growing luminosity and rate of interactions. This imposes strict requirements on the algorithms used for the reconstruction of charged particle trajectories. We present the results of the improvements achieved in the local reconstruction algorithms used in the cathode strip chambers of the CMS experiment.
关键词： CMS,CSC,reconstruction algorithm,tracking detector
更新于2025-09-04 15:30:14