Accuracy Of Position Detection Research Articles

Accuracy and Uncertainty of Position Detection of Moving Objects by Resonator Arrays

Arrays of magnetically coupled resonators have recently been proposed as position sensors for both static and dynamic applications. Despite their promising characteristics, an accurate evaluation of their functioning in non-ideal conditions is fundamental and necessary to adapt them to industrial contexts. This article analyses the accuracy of the position measurement in resonator arrays under system parameter variations. Appropriate parameters for the evaluation of the sensor performance have been discussed and analysed considering non-ideal system components by exploiting the Monte Carlo method.

Dense Pedestrian Detection Based on GR-YOLO.

In large public places such as railway stations and airports, dense pedestrian detection is important for safety and security. Deep learning methods provide relatively effective solutions but still face problems such as feature extraction difficulties, image multi-scale variations, and high leakage detection rates, which bring great challenges to the research in this field. In this paper, we propose an improved dense pedestrian detection algorithm GR-yolo based on Yolov8. GR-yolo introduces the repc3 module to optimize the backbone network, which enhances the ability of feature extraction, adopts the aggregation-distribution mechanism to reconstruct the yolov8 neck structure, fuses multi-level information, achieves a more efficient exchange of information, and enhances the detection ability of the model. Meanwhile, the Giou loss calculation is used to help GR-yolo converge better, improve the detection accuracy of the target position, and reduce missed detection. Experiments show that GR-yolo has improved detection performance over yolov8, with a 3.1% improvement in detection means accuracy on the wider people dataset, 7.2% on the crowd human dataset, and 11.7% on the people detection images dataset. Therefore, the proposed GR-yolo algorithm is suitable for dense, multi-scale, and scene-variable pedestrian detection, and the improvement also provides a new idea to solve dense pedestrian detection in real scenes.

MSSD: multi-scale self-distillation for object detection

Knowledge distillation techniques have been widely used in the field of deep learning, usually by extracting valid information from a neural network with a large number of parameters and a high learning capacity (the teacher model) to a neural network with a small number of parameters and a low learning capacity (the student model). However, there are inefficiencies in the transfer of knowledge between teacher and student. The student model does not fully learn all the knowledge of the teacher model. Therefore, we aim to achieve knowledge distillation of our network layer by a single model, i.e., self-distillation. We also apply the idea of self-distillation to the object detection task and propose a multi-scale self-distillation approach, where we argue that knowledge distillation of the information contained in feature maps at different scales can help the model better detect small targets. In addition, we propose a Gaussian mask based on the target region as an auxiliary detection method to improve the accuracy of target position detection in the distillation process. We then validate our approach on the KITTI dataset using a single-stage detector YOLO. The results demonstrate a 2.8% improvement in accuracy over the baseline model without the use of a teacher model.

Improvement of lithium battery corner detection accuracy based on image restoration method

Target detection technology has been widely used in the automatic production of lithium batteries. However, motion blur will lead to the reduction of the angular position detection accuracy of lithium batteries. To solve this problem, an improved fuzzy recovery model for angular position of lithium battery is proposed in this paper. Firstly, the improved lightweight neural network RepVGG was used as the main module of the backbone network, so that the network could improve the performance of network feature extraction while reducing the number of calculation parameters and improving the reasoning speed of fuzzy restoration. Secondly, we optimize the multi-Dconv head transposed attention (MDTA) module and reference it to the generator, which reduces the complexity of the model and strengthens the network’s attention to details and textures, and improves the visual effect of the restored image. Finally, we design a lightweight globally connectable residual network called SAC Block and use it to to improve the discriminator, which enhances the global receptive field of the model and improves the structural similarity between the restored image and the original image. In order to verify the effectiveness of the method, we verify it on the self-built dataset and GoPro dataset. The experiments show that our proposed lightweight model improves the peak signal-to-noise ratio (PSNR) index by 9.2% and 8.6% respectively compared with the original model. The visual effect of the restored image is better than that of other current similar algorithms, and it is confirmed that our model can better improve the accuracy of lithium battery angular position detection.

Solar position detection method by bionic polarized light compass.

To address the needs of polarized light navigation for accurate position information of feature points in the sky, an accurate solar position detection method based on an all-sky polarization pattern imaging system is proposed. Unlike the traditional spot-based solar position detection method, this method uses the polarization information inherent in the atmosphere to accurately measure solar position. This approach is characterized by simple detection, high accuracy, and wide application range. The optical acquisition system is composed of three miniature large-field camera modules and polarizers, which enables a more compact structure, smaller size, and lesser height. Based on this principle, the solar position solution algorithm was simulated and then verified in various weather environments using the optical acquisition system built as part of this study. Solar position was detected at different moments on the same day in clear weather, and the accuracy of the measured solar altitude and azimuth angles was 0.024° and 0.03°, respectively. The accuracy of the measured solar altitude and azimuth angles was 0.08° and 0.05°, respectively, when the sun was shielded by high-rise buildings and 0.3° and 0.1° when the sun was shielded by branches and tree leaves. Aerosol concentrations exceeding a certain amount destroyed the Rayleigh distribution pattern of polarized light, thus affecting solar position detection accuracy. It is concluded that this novel detection method can not only meet the needs of polarized light navigation for solar position, but also provide a new exploration idea for enthusiasts who are eager to explore the mysteries of the universe.

Research on Quadrant Detector Multi-Spot Position Detection Based on Orthogonal Frequency Division Multiplexing

Free space optical communication is developing towards laser communication networking. A novel method of quadrant detector (QD) multi-spot position detection based on orthogonal frequency division multiplexing (OFDM) is proposed for multi-spot laser communication systems. The mathematical model is constructed, and the Monte Carlo method is used to validate it. The position calculation of three beams incident on QD is simulated. The influence of key parameters on the accuracy of position detection is analyzed when the spots are at the same position and a different position. The results show that when the SNR of the system is 31.74 dB, the radius of the Gauss spot is 2 mm, the number of FFT (fast Fourier transform) points is 1024, and the center of the multi-spot is at the same position of the detector target; the accuracy of signal position detection calculated by the equation is 1.433 μm, and the simulation results are 1.351 μm, 1.354 μm, and 1.389 μm, respectively. When the center position of the multi-spot is at different positions of the detector target, the detection accuracy calculated by the formula is 1.438 μm, 1.433 μm, and 1.434 μm, respectively, and the simulation results are 1.419 μm, 1.387 μm, and 1.346 μm, respectively. The experimental results verify the effectiveness of the proposed multi-target simultaneous detection method. This article proposes a new multi-spot position detection method which can not only achieve one-to-multiple node laser communication but also improve the accuracy of point position detection.

A construction method of reverberation suppression filter using an end-to-end network.

Reverberation is the primary background interference of active sonar systems in shallow water environments, affecting target position detection accuracy. Reverberation suppression is a signal processing technique used to improve the clarity and accuracy of echo by eliminating the echoes, reverberations, and noise that occur during underwater propagation.This paper proposes an end-to-end network structure called the Reverberation Suppression Network (RS-U-Net) to suppress the reverberation of underwater echo signals. The proposed method effectively improves the signal-to-reverberation ratio (SRR) of the echo signal, outperforming existing methods in the literature. The RS-U-Net architecture uses sonar echo signal data as input, and a one-dimensional convolutional network (1D-CNN) is used in the network to train and extract signal features to learn the main features. The algorithm's effectiveness is verified by the pool experiment echo data, which shows that the filter can improve the detection of echo signals by about 10 dB. The weights of reverberation suppression tasks are initialized with an auto-encoder, which effectively uses the training time and improves performance. By comparing with the experimental pool data, it is found that the proposed method can improve the reverberation suppression by about 2 dB compared with other excellent methods.

A Wasserstein generative adversarial network with gradient penalty for active sonar signal reverberation suppression

Reverberation is the primary background interference of active sonar systems in shallow water environments, affecting target position detection accuracy. Reverberation suppression is a signal processing technique used to improve the clarity and accuracy of received signals by eliminating the echoes, reverberations, and noise that occur during underwater propagation. Existing reverberation suppression methods include algorithms based on Time-Frequency domain processing, noise reduction, adaptive filtering, and spectral subtraction, but their performance in high-reverberation environments (echo of small targets) still does not meet the requirements of target detection. To address the impact of high reverberation environments, we propose a structural suppression method based on the Wasserstein gradient penalty generative adversarial network (RSWGAN-GP). The reverberation suppression generation network uses a one-dimensional convolutional network structure to process normalized time-domain signals and achieves the reconstruction of the reverberation signal through Encoder-Decoder. The proposed method is verified through accurate and effective data collection during sea trials. Comparative results show that RSWGAN-GP effectively suppresses reverberation in observation signals with multiple bright spots, improving the signal-to-reverberation ratio by approximately 10 dB compared to other excellent algorithms and enhancing the information analysis and feature extraction capabilities of active sonar signals.

Characteristics of detection accuracy of the patient setup using InBore optical patient positioning system.

This study aimed to evaluate the detection accuracy of the AlignRT-InBore system in surface-guided radiation therapy using a phantom and to determine the feasibility of the system by conducting a comparative analysis with cone-beam computed tomography (CBCT) registration. The AlignRT-InBore system integrated with the ETHOS Therapy was used. A phantom and a QUASAR phantom were employed to examine the specific areas of interest relevant to clinical cases. The evaluation involved monitoring translations for approximately 30 min and assessing the position detection accuracy for static and moving objects. Fifty clinical cases were used to evaluate the position detection accuracy and its relationship with the localization accuracy of CBCT before treatment. The detection accuracy of static and moving objects was within 1.0 mm using the phantom. However, the longitudinal direction tended to be larger than the other directions. Regarding the accuracy of localization in clinical cases, a strong and statistically significant (p<0.01) correlation was observed in each direction. A detection accuracy within 1.0 mm is possible for static and moving objects. The detection accuracy of the patient setup using the InBore optical patient positioning system was extremely high, and the patient could be detected with high precision, suggesting its usefulness.

Autonomous Parking Space Detection for Electric Vehicles Based on Improved YOLOV5-OBB Algorithm

Currently, in the process of autonomous parking, the algorithm detection accuracy and rate of parking spaces are low due to the diversity of parking scenes, changes in lighting conditions, and other unfavorable factors. An improved algorithm based on YOLOv5-OBB is proposed to reduce the computational effort of the model and increase the speed of model detection. Firstly, the backbone module is optimized, the Focus module and SSP (Selective Spatial Perception) module are replaced with the general convolution and SSPF (Selective Search Proposals Fusion) modules, and the GELU activation function is introduced to reduce the number of model parameters and enhance model learning. Secondly, the RFB (Receptive Field Block) module is added to fuse different feature modules and increase the perceptual field to optimize the small target detection. After that, the CA (coordinate attention) mechanism is introduced to enhance the feature representation capability. Finally, the post-processing is optimized using spatial location correlation to improve the accuracy of the vehicle position and bank angle detection. The implementation results show that by using the improved method proposed in this paper, the FPS of the model is improved by 2.87, algorithm size is reduced by 1 M, and the mAP is improved by 8.4% on the homemade dataset compared with the original algorithm. The improved model meets the requirements of perceived accuracy and speed of parking spaces in autonomous parking.

Sensorless control of SPMSM based on an adaptive sliding mode observer with optimized phase-locked loop structure

To improve the speed and position detection accuracy of surface-mount permanent magnet synchronous motor (SPMSM) vector control and reduce unnecessary chattering of the system, this paper proposes a sensorless control strategy of SPMSM based on an adaptive sliding mode observer (ASMO) with optimized phase-locked loop (OPLL) structure. First, in order to overcome the chattering of system caused by discontinuous switching characteristic of signum function in conventional sliding mode observer (CSMO), a continuous saturation function is selected as the switching function. The ASMO adopts the system state-related adaptive gain function to adjust the switching gain value of the system in real time, which overcomes the slow response speed or severe chattering of the system caused by the constant switching gain of CSMO. Second, to reduce the phase delay between the rotor position estimation value and the actual value caused by the adoption of low-pass filter (LPF) and the position estimation error caused by arctangent function method, an OPLL method is designed for accurate estimation of rotor position and speed. Finally, the effectiveness and feasibility of the proposed improved SMO algorithm is verified by simulation and experiments on an SPMSM with rated power of 2 kW.

Initial Rotor Position Detection of SPMSM with High-frequency Signal Injection

The accuracy of initial rotor position detection is important for senseless control, meanwhile, high frequency signal injection takes its advantages for its simple principle, small calculation amount and good real-time performance. In this paper, the principle of high frequency signal injection is analysed and systematically studied from position information error reading and the direction of d-axis. Besides, factors which may lead to the error of position information error reading is also studied, the second-order notch filter is added to get higher accuracy. Finally, the model of high frequency signal injection is set up to verify the effectiveness of the method, the result shows that method can run well at 0 speed and effectively estimate the actual rotor position.

Weak celestial source fringes detection based on channel attention shrinkage networks and cluster-based anchor boxes generation algorithm

Detecting weak celestial source signals from massive radio data is a very challenging task because the radiation received by radio telescope is very weak and prone to disturbances. In order to detect these weak signals, we propose a two-stage object detection method that performs more finely in computer vision tasks. The novelty of the proposed method is to combine traditional soft thresholding denoising methods with attention mechanisms in deep neural networks. We propose a channel attention shrinkage network as the backbone of the object detection model to extract the features of weak signals from celestial sources by removing noise-related information. Moreover, targeting the characteristics of celestial source fringes in phase images, we propose a cluster-based anchor boxes generation algorithm to improve the accuracy of fringes position detection. We also introduce the CIoU loss function to improve the performance of the model because of the large aspect ratio of the celestial source fringes in the phase image. We generate simulated celestial source fringes data based on the parameters of the observation system to train our model and conduct experiments to evaluate the performance of the proposed algorithm. Our model obtains satisfactory detection accuracy and accurate for the location of celestial source fringes.

Location and corrosion detection of tower grounding conductors based on electromagnetic measurement

Tower grounding conductors are buried underground and serve as the grounded discharge channel for the fault or lightning current of a transmission power system. The performance of the grounding conductor is crucial for the safe and reliable operation of transmission power systems. This study proposes a steel corrosion detection and location method for tower grounding conductors using electromagnetic measurements. To measure the surface alternating current magnetic field from the tower grounding conductor, a three-axis magnetic sensor array was constructed using six anisotropic magnetoresistive (AMR) magnetic sensors with a small size (mm3). Through simulation analysis, the structural size of the magnetic sensor array was determined, and the feasibility of the detection principle was analyzed. The experimental results showed that the detection accuracy of the grounding conductor position can reach ± 0.1 m. The maximum deviation of the depth detection was 0.0964 m for the square-type grounding conductor. Furthermore, the simulation and experiment demonstrate that the value of fuzzy closeness decreases gradually with an increase in the degree of corrosion of the grounding conductor, proving that the degree of corrosion of the grounding conductor can be evaluated according to the value of fuzzy closeness. The proposed method has significant potential for engineering applications in the detection and maintenance of tower grounding conductors.

Effect of proton beam irradiation on the tracking efficiency of CMOS image sensors

A star tracker provides accurate space positioning and reference for satellites, intercontinental strategic missiles, and other spacecrafts. However, the main imaging unit of the star sensor – the image sensor – is affected by the space radiation environment and, in turn, affects the precision with which the star is located by the star tracker. In this study, the parameter degradation of a CMOS image sensor (CIS) after proton irradiation with different fluences was investigated. An outfield test platform for star map collection was built using the star sensor lens and image collection system. The influence of dark current, dark-current nonuniformity, and photo-response nonuniformity of the irradiated CIS on the star diagonal distance measurement error and star-point centroid position detection accuracy was studied. The results showed that with increasing proton fluences, the CIS noise increased, leading to an increase in the error in the measured diagonal distance of the star and a decrease in the star’s position detection accuracy. Among these parameters, the dark current plays the greatest role in influencing the measurement accuracy of the star tracker. Furthermore, when a tracker is exposed to space radiation with fluences that are same as those used in this experiment, it is beneficial to reduce the integration time. This reduction in the time will decrease the noise and improve the position measurement accuracy.

Research on improvement of defect detection accuracy by resonance judgment for noncontact acoustic inspection method by acoustic irradiation-induced vibration

Noncontact acoustic inspection methods using acoustic irradiation-induced vibration and laser Doppler vibrometer that can perform defect exploration from a distance are being studied. This method has the feature that it can measure a wide range of measurement objects such as composite materials used for aerospace as well as concrete structures such as tunnels and bridges without contact. From the experimental results, it was found that the increase in noise level due to the decrease in the return light of the laser due to the condition of the measurement surface causes a decrease in the estimation accuracy of defect exploration. Therefore, it has been clarified that the detection accuracy of the defect position can be improved by devising a resonance judgement process for discriminating the signal and noise due to the resonance of the defect portion.

Benchmarking High-Fidelity Pedestrian Tracking Systems for Research, Real-Time Monitoring and Crowd Control

High-fidelity pedestrian tracking in real-life conditions has been an important tool in fundamental crowd dynamics research allowing to quantify statistics of relevant observables including walking velocities, mutual distances and body orientations. As this technology advances, it is becoming increasingly useful also in society. In fact, continued urbanization is overwhelming existing pedestrian infrastructures such as transportation hubs and stations, generating an urgent need for real-time highly-accurate usage data, aiming both at flow monitoring and dynamics understanding. To successfully employ pedestrian tracking techniques in research and technology, it is crucial to validate and benchmark them for accuracy. This is not only necessary to guarantee data quality, but also to identify systematic errors. Currently, there is no established policy in this context. In this contribution, we present and discuss a benchmark suite, towards an open standard in the community, for privacy-respectful pedestrian tracking techniques. The suite is technology-independent and it is applicable to academic and commercial pedestrian tracking systems, operating both in lab environments and real-life conditions. The benchmark suite consists of 5 tests addressing specific aspects of pedestrian tracking quality, including accurate line-based crowd flux estimation, local density estimation, individual position detection and trajectory accuracy. The output of the tests are quality factors expressed as single numbers. We provide the benchmark results for two tracking systems, both operating in real-life, one commercial, and the other based on overhead depth-maps developed at TU Eindhoven, within the Crowdflow topical group. We discuss the results on the basis of the quality factors and report on the typical sensor and algorithmic performance. This enables us to highlight the current state-of-the-art, its limitations and provide installation recommendations, with specific attention to multi-sensor setups and data stitching.

Commissioning and routine quality assurance of the Radixact Synchrony system

The Radixact Synchrony system allows for target motion correction when tracking either fiducials in/around the target or a dense lesion in the lung. As such evaluation testing and quality assurance (QA) tests are required. To allow for QA procedures to be performed with a range of available phantoms evaluation of the dosimetric delivery accuracy was performed for a range of motions, phantoms, and motion platforms. A Computerized Imaging Reference Systems, Incorporated (CIRS) 1D motion platform and Accuray Tomotherapy "Cheese" phantom was utilized to perform absolute dose and GafChromic EBT3 film measurements. A HexaMotion platform and Delta4 phantom were utilized to quantify the effects of 1D and 3D motions. Inter-device comparison was performed with the ArcCHECK and Delta4 phantoms and GafChromic EBT3 film, five patient plans were delivered to each phantom when static and with two different motion types both with and without Synchrony motion correction. A range of QA tests are described. A phantom was designed to allow for daily verification of system functionality. This test allows for the detection of either fiducials or a dense silicone target with a stationary phantom. Monthly testing procedures are described that allow the user to verify the dosimetric improvement when utilizing synchrony delivery motion compensation versus uncorrected motions. These can be performed utilizing a 1D motion stage with an ion-chamber and GafChromic EBT3 film to allow for a 2D dosimetric validation. Alternatively, a 3D motion platform can be utilized where available. Monthly and annual imaging tests are described. Finally, annual test procedures designed to verify the coincidence of the imaging system and treatment isocenter are described. The evaluation of the Synchrony system using a range of QA devices shows consistently high dosimetric accuracy with similar trends in passing criteria found with GafChromic EBT3 film, ArcCHECK, and Delta4 phantoms for density-based respiratory model compensation. These results highlight the large improvements in the dose distribution when motion is accounted for with the Synchrony system as measured with a range of phantoms and motion platforms that the majority of users will have available. The testing methods and QA procedures described provide guidance for new users of the Radixact Synchrony system as they implement their own QA programs for this system, until such time as an AAPM task group report is made available. QA procedures including Kilovolts (kV) imaging quality metrics and imaging dose parameters, dose deposition accuracy, target detection coincidence, and target position detection accuracy are described.

路面電車における衛星測位の精度評価手法の検討

The trolley contactors installed on trolley wires are used to detect streetcars' positions and control their routes. The passage of a streetcar is detected when the pantograph contacts the mechanical switch of the trolley contactor. This requires periodic maintenances in high places, which are heavy burdens. Global Navigation Satellite System (GNSS) has been considered as an alternative to the trolley contactors. The accuracy of GNSS varies greatly depending on the surrounding environment. It is necessary to evaluate the accuracy of streetcar position detection using GNSS in advance. We propose the evaluation technique for the accuracy of streetcar position detection using GNSS.

IoMT-Enabled Fusion-Based Model to Predict Posture for Smart Healthcare Systems

Smart healthcare applications depend on data from wearable sensors (WSs) mounted on a patient’s body for frequent monitoring information. Healthcare systems depend on multi-level data for detecting illnesses and consequently delivering correct diagnostic measures. The collection of WS data and integration of that data for diagnostic purposes is a difficult task. This paper proposes an Errorless Data Fusion (EDF) approach to increase posture recognition accuracy. The research is based on a case study in a health organization. With the rise in smart healthcare systems, WS data fusion necessitates careful attention to provide sensitive analysis of the recognized illness. As a result, it is dependent on WS inputs and performs group analysis at a similar rate to improve diagnostic efficiency. Sensor breakdowns, the constant time factor, aggregation, and analysis results all cause errors, resulting in rejected or incorrect suggestions. This paper resolves this problem by using EDF, which is related to patient situational discovery through healthcare surveillance systems. Features of WS data are examined extensively using active and iterative learning to identify errors in specific postures. This technology improves position detection accuracy, analysis duration, and error rate, regardless of user movements. Wearable devices play a critical role in the management and treatment of patients. They can ensure that patients are provided with a unique treatment for their medical needs. This paper discusses the EDF technique for optimizing posture identification accuracy through multi-feature analysis. At first, the patients’ walking patterns are tracked at various time intervals. The characteristics are then evaluated in relation to the stored data using a random forest classifier.