Research on online measurement method of image target size based on binocular vision

Design of laser scanning binocular stereo vision imaging system and target measurement

The traditional structured light binocular vision measurement system consists of two cameras and a projector, which can be regarded to two monocular vision systems composed by the projector and a camera. In this paper, we present a threedimensional (3D) measurement method based on the combination of binocular vision and monocular vision. The common field of view is reconstructed by a binocular vision system, and the missing data area is filled up by two monocular vision systems. In order to improve the measurement accuracy and unify the three world coordinate systems, a calibration method is proposed. The calibration procedure consists of a binocular vision system calibration, the two monocular vision systems calibration and a globe optimization of the three systems for unifying to a common reference. In monocular vision system calibration, a new method based on virtual target is proposed and used to set up the coordinate relations. We use a projector and two cameras to build a vision system for testing the proposed technique. The experimental results show the calibration algorithm ensures the consistent accuracy in the three systems, which is important for data fusion. And it is clear that the proposed method improves the integrity of measurement results and measuring range efficiently.

Visual field occlusion is one of the causes of urban traffic accidents in the process of reversing. In order to meet the requirements of vehicle safety and intelligence, a method of target distance measurement based on deep learning and binocular vision is proposed. The method first establishes binocular stereo vision model and calibrates intrinsic extrinsic and extrinsic parameters, uses Faster R-CNN algorithm to identify and locate obstacle objects in the image, then substitutes the obtained matching points into a calibrated binocular stereo model for spatial coordinates of the target object. Finally, the obstacle distance is calculated by the formula. In different positions, take pictures of obstacles from different angles to conduct physical tests. Experimental results show that this method can effectively achieve obstacle object identification and positioning, and improve the adverse effect of visual field blindness on driving safety.

Particle overlap and segregation problems in on-line coarse particle size measurement

Evaluation of particle size distribution (PSD) of multimodal dispersion of nanoparticles is a difficult task due to inherent limitations of size measurement methods. The present work reports the evaluation of PSD of a dispersion of poly(isobutylcyanoacrylate) nanoparticles decorated with dextran known as multimodal and developed as nanomedecine. The nine methods used were classified as batch particle i.e. Static Light Scattering (SLS) and Dynamic Light Scattering (DLS), single particle i.e. Electron Microscopy (EM), Atomic Force Microscopy (AFM), Tunable Resistive Pulse Sensing (TRPS) and Nanoparticle Tracking Analysis (NTA) and separative particle i.e. Asymmetrical Flow Field-Flow Fractionation coupled with DLS (AsFlFFF) size measurement methods. The multimodal dispersion was identified using AFM, TRPS and NTA and results were consistent with those provided with the method based on a separation step prior to on-line size measurements. None of the light scattering batch methods could reveal the complexity of the PSD of the dispersion. Difference between PSD obtained from all size measurement methods tested suggested that study of the PSD of multimodal dispersion required to analyze samples by at least one of the single size particle measurement method or a method that uses a separation step prior PSD measurement.

The range of clear and single binocular vision differs between 3D displays and clinical prism vergences, but this difference is unexplained. This difference prevents clinicians from predicting the range of clear and single binocular vision in 3D-viewing patients. In this study, we tested a hypothesis for this difference. The purpose of this study was to determine whether changing fixation target size in 3D viewing significantly affects the vergence ranges and, if so, then to determine whether the target size effect is driven by fusional vergence gain changes, threshold of blur changes, or both. Twenty-one visually normal adults aged 18 to 28 years viewed 3D images at 40 cm in an electronic stereoscopic. The fixation target, a Maltese cross, moved in depth at 2∆/s by way of changing crossed or uncrossed disparity until blur and diplopia ensued. We used four target sizes: (1) small (width × height, 0.21° × 0.63°), (2) medium (1.43° × 4.3°), (3) large (3.6° × 10.8°), and (4) 3D (size changing congruently with disparity). The effect of target size on responses was tested by mixed ANOVAs. Mean convergence blurs and breaks increased with target size by 40% (P < .001) and 71% (P < .001), respectively, and in divergence by 33% (P = .03) and 30% (P = .04), respectively. The increases in break magnitude with target size implicate fusional vergence gain change in the size effect. Increasing target size raised the threshold of blur from 1.06 to 1.82 D in convergence and from 0.97 to 1.48 D in divergence (P = .008). Growing fixation target size in 3D viewing increases fusional vergence gain and blur thresholds, which together increase the limits of clear and single binocular vision. Therefore, the clarity of a 3D image depends not only on its disparity but also on the size of the viewed image.

In order to enable the mobile robot to obtain the three-dimensional information of the objects in space and ensure the safety of the mobile robot’s movement. Based on the principle of binocular stereo vision, combined with the methods of MATLAB and OpenCV, a target ranging system based on binocular stereo vision is designed on the mobile robot. The system uses the built-in toolbox of MATLAB to complete the binocular camera calibration, use OpenCV to extract the corner information and edge information of the target, and use the SIFT stereo matching algorithm to stereo match the left and right image pairs, and then obtain the disparity map by writing the ranging program, reproject the two-dimensional space points into the three-dimensional space, realize the conversion from two-dimensional coordinates to three-dimensional coordinates, so as to obtain the distance between the mobile robot and the target in real time. Finally, the distance test result is compared with the actual distance result, which proves that the measurement error is small, and verifies the feasibility of the distance measurement method.

In this paper, a measurement system based on internal cooperation of cameras in binocular vision is proposed. In terms of the hardware structure, the system is composed of a binocular vision module, a controllable platform and an electronic gradienter, which can be used to collect binocular images and measure horizontal and vertical angles between the binocular vision module and objects. In terms of data processing, a new measurement method based on the cooperation of monocular and binocular vision (MBC) is put forward. Firstly, the depth values of some effective points are obtained according to feature point matching results. Then, a depth propagation algorithm based on MBC is adopted to compute other depth information of the object region. After that, the actual size of unit pixels is computed on the basis of the corresponding disparity value, and it is corrected according to the horizontal and vertical angles. Finally, accurate size measurement of the object is achieved by accumulating the number of pixels. Experimental results show that the proposed system can achieve more accurate measurement results compared to the traditional binocular vision measurement method. For all the experimental objects, the absolute relative measurement errors with our method are all lower than 3.5%.

In order to accurately measure the distance and size information of underwater targets, an underwater target ranging and size measurement system based on binocular vision is proposed. Underwater binocular calibration method is used to obtain the underwater parameters of binocular camera, and the underwater images are calibrated to make them coplanar and aligned. The improved CLAHE algorithm is used to process underwater images and improve the image contrast. The parallax map is obtained by SGBM stereo matching algorithm, and the distance and size of the target are measured and calculated according to the parallax map. The results of underwater experiment show that the measurement accuracy of the system is high for the distance and size of the close-range underwater target, and the measurement error conforms to the requirements of underwater experiment.

The position error on the end of the industrial robot is an important specification for evaluating its accuracy performance. In the ISO 9283 standard, the laser trackers and the binocular vision measurement methods are recommended to calibrate the positioning error. The calibration accuracy measured by using the laser tracker method is superior to that by using the binocular vision measurement method. Thus, this paper emphasized to study how to improve the calibration accuracy of the end position error by using the binocular vision measurement system. The high precision lengths as reference are introduced to combine with a conventional binocular vision system to make a new measurement system. The system errors of the binocular vision system can be corrected. In order to verify the correction effect, taking the industrial robot as an experiment example, the experimental results show that the absolute position error on the end of the industrial robot by using the binocular vision system with reference length constraint can reduce from 0.491 mm to 0.330 mm, and the repetitive positioning error reduced from 0.116 mm to 0.023 mm. The accuracy improved by about 33% and 80% respectively. Compared with the laser tracker measurement results under the same experimental conditions, the difference between the two are 0.34 μm and 7.80 μm. It can be considered that the corrected binocular vision calibration method can achieve the same accuracy with the laser tracker. It can be widely used for high-precision calibration of industrial robots as a means of balancing economics and precision.

Purpose One of the prerequisites for enabling welding robots to achieve autonomous welding is the ability to accurately recognize the real-time state of the welding seam. This paper aims to focus on an arc welding robot used to weld the bead of the hydraulic bracket’s box structure and explores a method for online assessment and measurement of the weld bead gap using laser vision. Design/methodology/approach First, a binocular laser vision measurement system was developed to meet the requirements for measuring weld gaps at various positions within the box structure. Second, the images of weld gaps from these structures were collected to create data sets for both a classification network and a semantic segmentation network, evaluating and comparing each model. Finally, the MobileNet V2 network was selected to assess the validity of the welding gap, and the optimized DeepLab V3+ network was used to design the welding gap measurement algorithm. Findings The results indicate that the accuracy of MobileNet V2 is 95.43% and the response time is about 1.72 s. The limit error of the designed measurement algorithm is about 0.081 mm and the response time is about 1.77 s, which meets the actual measurement needs. Originality/value The method can not only realize the accuracy and measurement of the welding gap of the hydraulic support box structure, but also provide a new idea for the online measurement of welding conditions and lay the foundation for the realization of robot autonomous welding.

Binocular vision measurement benefits from high prediction robustness and low structural complexity. However, there are still significant flaws in its accuracy. In this paper, binocular vision measurement of a rectangular workpiece is investigated. A new precise measurement method based on binocular vision is designed to achieve precise measurement of rectangular workpiece dimensions. Firstly, an algorithm for workpiece location based on Zernike moments and corner matching is proposed and employed to precisely locate the workpiece and extract the sub-pixel coordinates of discrete points on an image’s edge. Then, a novel stereoscopic matching algorithm combined with epipolar-geometry and cross-ratio invariance (CMEC) is proposed to improve the accuracy of binocular vision stereoscopic matching. Finally, a projection plane is introduced after the 3D reconstruction of discrete points in the workpiece contours by fitting the plane with least squares. The projection plane limits the coordinate fluctuations of discrete points. Furthermore, the data screening is used to further improve the accuracy of size calculation. The experimental results of the standard checkerboard and actual workpiece show that CMEC’s matching accuracy reached 99%, and the proposed method’s measurement accuracy reached 0.018 mm. This work presents a novel algorithm for stereoscopic matching in binocular vision and machine vision measurement.

We have analyzed the binocular coordination of the eyes during far-to-near refixation saccades based on the evaluation of distance ratios and angular directions of the projected target images relative to the eyes' rotation centers. By defining the geometric point of binocular single vision, called Helmholtz point, we found that disparities during fixations of targets at near distances were limited in the subject's three-dimensional visual field to the vertical and forward directions. These disparities collapsed to simple vertical disparities in the projective binocular image plane. Subjects were able to perfectly fuse the vertically disparate target images with respect to the projected Helmholtz point of single binocular vision, independent of the particular location relative to the horizontal plane of regard. Target image fusion was achieved by binocular torsion combined with corrective modulations of the differential half-vergence angles of the eyes in the horizontal plane. Our findings support the notion that oculomotor control combines vergence in the horizontal plane of regard with active torsion in the frontal plane to achieve fusion of the dichoptic binocular target images.

The mobile crushing station is one of the main equipment of the semi-continuous open-pit mining system. The discharge arm and the receiving equipment are manually aligned, which has the problems of long alignment time and low alignment accuracy, which affects the working efficiency of the mining system. According to the development and application of space rendezvous and docking technology at home and abroad, the advantages and disadvantages of different measurement methods are compared and analysed, and the method of applying binocular measurement technology to system positioning in the automatic alignment system of the discharge arm is determined. There are three movements in the mechanical part of the designed discharge arm alignment control system, including the rotary motion of the visual measurement mechanism and the horizontal rotation and telescopic motion of the discharge arm. According to the kinematic analysis and binocular vision measurement theory, the deviation model of the alignment control of the discharge arm is established. A binocular vision measurement and localization method based on the combination of stereo calibration and template matching is proposed, which achieves surprising measurement accuracy. An automatic alignment method of the discharge arm of the mobile crushing station is proposed based on the binocular vision and fuzzy control method. Its validity is verified by simulation and experiment. The strategy of motion decomposition is applied to the alignment system to avoid unnecessary motion of the discharge arm. The research results all show that the alignment method can achieve the angle deviation within ±0.5 degrees, the distance deviation within ±15 mm, and the test alignment time is about 5 minutes, which is better than other alignment control models; the alignment accuracy and the alignment time are improved by more than 50%. The method can control the discharge arm to complete the alignment task quickly and smoothly, which lays a foundation for the further automatic research of the discharge arm.

Automation of intercept method for grain size measurement: A topological skeleton approach