Camera Coordinate System Research Articles

Dual-UAV Collaborative High-Precision Passive Localization Method Based on Optoelectronic Platform

Utilizing the optical characteristics of the target for detection and localization does not require actively emitting signals and has the advantage of strong concealment. Once the optoelectronic platform mounted on the unmanned aerial vehicle (UAV) detects the target, the vector pointing to the target in the camera coordinate system can estimate the angle of arrival (AOA) of the target relative to the UAV in the Earth-centered Earth-fixed (ECEF) coordinate system through a series of rotation transformations. By employing two UAVs and the corresponding AOA measurements, passive localization of an unknown target is possible. To achieve high-precision target localization, this paper investigates the following three aspects. Firstly, two error transfer models are established to estimate the noise distributions of the AOA and the UAV position in the ECEF coordinate system. Next, to reduce estimation errors, a weighted least squares (WLS) estimator is designed. Theoretical analysis proves that the mean squared error (MSE) of the target position estimation can reach the Cramér–Rao lower bound (CRLB) under the condition of small noise. Finally, we study the optimal placement problem of two coplanar UAVs relative to the target based on the D-optimality criterion and provide explicit conclusions. Simulation experiments validate the effectiveness of the localization method.

Locating Anchor Drilling Holes Based on Binocular Vision in Coal Mine Roadways

The implementation of roof bolt support within a coal mine roadway has the capacity to bolster the stability of the encompassing rock strata and thereby mitigate the potential for accidents. To enhance the automation of support operations, this paper introduces a binocular vision positioning method for drilling holes, which relies on the adaptive adjustment of parameters. Through the establishment of a predictive model, the correlation between the radius of the target circular hole in the image and the shooting distance is ascertained. Based on the structural model of the anchor drilling robot and the related sensing data, the shooting distance range is defined. Exploiting the geometric constraints inherent to adjacent anchor holes, the precise identification of anchor holes is detected by a Hough transformer with an adaptive parameter-adjusted method. On this basis, the matching of the anchor hole contour is realized by using linear slope and geometric constraints, and the spatial coordinates of the anchor hole center in the camera coordinate system are determined based on the binocular vision positioning principle. The outcomes of the experiments reveal that the method attains a positioning accuracy of 95.2%, with an absolute error of around 1.52 mm. When compared with manual operation, this technique distinctly enhances drilling accuracy and augments support efficiency.

Positioning Using Visible Light Communications: A Perspective Arcs Approach

Visible light positioning (VLP) is an accurate indoor positioning technology that uses luminaires as transmitters. In particular, circular luminaires are a common source type for VLP, which are typically treated only as point sources for positioning, while ignoring their geometry characteristics. In this paper, the arc feature of the circular luminaire and the coordinate information obtained via visible light communication (VLC) are jointly used for positioning, and a novel perspective arcs approach is proposed for VLC-enabled indoor positioning. The proposed approach does not rely on any inertial measurement unit and has no tilted angle limitation at the user. First, a VLC assisted perspective circle and arc algorithm (V-PCA) is proposed for a scenario in which a complete luminaire and an incomplete one can be captured by the user. Based on plane and solid geometry theory, the relationship between the luminaire and the user is exploited to estimate the orientation and the coordinate of the luminaire in the camera coordinate system. Then, the pose and location of the user in the world coordinate system are obtained by single-view geometry theory. Considering the cases in which parts of VLC links are blocked, an anti-occlusion VLC assisted perspective arcs algorithm (OA-V-PA) is proposed. In OA-V-PA, an approximation method is developed to estimate the projection of the luminaire’s center on the image and, then, to calculate the pose and location of the user. Simulation results show that the proposed indoor positioning algorithm can achieve a 90th percentile positioning accuracy of around 10 cm. Moreover, an experimental prototype is implemented to verify the feasibility. In the established prototype, a fused image processing method is proposed to simultaneously obtain the VLC information and the geometric information. Experimental results in the established prototype show that the average positioning accuracy is less than 5 cm for different tilted angles of the user.

The general method of the tanker car mouth pose measurement

PurposeThe coupling process between the loading mechanism and the tank car mouth is a crucial step in the tank car loading process. The purpose of this paper is to design a method to accurately measure the pose of the tanker car.Design/methodology/approachThe collected image is first subjected to a gray enhancement operation, and the black parts of the image are extracted using Otsu’s threshold segmentation and morphological processing. The edge pixels are then filtered to remove outliers and noise, and the remaining effective points are used to fit the contour information of the tank car mouth. Using the successfully extracted contour information, the pose information of the tank car mouth in the camera coordinate system is obtained by establishing a binocular projection elliptical cone model, and the pixel position of the real circle center is obtained through the projection section. Finally, the binocular triangulation method is used to determine the position information of the tank car mouth in space.FindingsExperimental results have shown that this method for measuring the position and orientation of the tank car mouth is highly accurate and can meet the requirements for industrial loading accuracy.Originality/valueA method for extracting the contours of various types of complex tanker mouth is proposed. This method can accurately extract the contour of the tanker mouth when the contour is occluded or disturbed. Based on the binocular elliptic conical model and perspective projection theory, an innovative method for measuring the pose of the tanker mouth is proposed, and according to the space characteristics of the tanker mouth itself, the ambiguity of understanding is removed. This provides a new idea for the automatic loading of ash tank cars.

Design, integration, and evaluation of a robotic peach packaging system based on deep learning

Fruit packaging is one of the most time-consuming and labor-intensive tasks during postharvest commercialization. With the aging of the global population, it is necessary to apply robot to replace the manual manipulation. However, robotic packaging for fragile fruit is more complicated and difficult, compared with other postharvest processes, such as quality detection and grading. In this study, for better positioning accuracy and grasping robustness, we developed a prototype for peach packaging robot based on deep learning. First, the dataset for peach object detection was built, and YOLO v5 models with different width and depth were trained in an end-to-end manner on this dataset. Considering the requirements on both accuracy and real-time performance in fruit postharvest processing, YOLO v5 - S was finally adopted as the peach detection model for robotic manipulation, which can achieve mAP-50 = 0.996 on validation set and runs at 142.86 fps on RTX 3060. Next, the “Eye-on-Base” hand eye calibration method was used to solve the coordinate transformation matrix from the camera coordinate system to the robot base coordinate system. The results on landmark positioning experiment showed that the positioning error along X and Y axes was 4.87 mm and 5.00 mm on average, respectively. The positioning error alone Z direction was 18.47 mm on average, which was caused mainly by the depth perception error of the RGB-D camera. In the grasping experiment, the influence of the depth perception accuracy was explored, the grasping success rate for small, medium, and large size of peaches was 100 %, 97 %, and 97 %, respectively. Besides, the entire pipeline proposed in this study took 252.81 ms on average for depth perception, object detection, coordinate transformation, and grasping path planning. Finally, the early stage bruise of the peaches was also evaluated through SFDI technology. In general, this research provided a feasible and reliable scheme for the fruit packaging robot, which is potential to be deployed in postharvest commercialization.

SmartMocap: Joint Estimation of Human and Camera Motion Using Uncalibrated RGB Cameras

Markerless human motion capture (mocap) from multiple RGB cameras is a widely studied problem. Existing methods either need calibrated cameras or calibrate them relative to a static camera, which acts as the reference frame for the mocap system. The calibration step has to be done <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a priori</i> for every capture session, which is a tedious process, and re-calibration is required whenever cameras are intentionally or accidentally moved. In this paper, we propose a mocap method which uses multiple static and moving extrinsically uncalibrated RGB cameras. The key components of our method are as follows. First, since the cameras and the subject can move freely, we select the ground plane as a common reference to represent both the body and the camera motions unlike existing methods which represent bodies in the camera coordinate system. Second, we learn a probability distribution of short human motion sequences ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula> 1 sec) relative to the ground plane and leverage it to disambiguate between the camera and human motion. Third, we use this distribution as a motion prior in a novel multi-stage optimization approach to fit the SMPL human body model and the camera poses to the human body keypoints on the images. Finally, we show that our method can work on a variety of datasets ranging from aerial cameras to smartphones. It also gives more accurate results compared to the state-of-the-art on the task of monocular human mocap with a static camera. A video demo and our code are available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://tinyurl.com/yeykrb67</uri> and <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://tinyurl.com/2p9rme9y</uri> .

Precise measurement for line structure light vision sensor with large range

High precision and large measurement range are the target of any one three-dimensional scanner. For a line structure light vision sensor, measurement precision depends on its calibration results, i.e., determining mathematical expression of the light plane in camera coordinate system. However, as calibration results are locally optimal solutions, high precise measurement in a large range is difficult. In this paper, we give a precise measurement method and the corresponding calibration procedure for a line structure light vision sensor with a large measurement range. A motorized linear translation stages with a travel range of 150 mm and a planar target which is a surface plate with a machining precision of 0.05 mm are utilized. With the help of the linear translation stage and the planar target, functions which gives the relationship between center point of the laser stripe and the perpendicular/ horizontal distance are obtained. Once image of light stripe is captured, we can get a precise measurement result from the normalized feature points. Compared with a traditional measurement method, distortion compensation is not necessary and precision of measurement is improved significantly. Experiments show that root mean square error of measurement results according to our proposed method is reduced by 64.67% related to the traditional method.

Rapid and flexible calibration of DFPP using a dual-sight fusion target.

The parameter calibration of a digital fringe projection profilometry (DFPP) system is a fundamental step and directly related to 3D measurement accuracy. However, existing solutions based on geometric calibration (GC) suffer from the weakness of limited operability and practicality. In this Letter, a novel, to the best of our knowledge, dual-sight fusion target is designed for flexible calibration. The novelty of this target is the ability to directly characterize control rays for ideal pixels of the projector, and to transform the rays into the camera coordinate system, which replaces the traditional phase-shifting algorithm and avoids the error from the nonlinear response of the system. Attributed to the excellent position resolution of a position-sensitive detector within the target, the geometric relationship between the projector and camera can be easily established by projecting only one diamond pattern. Experimental results demonstrated that the proposed method using only 20 captured images is capable of achieving comparable calibration accuracy to the traditional GC method (20 images versus 1080 images, 0.052 pixels versus 0.047 pixels), which is suitable for rapidly and accurately calibrating the DFPP system in the 3D shape measurement field.

Calibration method of line-structured light sensors based on a hinge-connected target with arbitrary pinch angles.

Line-structured light 3D measurement is often used for 3D contour reconstruction of objects in complex industrial environments, where light plane calibration is a key step. In this paper, we propose a calibration method for a line-structured optical system based on a hinge-connected double-checkerboards stereo target. First, the target is moved randomly in multiple positions at any angle within the camera measurement space. Then, by acquiring any one image of the target with line-structured light, the 3D coordinates of the light stripes feature points are solved with the help of the external parameter matrix of the target plane and the camera coordinate system. Finally, the coordinate point cloud is denoised and used to quadratically fit the light plane. Compared with the traditional line-structured measurement system, the proposed method can acquire two calibration images at once; thus, only one image of line-structured light is needed to complete the light plane calibration. There is no strict requirement for the target pinch angle and placement, which improve system calibration speed with high accuracy. The experimental results show that the maximum RMS error of this method is 0.075mm, and the operation is simpler and more effective to meet the technical requirements of industrial 3D measurement.

Dynamic Synthesis of Three−Point Circle Peripheral Docking Technology Pose

Research on space docking technology was first motivated by the application scenario of space station docking in the aviation field. Due to the maturity of this technology, its application field is expanding to other industries. To benefit the intelligent transportation field, this study uses space docking technology to realize combination and reconstruction between car bodies. Different spatial docking methods and structural characteristics are determined by different application scenarios. The docking of the space station is completed in the suspended state of the body in the outer space environment, which requires advanced technology, is high in hardware cost, and involves a small channel diameter. In this study, the docking of the reconstructed vehicle is completed on the ground; thus, it is low in hardware cost and involves a large channel diameter. Based on the above technical requirements, a three−point circular peripheral docking method is designed for the reconstructed vehicle. A visual positioning system is built, the mapping relationship between the camera coordinate system and the landmark coordinate system rotation matrix and translation vector is established, and the adaptive capture behavior is realized by path planning through the inverse pose solution model. Simulation experiments demonstrate that the active and passive vehicle bodies can achieve compliance capture with small collision force under the two conditions of forward collision and oblique collision, and the recovery coefficient after collision and docking is in the range of (0, 0.01). The acceleration decay process under two working conditions is measured in the crash test of a sample vehicle, which verifies the feasibility of the space reconstruction of the vehicle docking mechanism and the ability of this configuration to achieve tasks, providing a constructive idea for space docking technology with a large channel diameter.

A single-vision dual imaging optical system in flip chip alignment

In the case of flip-chip, the key to high-quality packaging is the high-precision alignment of the chip to the PCB. High-precision alignment is usually achieved using vision. Since the lens and camera are expensive and the camera coordinates system conversion is cumbersome, the single-vision system is proposed. However, there are defects in that the loss of light source is large, and the coaxial optical lens cannot be used. In this paper, a new single-vision dual-imaging optical system is proposed based on Zemax, which effectively solves the defects of the old single-vision system. The results show that the system can reduce the use of the lens and camera, reduce the use cost of the equipment, and easily convert the camera coordinate system to ensure the imaging quality.

A visual measurement method of the three-dimensional coordinates of the center of forgings with asymmetric flash for the intelligent hammer die forging

Hammer die forging is a widely used mechanical manufacturing technology. Although it is easy to realize the automation of cutting and heating raw material, trimming the forging flash, and shaping the forgings in the processing of hammer die forging, it is difficult to achieve the automation of the forging process of hammer die forging, which is critical to the automated hammer die forging. It is because of the malposition phenomenon in which the forgings are often extracted out of the lower die cavity. Manual judgement of the phenomenon and manual clamping of the malpositioned forging are required to reset the forging. To achieve the automated forging process, it is necessary to identify the three-dimensional coordinates of the forging centre. However, the asymmetric flash of the forging reduces the localization accuracy. Therefore, a bidirectional correction and binocular vision localization (BCBVL) algorithm is proposed in this paper. However, identifying whether the malposition phenomenon occurs by the BCBLV method is time-consuming and can affect the execution of the subsequent processes such as the trimming and shaping processes. Hence, two methods based on the forging angle and the forging nonoverlapping area are proposed to obtain the fast judgement of the malpositioned forging. Experiments are conducted using a test bench composed of a binocular camera, an industrial manipulator, a 3D-printed die cavity, and a scraper forging of the coal mine scraper conveyor. The results indicate that the average localization error of BCBVL method is 7.31 mm in the left camera coordinate system and is 8.89 mm in the manipulator coordinate system. The two proposed fast judgement methods of the malpositioned forging take 0.32 s and 0.88 s, respectively. The study provides coordinates for the manipulator to grasp malpositioned forgings to achieve the automated forging process of hammer die forging.

A new method for high dynamic range 3D measurement combining adaptive fringe projection and original-inverse fringe projection

For fringe projection profilometry (FPP), high reflections on metal, plastic, and ceramic surfaces cause intensity saturation, resulting in three dimensional (3D) measurement errors. The measurement efficiency using the multiple exposure method (MEM) is low and the exposure time is difficult to quantify. The original and inverse fringe projection method (OIFPM) suffers from saturation of the opposite fringes on highly reflective surfaces. The adaptive fringe projection method (AFPM) is still limited by image dynamic range and pixel mapping accuracy. To this end, this paper proposes a new scheme combining OIFPM and AFPM, called the original and inverse adaptive fringe projection method (OIAFPM). Firstly, an adaptive intensity template in the camera coordinate system is generated. Secondly, a pixel mapping between the camera and projector images is established. Thirdly, original and inverse adaptive fringes are generated and projected. Finally, 72 wrapped phase calculation equations are given in detail. Experiments confirm that the 3D measurement employing the proposed OIAFPM is much better than that employing AFPM and OIFPM. Although the 3D measurement employing MEM is similar to that employing OIAFPM, the measurement efficiency employing OIAFPM is much higher than that employing MEM.

Non-Cooperative Spacecraft Pose Measurement with Binocular Camera and TOF Camera Collaboration

Non-cooperative spacecraft pose acquisition is a challenge in on-orbit service (OOS), especially for targets with unknown structures. A method for the pose measurement of non-cooperative spacecrafts based on the collaboration of binocular and time-of-flight (TOF) cameras is proposed in this study. The joint calibration is carried out to obtain the transformation matrix from the left camera coordinate system to the TOF camera system. The initial pose acquisition is mainly divided into feature point association and relative motion estimation. The initial value and key point information generated in stereo vision are yielded to refine iterative closest point (ICP) frame-to-frame registration. The final pose of the non-cooperative spacecraft is determined through eliminating the cumulative error based on the keyframes in the point cloud process. The experimental results demonstrate that the proposed method is able to track the target spacecraft during aerospace missions, which may provide a certain reference value for navigation systems.

A Palletizing System for Microchannel Heat Exchangers Based on 3D Visual Guidance

Aiming at the problems of slow manual palletizing, high risk and easy damage to products after the assembly of microchannel heat exchanger, a palletizing system based on 3D visual guidance is presented in this paper. Firstly, an automatic calibration method for RGB-D camera extrinsic parameters was adopted: used random sample consensus algorithm RANSAC for plane fitting, and the pallet was idealized as a plane. The camera extrinsic parameters were calculated according to the rotation relationship between the plane normal vector and the camera coordinate system. When it was performing detection, converted depth data into point cloud data and preprocessed, including coordinate transformation, downsampling, etc. After that, according to the characteristics of stacking, a point cloud segmentation algorithm based on depth and the number of points was used, which could not only segment the pallet and sponge strips, but also effectively detect obstacles. For different parts segmented, the pallet was positioned by fitting the minimum bounding rectangle, and the stacking depths were obtained by calculating the centroid of the sponge strips. Finally, a series of constraints were used to determine whether the unloading conditions were met. The experimental results show that the automatic calibration is effective, the time consuming is about 0.43s, and the depth range of the pallet is 11mm after calibration. The algorithm can accurately identify various situations above the stacking and the time consuming is about 1.63s.

Retracted] Motion Control System of IoT Intelligent Robot Based on Improved ResNet Model

In order to further optimize the precision and efficiency of intelligent robot navigation system control, an IoT intelligent robot motion control system based on the improved ResNet model is proposed. Based on the deep learning method, using the Faster R‐CNN target detection architecture and the ResNet50 convolutional neural network, the network is trained according to the characteristics of the operation target of the distribution line maintenance robot system. On this basis, combined with the binocular vision ranging principle, the coordinates of the job target in the camera coordinate system are measured, and the coordinates are converted into the robot base coordinate system through hand‐eye calibration, so as to complete the spatial positioning of the job target. The results showed that the errors of the binocular measurement methods adopted by the system are all within 1%. Conclusion. The method can well adapt to the complex background of the operation scene, the change of illumination, and the partial occlusion of the target and can meet the requirements of the distribution line maintenance robot for the measurement and positioning of the target space.

Delving Deep Into One-Shot Skeleton-Based Action Recognition With Diverse Occlusions

Occlusions are universal disruptions constantly present in the real world. Especially for sparse representations, such as human skeletons, a few occluded points might destroy the geometrical and temporal continuity critically affecting the results. Yet, the research of data-scarce recognition from skeleton sequences, such as one-shot action recognition, does not explicitly consider occlusions despite their everyday pervasiveness. In this work, we explicitly tackle body occlusions for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</i> keleton-based <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</i> ne-shot <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">A</i> ction <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</i> ecognition (SOAR). We mainly consider two occlusion variants: 1) random occlusions and 2) more realistic occlusions caused by diverse everyday objects, which we generate by projecting the existing IKEA 3D furniture models into the camera coordinate system of the 3D skeletons with different geometric parameters, ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.</i> , rotation and displacement). We leverage the proposed pipeline to blend out portions of skeleton sequences of the three popular action recognition datasets (NTU-120, NTU-60 and Toyota Smart Home) and formalize the first benchmark for SOAR from partially occluded body poses. This is the first benchmark which considers occlusions for data-scarce action recognition. Another key property of our benchmark are the more realistic occlusions generated by everyday objects, as even in standard recognition from 3D skeletons, only randomly missing joints were considered. We re-evaluate existing state-of-the-art frameworks for SOAR in the light of this new task and further introduce <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Trans4SOAR</i> – a new transformer-based model which leverages three data streams and mixed attention fusion mechanism to alleviate the adverse effects caused by occlusions. While our experiments demonstrate a clear decline in accuracy with missing skeleton portions, this effect is smaller with <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Trans4SOAR</i> , which outperforms other architectures on all datasets. Although we specifically focus on <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">occlusions</i> , <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Trans4SOAR</i> additionally yields state-of-the-art in the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">standard</i> SOAR without occlusion, surpassing the best published approach by <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$2.85\%$</tex-math></inline-formula> on NTU-120.

Accurate Head Pose Estimation Using Image Rectification and a Lightweight Convolutional Neural Network

Head pose estimation is an important step for many human-computer interaction applications such as face detection, facial recognition, and facial expression classification. Accurate head pose estimation benefits these applications that require face images as the input. Most head pose estimation methods suffer from perspective distortion because the users do not always align their face perfectly with the camera. This paper presents a new approach that uses image rectification to reduce the negative effect of perspective distortion and a lightweight convolutional neural network to obtain highly accurate head pose estimations. The proposed method calculates the angle between the optical axis of the camera and the projection vector of the center of the face. The face image is rectified using this estimated angle through perspective transformation. A lightweight network that is only 0.88 MB in size is designed to take the rectified face image as the input to perform head pose estimation. The output of the network, the head pose estimation of the rectified face image, is transformed back to the camera coordinate system as the final head pose estimation. Experiments on public benchmark datasets show that the proposed image rectification method and the newly designed lightweight network improve the accuracy of head pose estimation remarkably. Compared with state-of-the-art methods, our approach achieves both higher accuracy and faster processing speed.

A novel motionless calibration method for augmented reality surgery navigation system based on optical tracker

Augmented reality (AR) surgery navigation systems display the pre-operation planned virtual model at the accurate position in the real surgical scene to assist the operation. Accurate calibration of the mapping relationship between the virtual coordinate and the real world is the key to the virtual-real fusion effect. Former calibration methods require the doctor user to conduct complex manual procedures before usage. This paper introduces a novel motionless virtual-real calibration method. The method only requires to take a mixed reality image containing both virtual and real marker balls using the built-in forward camera of the AR glasses. The mapping relationship between the virtual and real spaces is calculated by using the camera coordinate system as a transformation medium. The composition and working process of the AR navigation system is introduced, and then the mathematical principle of the calibration is designed. The feasibility of the proposed calibration scheme is verified with a verification experiment, and the average registration accuracy of the scheme is around 5.80mm, which is of same level of formerly reported methods. The proposed method is convenient and rapid to implement, and the calibration accuracy is not dependent on the user experience. Further, it can potentially realize the real-time update of the registration transformation matrix, which can improve the AR fusion accuracy when the AR glasses moves. This motionless calibration method has great potential to be applied in future clinical navigation research.

A Novel Training Quantitative Evaluation Method Based on Virtual Reality

Quantitative training virtualization can be applied in the fields of human–computer interaction, virtual reality and motion analysis, and has attracted much attention. Based on the virtual reality theory, this paper constructs a training quantitative evaluation method, evaluates the trainer’s ergonomics, and finally compares the evaluation method with the simulation results. According to the collected training data, this paper uses the methods of model reuse and feature parameter adjustment in the Jack software to quickly generate a 3D training model with the required percentages, and performs data reorganization and analysis on the captured training data, which solves the problem of training quantitative evaluation and the problem of uncertainty of results. During the simulation process, according to its reorganized data, a large number of comparative experiments and evaluations were performed on the performance of the model proposed in this paper on multiple indicators of multiple public data sets. The experimental results show that the cycle is reduced by 10 times, the mini-batch is 32, and the sequence length is 16. In this way, the spatial characteristics of the channel coupling relationship can be better analyzed, and the effect of spatial cognitive training can be effectively evaluated. The training pose and shape estimation model and the corresponding data set and multiple indicators have reached the performance of the existing state-of-the-art models. The integrated model of accurate training pose and shape sequence in the camera coordinate system can be reconstructed, which effectively enhances the effectiveness of the virtual scene parameter adjustment strategy.