Virtual Epipolar Line Construction of Single-Lens Bi-Prism Stereovision System

This paper proposes a simple geometrical ray based approach to solve the stereo correspondence problem for the single-lens bi-prism stereovision system. Each image captured using this system can be divided into two sub-images on the left and right and these sub-images are generated by two virtual cameras which are produced by the bi-prism. This stereovision system is equivalent to the conventional two camera system and the two sub-images captured have disparities which can be used to reconstruct back the 3-dimensional （3D） scene. The stereo correspondence problem of this system will be solved geometrically by applying the epipolar geometry constraint on the generated virtual cameras instead of the real CCD camera. Experiments are conducted to validate the proposed method and the results are compared to the calibration based approach to confirm its accuracy and effectiveness.

Automatic teaching of stereovision-guided welding robot using ant colony optimization algorithm

A binocular stereovision system with a linear laser emitter is developed to detect seam position and its orientation, employing acquired 3-dimensional seam data, the automatic teaching of welding robot is implemented using a controlling strategy based on ant colony optimization（ ACO ） algorithm, in which the angle increment of robot joint is discretized as the nodes of ACO graph and a corresponding pheromone updating strategy is presented. The experimental results for curvilinear seams and saddle-shaped seams show that the automatic teaching of welding robot can be successfully completed using the ACO-based controlling strategy under the guidance of stereovision, and the welding trajectory generated by the proposed method has higher accuracy and less setting time compared with conventional proportional-integral-differential （PID） controller and fuzzy controller.

A simple rectification method for linear multi-baseline stereovision system

The linear multi-baseline stereo system introduced by the CMU-RI group has been proven to be a very effective and robust stereovision system. However, most traditional stereo rectification algorithms are all designed for binocular stereovision system, and so, cannot be applied to a linear multi-baseline system. This paper presents a simple and intuitional method that can simultaneously rectify all the cameras in a linear multi-baseline system. Instead of using the general 8-parameter homography transform, a two-step virtual rotation method is applied for rectification, which results in a more specific transform that has only 3 parameters, and more stability. Experimental results for real stereo images showed the presented method is efficient.

AUTOMATED IMAGE MATCHING WITH CODED POINTS IN STEREOVISION MEASUREMENT

A coding-based method to solve the image matching problems in stereovision measurement is presented. The solution is to add and append an identity ID to the retro-reflect point, so it can be identified efficiently under the complicated circumstances and has the characteristics of rotation, zooming, and deformation independence. Its design architecture and implementation process in details based on the theory of stereovision measurement are described. The method is effective on reducing processing data time, improving accuracy of image matching and automation of measuring system through experiments.

Visualizing surface strain distribution of facial skin using stereovision

An experimental technique has been developed for measuring and visualizing strain distribution on facial skin. A stereovision technique based on digital image correlation is employed for obtaining the displacement distribution on the human face. Time-variation of the movement of the facial skin surface is obtained from consecutive images obtained using a pair of high-speed cameras. The strains on the facial skin surface are then obtained from the measured displacements. The performance of the developed system is demonstrated by applying it to the measurement of the strain on facial skin during the production of sound. Results show that the strains on facial skin can be visualized. Further discussion on the relationship between the creation of wrinkles and strains is possible with the help of the developed system.

Crowdedness estimation approach based on stereovision for bus passengers

An estimation approach is proposed in this paper based on the binocular stereovision to collect the degree of crowdedness in public transports. The proposed method combines the disparity with frame differences to extract the foreground object. An adaptive window normalized cross correlation （NCC） matching and interpolated method is applied to get the sub-pixel image disparity value. Then, the foreground object is projected to the horizontal plane to eliminate the influence of the occlusion and perspective effect. Finally the degree of crowdedness is calculated from the area and the perimeter of the foreground objects. Experimental results show that the proposed method can obtain good estimation results in the simulated scenes in the laboratory and on parking or moving buses. This approach is effective to illumination changes, shadows and occlusion of passengers.

AB019. A proposed test of stereovision to identify local retinal abnormalities

Background:The human visual system extracts depth information from disparity in the images seen by the two eyes.The ability to calculate depth from disparity will be disrupted if local retinal abnormalities distort parts of those images,especially if these distortions are different in the two eyes.In its early stages,age-related macular degeneration(AMD)causes slight distortions in the central vision field which differ in the two eyes.AMD is the most common form of irreversible blindness in people over the age of 50.The goal of this project is to develop a stereoscopic perception test which leverages the sensitivity of binocular depth perception to detect the interocular differences symptomatic of either early-stage AMD or other diseases affecting the retina.Methods:A program was written in MATLAB that allowed separate left and right eye stimuli to be shown to the two eyes.NVIDIA 3D Vision 2 stereoscopic glasses were used to present the stimuli.The test we have developed consists of random dot patterns covering the central 5 degrees of vision.One or more disk-shaped perturbations in depth are displayed at different locations in the visual field of the subjects.Of the ten possible target locations,we present between one and four disks on each trial.The disks will only be visible if there is an undistorted input for that visual field location from the two retinae.The participant uses a keypad to report the number of floating disks seen.A set of trials with randomized locations and numbers of disks is used to gather initial data on likely areas of stereoscopic vision deficit;afterwards,likelihoods for deficits in each location are calculated and used to generate customized subsequent trials.Results:The software to perform the local stereovision test has been developed and is now being piloted.We are currently collecting data from healthy normal subjects prior to applying the test to clinical populations.In order to simulate the central vision distortions of AMD,patches of the stimulus for one eye are scrambled and blurred.This allows us to ensure that the task is functioning correctly.Conclusions:The next step for this project is for it to be tested on ageing clinical populations to find its effectiveness in differentiating patients with normal sight from those showing early symptoms of AMD or other retinal abnormalities such as diabetic retinopathy.This test could represent a novel approach in early clinical detection of ocular disease.

Stereovision system for estimating tractors and agricultural machines transit area under orchards canopy

Managing orchards requires delicate agricultural operations being typically carried out in narrow zones where the operators usually drive machineries under stress that could result in poor performance.In such conditions,the use of technology would help manage the machines to reduce the hazardous work and eventual damage to the plants.To safely drive a tractor,the driver needs to be aware of its surroundings,thus a stereovision system can provide helpful information.Stereo imaging has proven to be an effective three-dimensional vision system.Indeed,the range(or third coordinate)information is useful to detect the obstacle distances.Such distances,when detected during agricultural operations,could be used to assist the operator in driving the tractor at regular or variable working speeds and eventually to provide manufacturers useful indications to model the form of ROPS(roll over protection structure).This study aimed to verify the closeness of agreement between manual and stereo-image measurements,and thus to provide helpful information regarding safety and working purposes.The system used a custom low-cost dual web-camera in combination with an image analysis algorithm in order to automatically extract the information needed.Manual independent measurements were carried out using a metric tape(sensitivity 1 cm).A regular structure was used for the analysis:four rows of ten trees each one.Alternated red and blue paper markers were placed on the hazelnut trees(two per tree)of two couples of rows for enhanced visibility.For each couple of trees(one on the right,the other on the left),the four markers formed a trapezoid that was measured.The results of the analysis demonstrated that the stereo vision provided distance measurements with reasonable accuracy(error<5%)in the range of distances lower than 20 m.The resolution assessed for the developed video system is suitable for obtaining distance information in real scenes.This information could be used to assist drivers to operate agricultural machineries through narrow tree rows during work execution.Moreover,such information could be used for safeguarding decision-making and/or for controlling some tractor functions such as continuing moving,changing driving direction,changing 3-point hitch position,reducing transmission speed,halting the tractor.These functions will be necessary before tractors become fully autonomous.Finally,the measured distances,marking the narrow transitions between the tree rows,could be also used to study the ROPS form,both for working safely and for avoiding possible damage caused to the hazel trees laterally.

Greedy calibration method for binocular camera system via characteristic homography matrix

A plane-based and linear camera calibration technique without considering lens distortion is proposed in a greedy and intuitive framework for the binocular camera system. Characteristic homography matrix and consistency constraints in close range are employed in this calibration. First, in order to calculate the internal geometries of the cameras, total least-square fitting as a robust tool for the geometrical cost function is exploited to recover the accurate principal point of each camera from all the characteristic lines of the homography matrices for all model planes. Secondly, generic prior knowledge of the aspect ratio of pixel cells is incorporated into the system to obtain the exact principal length in each camera. Thirdly, extrinsic geometries are accurately computed for all planar patterns with respect to each monocular camera. Finally, the rigid displacement between binocular cameras can be obtained by imposing the consistency constraints in 3-space geometry. Both simulation and real image experimental results indicate that reasonably reliable results can be obtained by this technique. And the proposed method is sufficient for applications where high precision is not required and can be easily performed by common computer users who are not experts in computer vision.

Guiding the welding robot to the initial welding position with visual method

Using step pattern match technology with variational resolution can recognize the position and orientation of the weld seam in the image. According to using the image segmentation method based on pattern match, not only advanced the speed and anti-jamming capability, but also captured the edge information of the weld seam and the edge of the workpiece, and the image coordinate of the initial welding position can be obtained. The matrix for hand-eye relationship of the robot can be calculated by adopting the rapid calculation method. According to the depth calculating principle with the special point matching using binocular stereovision, the initial welding position can be confirmed by calculating the middle point of the perpendicular line of two radials in the space, and the function to guide the welding robot to the initial welding position can be realized.

On-line Free-viewpoint Video:From Single to Multiple View Rendering

In recent years, many image-based rendering techniques have advanced from static to dynamic scenes and thus become video-based rendering （VBR） methods. But actually, only a few of them can render new views on-line. We present a new VBR system that creates new views of a live dynamic scene. This system provides high quality images and does not require any background subtraction. Our method follows a plane-sweep approach and reaches real-time rendering using consumer graphic hardware, graphics processing unit （GPU）. Only one computer is used for both acquisition and rendering. The video stream acquisition is performed by at least 3 webcams. We propose an additional video stream management that extends the number of webcams to 10 or more. These considerations make our system low-cost and hence accessible for everyone. We also present an adaptation of our plane-sweep method to create simultaneously multiple views of the scene in real-time. Our system is especially designed for stereovision using autostereoscopic displays. The new views are computed from 4 webcams connected to a computer and are compressed in order to be transfered to a mobile phone. Using GPU programming, our method provides up to 16 images of the scene in real-time. The use of both GPU and CPU makes this method work on only one consumer grade computer.

Depth perception differences between hemispheres,genders,and eye dominance A study on evoked potential

BACKGROUND： Certain neural functions, such as peripheral reflexes, differ between genders, while higher brain functions, such as language, are asymmetrically distributed between the two hemispheres. The question remains as to whether depth perception differs between hemispheric laterality and genders, and whether it is affected by eye dominance. OBJECTIVE： To determine whether depth perception is influenced by factors such as gender, eye dominance, and hemispheric lateralization by recording evoked potential associated with depth perception. DESIGN, TIME AND SETTING： A contrast observation based on neuroelectrophysiology was performed at the Department of Biophysics of Ege University Medical School between June 2006 and April 2007. PARTICIPANTS： A total of 34 subjects, 19 females and 15 males, were included in the study with a mean age of （31.0 ± 6.9） years. All subjects were free of neurological or psychological disorders, or problems such as strabismus or vision correction. METHODS： Random-dot stereograms were used to elicit brain activity. A specially designed signal acquisition system employing two computers was used to record evoked potentials from both hemispheres via two pairs of scalp electrodes placed over the occipitotemporal areas of both hemispheres at symmetrical locations. MAIN OUTCOME MEASURES： Negative potential with a mean latency of （211.21 ±25.55） ms and a mean amplitude of （6.05 ± 1.53） pV was recorded from both occipitotemporal areas in 30 out of 34 participants. This was termed ＂Nd＂ and represented the evoked potential associated with depth perception. RESULTS： There were no significant differences in Nd amplitude or latency between the two hemispheres, the two eyes, or genders （P 〉 0.05）. CONCLUSION： The evoked potential associated with depth perception was not influenced by gender, hemisphere, or eye dominance.

Dental Arch3D Direct Detection System from the Patient＇s Mouth and Robot for Implant Positioning

This paper describes a three-dimensional structured light scanning system to generate a virtual model of a dental arch, from the patient＇s mouth, and the scheme ofa 2 ＋ 1 DOF （degree of freedom） parallel/serial Robot for implant positioning, both positioned on a platform held in a fixed position with respect to the patient＇s head. Presently, dental prosthesization requires quite a long time to be completed. This process, in fact, involves the detection of the shape of the dental arch, its plaster model generation, scanning of it, prosthesis preparation and its implant. The procedur＇e is even longer when use of dental implants is required, while early loading of the implants is considered a positive solution. Current research effort is focused on the development of devices for the direct intra-oral determination of the shape of dental prostheses and inserts. These devices, however, are able to detect limited portions of the dental arch, since they must be hand-held by the doctor without external supports, and this may produce relatively large errors due to the sum of relatively small ones. Furthermore, to place an implant correctly, the doctor can use a new system to guide the implant position, but this requires sending the information in Sweden to obtain a special mask in return.