No-Reference Stereo Image Quality Assessment Based on Transfer Learning

In order to apply the deep learning to the stereo image quality evaluation,two problems need to be solved:The first one is that we have a bit of training samples,another is how to input the dimensional image’s left view or right view.In this paper,we transfer the 2D image quality evaluation model to the stereo image quality evaluation,and this method solves the first problem;use the method of principal component analysis is used to fuse the left and right views into an input image in order to solve the second problem.At the same time,the input image is preprocessed by phase congruency transformation,which further improves the performance of the algorithm.The structure of the deep convolution neural network consists of four convolution layers and three maximum pooling layers and two fully connected layers.The experimental results on LIVE3D image database show that the prediction quality score of the model is in good agreement with the subjective evaluation value.

Three-dimensional motion parameters estimation from stereo image sequences based on infrared reflective markers

In this paper,an innovative 3D motion parameters estimation method from stereo image sequences based on infrared(IR) reflective markers is presented.It was assumed that two high speed CCD cameras had been calibrated previously.The method consists of the following steps:1) the coordinate of several markers and depth map for each stereo pair was determined from the sequences of stereo images by relations of markers' coordinate the correspondence between markers was established,2) the 3D motion parameters of the target was computed based upon the matched markers' coordinate,and 3) translated 3D motion parameters estimation into the problem of least square according to the movement model of the object to be measured.Without using line,curve or corner correspondence,this method can calculate the depth of these markers feature easily and quickly in contrast to traditional approaches.The two CCD cameras work on 200 f/s,and each processing cost time is about 3 ms.It was found that,by using several markers and a large number of stereo images,this method can improve the computational speed,robustness and numerical accuracy of the motion parameters in comparison with traditional methods.The virtual simulation experiment was conducted using synthesized stereo image sequences based on 6-DOF motion platform and the experimental results proved the validity of our approach and showed that the translation and rotation precision is up to 0.1 mm and 0.1°.

An Adaptive and Image-guided Fusion for Stereo Satellite Image Derived Digital Surface Models

The accuracy of Digital Surface Models(DSMs)generated using stereo matching methods varies due to the varying acquisition conditions and configuration parameters of stereo images.It has been a good practice to fuse these DSMs generated from various stereo pairs to achieve enhanced,in which multiple DSMs are combined through computational approaches into a single,more accurate,and complete DSM.However,accurately characterizing detailed objects and their boundaries still present a challenge since most boundary-ware fusion methods still struggle to achieve sharpened depth discontinuities due to the averaging effects of different DSMs.Therefore,we propose a simple and efficient adaptive image-guided DSM fusion method that applies k-means clustering on small patches of the orthophoto to guide the pixel-level fusion adapted to the most consistent and relevant elevation points.The experiment results show that our proposed method has outperformed comparing methods in accuracy and the ability to preserve sharpened depth edges.

A Skeletal Camera Network for Close-range Images with a Data Driven Approach in Analyzing Stereo Configuration

Structure-from-Motion(SfM)techniques have been widely used for 3D geometry reconstruction from multi-view images.Nevertheless,the efficiency and quality of the reconstructed geometry depends on multiple factors,i.e.,the base-height ratio,intersection angle,overlap,and ground control points,etc.,which are rarely quantified in real-world applications.To answer this question,in this paper,we take a data-driven approach by analyzing hundreds of terrestrial stereo image configurations through a typical SfM algorithm.Two main meta-parameters with respect to base-height ratio and intersection angle are analyzed.Following the results,we propose a Skeletal Camera Network(SCN)and embed it into the SfM to lead to a novel SfM scheme called SCN-SfM,which limits tie-point matching to the remaining connected image pairs in SCN.The proposed method was applied in three terrestrial datasets.Experimental results have demonstrated the effectiveness of the proposed SCN-SfM to achieve 3D geometry with higher accuracy and fast time efficiency compared to the typical SfM method,whereas the completeness of the geometry is comparable.

Optimization of the forearm angle for arm wrestling using multi-camera stereo digital image correlation: A preliminary study

This study analyzes the function of different muscles during arm wrestling and proposes a method to analyze the optimal forearm angle for professional arm wrestlers.We built a professional arm-wrestling platform to measure the shape and deformation of the skin at the biceps brachii of a volunteer in vivo during arm wrestling.We observed the banding phenomenon of arm skin strain during muscle contraction and developed a model to evaluate the moment provided by the biceps brachii.According to this model,the strain field of the area of interest on the skin was measured,and the forearm angles most favorable and unfavorable to the work of the biceps brachii were analyzed.This study demonstrates the considerable potential of applying DIC and its extension method to the in vivo measurement of human skin and facilitates the use of the in vivo measurement of skin deformation in various sports in the future.

Center of rotation estimation for rocket nozzle by infrared reflective makers and image sequences

The determination of an accurate center of rotation of rocket motor nozzle or other object to be measured is of great interest across a wide range of applications,such as rocket,missile,robotics,industry,spaceflight,aviation and human motion analysis fields,particularly for clinical gait analysis.A new approach was proposed to estimate the moving objects' instantaneous center of rotation and other motion parameters.The new method assumes that the two segment of object to be measured are rigid body which rotates around a center of rotation between each other relatively.The center of rotation varies with time in the global coordinate system but is fixed in the local coordinate system attached to each segment.The models of rocket motor nozzle and its movement were established.The arbitrary moving object's corresponding to motion equations were deduced,and the least square closed-form solutions of the object's motion parameters were figured out.It is assumed that the two high speed CCD cameras mounted on the 750 nm infrared(IR) filter are synchronized and calibrated in advance.The virtual simulation experiment using 3D coordinates of markers was conducted by synchronized stereo image sequences based on 6-DOF motion platform and the experimental results prove the feasibility of our algorithm.The test results show that the precision of x,y,z component on center of rotation is up to 0.14 mm,0.13 mm,0.15 mm.

Interchannel phase difference and stereo sound image localization

By considering higher order approximation to the interaural phase difference, a more general localization equation for stereo sound image with interchannel phase difference is derived. At very low frequency or low interchannel phase difference, the equation can be simplified to Makita theory. In general, image position is obviously affected by frequency.It is shown that image position varying with freqllency is the main reason for image width broadening in stereo reproduction with interchannel phase difference. And an extra interaural sound level difference caused by interchannel phase difference is the main reason for image naturalness degrading. In practice, it is necessary to reduce the interchannel phase difference,at least, to less than 60°.

Autostereoscopic three-dimensional display with high dense views and the narrow structure pitch

An auto-stereoscopic three-dimensional （3D） display method with the narrow structure pitch and high dense viewpoints is presented. Normally, the number of views is proportional to the structure pitch of the lenticular lens array. Increasing the density of views will decrease the spatial display resolution. Here a lenticular lens array with one pitch covering 5.333 subpiexels and a novel subpixel arrangement method are designed, and a 32 view 3D display is demonstrated. Compared with the traditional 6-view 3D display, the angular resolution and the displayed depth of field are significantly improved.

A Novel Data Embedding Method for H.264 Stereo Video Codec with Joint Prediction Scheme

It is important to reduce data redundancy of stereo video in practical applications. In this paper,first,a data embedding method for stereo video（DEMSV） is investigated by embedding the encoding data into the reference frame to encode stereo video. It can use only one channel to transfer all the video data and the receiver can choose a monocular video decoder or stereo video decoder adaptively. Then,introducing the joint prediction scheme in the coding process of DEMSV,we propose a novel data embedding method for H.264 stereo video codec with joint prediction scheme（DEMSV-JPS） to achieve high coding efficiency. Experimental results show that the proposed method can obtain high peak signal-to-noise ratio（PSNR） and compression ratio（at least 33 dB for the test sequence） . Comparing the testing methods using JPS and without using JPS,we prove that JPS can further improve the objective and visual quality. DEMSV-JPS shows such advantages and will be suitable to applications in real-time environments of stereo-video transmission.

Quantization error in stereo imaging system with noise distributions

The problem of estimating quantization error in 2D images is an inherent problem in computer vision.The outcome of this problem is directly related to the error in reconstructed 3D position coordinates of an object.Thus estimation of quantization error has its own importance in stereo vision.Although the quantization error cannot be controlled fully,still statistical error analysis helps us to measure the performance of stereo systems that relies on the imaging parameters.Generally,it is assumed that the quantization error in 2D images is distributed uniformly that need not to be true from a practical aspect.In this paper,we have incorporated noise distributions(Triangular and Trapezoidal)for the stochastic error analysis of the quantization error in stereo imaging systems.For the validation of the theoretical analysis,the detailed simulation study is carried out by considering different cases.

Single-camera active stereo vision system using fiber bundles

We propose an approach for realizing 3D reconstruction in small field of view or some extreme environments. We combine the stereo vision and the structured light technologies and change the traditional ways of applying them by employing two fiber bundles. The processes of calibration and 3D reconstruction are also introduced. Experiments are performed to verify the feasibility and effectiveness of our proposed approach.

Reconstruction of 3-D surface waves generated by moving submerged sphere based on stereo imaging principle

A sailing ship can produce significant disturbances on the water surface,but the perturbation generated by a moving submerged source is much smaller due to the physical property of the free surface,as represented by the rigid-lid assumption,with the geometric displacement barely observed or measured.Based on the stereo imaging principle,an experimental system for the three-dimensional measurement of the surface perturbation is built by assembling two charge coupled device(CCD)sensors,to measure the surface waves generated by a small submerged sphere,including the small-scale vertical displacements and the flow field on the water surface.The obtained results are consistent with those obtained by the theoretical analysis,and the measurement accuracy for the vertical displacements is improved by 50%compared to that of the direct optical method based on the image grey levels.Additionally,the present measurement technique can be efficiently and precisely applied to other measurements of small-scale disturbances on a free surface.

Fluorescent digital image correlation techniques in experimental mechanics

White light has often been used for surface illumination to acquire images for digital image correlation(DIC) analysis. In recent years, fluorescent imaging technique has been introduced for illumination, surface deformation and topography measurements with applications on various materials including biomaterials(biofilms, etc.) at the microscale. Traditional imaging, with the use of white light, encounters technical issues such as specular reflection owing to moisture or smooth shiny surfaces(e.g., metallic or glass surfaces). As an alternative to white light, fluorescent imaging serves as a solution to resolve the issues of specular reflection.Fluorescent DIC techniques, especially the fluorescent stereo DIC, allow 3 D surface profilometry and deformation measurements at the microscale and submicron scale. Fluorescent stereo imaging under a microscope utilizes emission wavelengths that are different from illumination wavelengths to ensure clear images on any surface that might give reflections at certain angles when white light is used, allowing accurate metrology and deformation measurement. In addition microscopic fluorescent imaging provides nanoscale resolutions surpassing Abbe's diffraction limit. This paper provides a review of the recent advances in fluorescent DIC.

3D display with uniform resolution and low crosstalk based on two parallax interleaved barriers

The resolution of the parallax image is inversely proportional to the view number in the horizontal direction for the traditional autostereoscopic display based on a parallax barrier. To balance the resolution in the vertical and horizontal directions, two parallax interleaved barriers are designed. The liquid crystal display panel provides the synthetic image with square pixel units, and the pixels in a unit are distributed to different horizontal views. Two parallax interleaved barriers work together to modulate pixels in vertical and horizontal directions. 3D display with uniform resolution and low crosstalk is demonstrated.

Experimental and numerical investigation to elucidate the fluid flow through packed beds with structured particle packings

The present paper presents an experimental and numerical investigation of the dispersion of the gaseous jet flow and co-flow for the simple unit cell(SUC)and body-centred cubic(BCC)configuration of particles in packed beds.The experimental setup is built in such a way that suitable and simplified boundary conditions are imposed for the corresponding numerical framework,so the simulations can be done under very similar conditions as the experiments.Accordingly,a porous plate is used for the co-flow to achieve the uniform velocity and the fully developed flow is ensured for the jet flow.The SUC and BCC particle beds consist of 3D-printed spheres,and the non-isotropy near the walls is mostly eliminated by placing half-spheres at the channel walls.The flow velocities are analysed directly at the exit of the particle bed for both beds over 36 pores for the SUC configuration and 60 pores for the BCC configuration,for particle Reynolds numbers of 200,300,and 400.Stereo particle image velocimetry is experimentally arranged in such a way that the velocities over the entire region at the exit of the packed bed are obtained instantaneously.The numerical method consists of a state-of-the-art immersed boundary method with adaptive mesh refinement.The paper presents the pore jet structure and velocity field exiting from each pore for the SUC and BCC packed particle beds.The numerical and experimental studies show a good agreement for the SUC configuration for all flow velocities.For the BCC configuration,some differences can be observed in the pore jet flow structure between the simulations and the experiments,but the general flow velocity distribution shows a good overall agreement.The axial velocity is generally higher for the pores located near the centre of the packed bed than for the pores near the wall.In addition,the axial velocities are observed to increase near the peripheral pores of the packed bed.This behaviour is predominant for the BCC configuration as compared to the SUC configuration.The velocities near the peripheral pores can become even higher than those at the central pores for the BCC configuration.It is shown that both the experiments as well as the simulations can be used to study the complex fluid structures inside a packed bed reactor.