Accurate Detection and Smoothness-Oriented Avoidance Method of Singularity in 5-Axis CNC Machining

Tool path generation is a fundamental problem in 5-axis CNC machining, which consists of tool orientation planning and cutter-contact (CC) point planning. The planning strategy highly depends on the type of tool cutters. For ball-end cutters, the tool orientation and CC point location can be planned separately; while for flat end cutters, the two are highly dependent on each other. This paper generates a smooth tool path of workpiece surfaces for flat end mills from two stages: Computing smooth tool orientations on the surface without gouging and collisions and then designing the CC point path. By solving the tool posture optimization problem the authors achieve both the path smoothness and the machining efficiency. Experimental results are provided to show the effectiveness of the method.

Aiming at the problem of singular configuration of industrial robot in linear operation, this paper analyzes and studies the singularity configuration and singularity avoidance method of industrial robot, and a dynamic damping least square method singularity avoidance trajectory planning algorithm based on minimum singular value is proposed. The kinematics model of the robot with spherical wrist structure is established. Based on the decoupling analysis of the robot singularity, the singularity mathematical expressions of the wrist, the elbow and the shoulder are obtained respectively. It is closely related to the length and offset of connecting link. The dynamic damped least square method based on the minimum singular value is used to adjust the trajectory of the Cartesian space and the mapped joint space in the singular region. Simulation results show that the velocity of the proposed method is stable near the singular configuration, and there is no uncontrollable phenomenon of motion discontinuity and stability degradation.

In industrial inspection, X-ray detection methods are the mainstream approach for non-destructive testing (NDT) of weld defects. In response to the issues of insufficient detection accuracy and slow detection speed in existing X-ray weld defect detection (WDD) methods, a lightweight X-ray WDD model, AFD-YOLOv10, based on an improved YOLOv10n, is proposed. First, by introducing variable kernel convolution (AKConv) to replace traditional convolution in the backbone network, the model better adapts to the multi-scale variations in weld defects while maintaining its lightweight nature. Second, a lightweight C2f-Faster module is incorporated into both the backbone and neck networks to achieve a more symmetrical and efficient feature flow, reducing the model’s computational complexity and achieving lightweight design. Finally, dynamic upsampling (DySample) is added to the neck network to enhance the model’s detection accuracy for targets of different scales. This combination of innovations strikes an effective symmetry between model complexity, inference speed, and detection performance. Experimental results show that the improved AFD-YOLOv10 model achieves accuracies, recall rates, and mean average precision values of 90.7%, 88.8%, and 93.8%, respectively, on five typical X-ray weld defects, representing improvements of 4.9%, 4.1%, and 5.3% over the YOLOv10n baseline model, with a 10.1% reduction in model parameters and a 13.3% increase in detection speed. Compared with other existing mainstream detection methods, the AFD-YOLOv10 model not only improves the accuracy of X-ray WDD but also achieves model lightweighting, demonstrating overall detection performance superior to other mainstream algorithms, thus meeting the industrial production requirements for X-ray WDD. Additionally, generalization experiments conducted using a public dataset of surface defects in steel validate the good generalization performance of the AFD-YOLOv10 model.

An accurate detection and segmentation model of obscured green fruits

In view of the need to remove empty cells and unqualified seedlings for automatic transplanting of leafy vegetable seedlings, this paper proposes a method to detect the growth parameters of leafy vegetable seedlings by using machine vision technology. This method uses the image processor PV200 to perform image grayscale, threshold segmentation, corrosion, expansion, area division, etc. to obtain the pixel value of the leaf area of the seedling and compare it with the set standard value, which provides guiding information for eliminating empty cells and unqualified seedlings. Lettuce seedlings at 17 days, 20 days, and 22 days of seedling age were used as the test objects, and the growth status and test results of the seedlings were analyzed to determine the optimum seedling age for transplanting. The test results show that there is basically no leaf cross-border between the lettuce seedlings at the age of 17 days, the average pixel area of the leaves is 3771.74, and the detection accuracy rate is 100%; the seedlings at the age of 22 days grow 5–6 leaves, the detection accuracy of unqualified seedlings and qualified seedlings was 62.50% and 88.16%, respectively, and the comprehensive detection accuracy was 85.71%. The comprehensive detection accuracy rate showed a downward trend with the increase of seedling age, mainly due to the partial occlusion between leaves. The transplanting of leafy vegetable seedlings is a sparse transplanting operation, and the seedling spacing increases after transplanting. Therefore, the detection of seedlings in the process of transplanting can greatly improve the recognition accuracy and solve the problem that the leaves of the seedlings in the seedling tray are obscured by each other and affect the detection accuracy. The research results can provide a theoretical basis and design reference for the development of the visual inspection system and the transplanting actuator of the leafy vegetable seedlings transplanting robot.

Voltage sag characteristic is an important indicator of power quality. Considering the large number of voltage sag sensitive loads in power systems, it is essential to identify voltage sag accurately and quickly to ensure safe and stable operation. Based on the concept and characteristics of voltage sag phenomenon, this paper summarizes the principles of different voltage sag detection methods in the time domain and transform domain, and analyzes in detail the RMS method, the peak voltage method, the fundamental component method based on the time domain, the wavelet transform method based on the transform domain, the dq coordinate transform detection method based on the instantaneous reactive power theory, and other methods such as Kalman filter detection method based on detection delay, calculation amount of detection method, anti-interference ability, detection accuracy and other performance. The typical detection algorithms in the time domain and the transform domain are analyzed. Finally, the main detection methods listed in this paper are summarized.

In this article, a fast approach for robust trajectory planning, in the task space, of redundant robot manipulators is presented. The approach is based on combining an original method for obstacle avoidance by the manipulator configuration with the traditional potential field approach for the motion planning of the end‐effector. This novel method is based on formulating an inverse kinematics problem under an inexact context. This procedure permits dealing with the avoidance of obstacles with an appropriate and easy to compute null space vector; whereas the avoidance of singularities is attained by the proper pseudoinverse perturbation. Furthermore, it is also shown that this formulation allows one to deal effectively with the local minimum problem frequently associated with the potential field approaches. The computation of the inverse kinematics problem is accomplished by numerically solving a linear system, which includes the vector for obstacle avoidance and a scheme for the proper pseudoinverse perturbation to deal with the singularities and/or the potential function local minima. These properties make the proposed approach suitable for redundant robots operating in real time in a sensor‐based environment. The developed algorithm is tested on the simulation of a planar redundant manipulator. From the results obtained it is observed that the proposed approach compares favorably with the other approaches that have recently been proposed. © 1995 John Wiley & Sons, Inc.

The Visible Infrared Imaging Radiometer Suite (VIIRS) day/night band (DNB) data are very sensitive to low radiation and capable of detecting faint light sources emitted by vessels at night. Existing vessel detection methods are mainly based on pixel statistical feature estimation or manual experience to determine the threshold for detection. In complex scenes, problems such as interference targets and inaccurate background modeling result in inaccurate detection accuracy and poor robustness. In this article, a vessel detection method based on an improved constant false alarm rate (CFAR) detector is proposed, and more accurate threshold selection is obtained through background sample truncation and distribution adjustment. Then, the local peak detection algorithm removes the bright spots in the nonvessel location and realizes the vessel detection. We selected data from two research areas, the waters around the East China Sea and the waters around the Gulf of Mexico of the United States, to build a vessel dataset and applied the algorithm to the dataset. The experimental results show that the total detection accuracy of the algorithm is 94.48%, and the recall rate is 93.40%, which is higher than the other two comparison methods. Especially in complex scenarios with high target density, such as ports, the recall rate is significantly improved, which proves the applicability of the algorithm.

Background: Forensic toxicology plays a crucial role in substance abuse detection, criminal investigations, and public health interventions. The increasing prevalence of novel psychoactive substances, opioid abuse, and drug-related fatalities has necessitated advancements in toxicological techniques to improve detection accuracy and response strategies. Despite the growing application of high-resolution analytical tools, gaps remain in real-time detection capabilities and their integration into forensic and clinical settings. Objective: This systematic review aims to evaluate recent advancements in forensic toxicology for substance abuse detection and assess their implications for public health policies and forensic investigations. Methods: A systematic review was conducted following PRISMA guidelines, searching PubMed, Scopus, Web of Science, and Cochrane Library for studies published between 2019 and 2024. Inclusion criteria comprised peer-reviewed studies on forensic toxicology methods for substance detection, epidemiological trends, and their impact on public health. Non-English studies, animal research, and conference abstracts were excluded. Data extraction focused on study design, sample size, analytical techniques, and key findings. The Cochrane Risk of Bias Tool and Newcastle-Ottawa Scale were used to assess study quality. Results: A total of eight studies met the inclusion criteria. Emerging toxicological techniques, including high-resolution mass spectrometry, biosensors, and portable detection devices, demonstrated enhanced sensitivity in identifying illicit substances. The review also highlighted the growing burden of opioid abuse, particularly xylazine co-use, and the limitations of conventional toxicological screening in detecting emerging substances. Variability in methodologies and the risk of publication bias were noted as challenges affecting data synthesis. Conclusion: Advancements in forensic toxicology have significantly improved drug detection accuracy, aiding both legal investigations and public health interventions. However, challenges remain in standardizing methodologies and ensuring real-time detection of emerging substances. Future research should focus on refining forensic toxicology protocols and enhancing collaboration between forensic scientists, healthcare professionals, and policymakers to mitigate the public health impact of substance abuse.

Channel pruned YOLO V5s-based deep learning approach for rapid and accurate apple fruitlet detection before fruit thinning

Detecting careless responding in survey data is important to ensure the credibility of study findings. Of several available detection methods, personal reliability (PR) is one of the best-performing indices. Curran, Journal of Experimental Social Psychology, 66, 4-19, (2016) proposed a resampled version of personal reliability (RPR). Compared to the conventional PR or even–odd consistency, in which just one set of scale halves is used, RPR is based on repeated calculation of PR across several randomly rearranged sets of scale halves. RPR should therefore be less affected than PR by random errors that may occur when a specific set of scale half pairings is used for the PR calculation. In theory, RPR should outperform PR, but it remains unclear whether it in fact does, and under what conditions the potential gain in detection accuracy is the most pronounced. We conducted two studies: a simulation study examined the performance of the conventional PR and RPR in detecting simulated careless responding, and a real data example study analyzed their performance when detecting human-generated careless responding. In both studies, RPR turned out to be a significantly better careless response indicator than PR. The results also revealed that using 25 resamples for the RPR computation is sufficient to obtain the expected gain in detection accuracy over the conventional PR. We therefore recommend using RPR instead of the conventional PR when screening questionnaire data for careless responding.Supplementary InformationThe online version contains supplementary material available at 10.3758/s13428-024-02506-0.

A few promising solutions for thermal imaging Unexploded Ordnance (UXO) detection were proposed after the start of the military conflict in Ukraine in 2014. At the same time, most of the landmine clearance protocols and practices are based on old, 20th-century technologies. More than 60 countries worldwide are still affected by explosive remnants of war, and new areas are contaminated almost every day. To date, no automated solutions exist for surface UXO detection by using thermal imaging. One of the reasons is also that there are no publicly available data. This research bridges both gaps by introducing an automated UXO detection method, and by publishing thermal imaging data. During a project in Bosnia and Herzegovina in 2019, an organisation, Norwegian People’s Aid, collected data about unexploded ordnances and made them available for this research. Thermal images with a size of 720 × 480 pixels were collected by using an Unmanned Aerial Vehicle at a height of 3 m, thus achieving a very small Ground Sampling Distance (GSD). One of the goals of our research was also to verify if the explosive war remnants’ detection accuracy could be improved further by using Convolutional Neural Networks (CNN). We have experimented with various existing modern CNN architectures for object identification, whereat the YOLOv5 model was selected as the most promising for retraining. An eleven-class object detection problem was solved primarily in this study. Our data were annotated semi-manually. Five versions of the YOLOv5 model, fine-tuned with a grid-search, were trained end-to-end on randomly selected 640 training and 80 validation images from our dataset. The trained models were verified on the remaining 88 images from our dataset. Objects from each of the eleven classes were identified with more than 90% probability, whereat the Mean Average Precision (mAP) at a 0.5 threshold was 99.5%, and the mAP at thresholds from 0.5 to 0.95 was 87.0% up to 90.5%, depending on the model’s complexity. Our results are comparable to the state-of-the-art, whereat these object detection methods have been tested on other similar small datasets with thermal images. Our study is one of the few in the field of Automated UXO detection by using thermal images, and the first that solves the problem of identifying more than one class of objects. On the other hand, publicly available thermal images with a relatively small GSD will enable and stimulate the development of new detection algorithms, where our method and results can serve as a baseline. Only really accurate automatic UXO detection solutions will help to solve one of the least explored worldwide life-threatening problems.

Withcontinuous advancements in remote sensing technology, object detection in remote sensing images has emerged as a critical research direction in maritime surveillance, port management, and national defense. Among these applications, ship detection is a key task. Due to the fact that ships in images typically exhibit arbitrary rotations, multi-scale distributions, and complex backgrounds, conventional detection methods based on horizontal or rotated bounding boxes often fail to adequately capture the fine-grained information of the targets, thereby compromising detection accuracy. This paper proposes the Dense Representative Points-Guided Rotated-Ship Detection (DenseRRSD) method. The proposed approach represents ship objects using dense representative points (RepPoints) to effectively capture local semantic information, thereby avoiding the background noise issues associated with traditional rectangular bounding box representations. To further enhance detection accuracy, an edge region sampling strategy is devised to uniformly sample RepPoints from critical ship parts, and a Weighted Residual Feature Pyramid Network (WRFPN) is introduced to efficiently fuse the multi-scale features through residual connections and learnable weights. In addition, a Weighted Chamfer Loss (WCL) combined with a staged localization loss strategy is employed to progressively refine localization from coarse to fine stages. Experimental results on both the HRSC2016 dataset and the newly constructed DOTA-SHIP dataset demonstrate that DenseRRSD achieves state-of-the-art detection accuracy, with mean Average Precision (mAP) scores of 91.2% and 83.2%, respectively, significantly outperforming existing methods. These results verify the effectiveness and robustness of the proposed approach in rotated-ship detection under diverse conditions.

Synthetic Aperture Radar (SAR) is a high-resolution radar that operates all day and in all weather conditions, so it has been widely used in various fields of science and technology. Ship detection using SAR images has become important research in marine applications. However, in complex scenes, ships are easily submerged in sea clutter, which cause missed detection. Due to this, strong sidelobes in SAR images generate false targets and reduce the detection accuracy. To solve these problems, a ship detection method based on eigensubspace projection (ESSP) in SAR images is proposed. First, the image is reconstructed into a new observation matrix along the azimuth direction, and the phase space matrix of the reconstructed image is constructed by using the Hankel characteristic, which preliminarily determines the approximate position of the ship. Then, the autocorrelation matrix of the reconstructed image is decomposed by eigenvalue decomposition (EVD). According to the size of the eigenvalues, the corresponding eigenvectors are divided into two parts, which constitute the basis of the ship subspace and the clutter subspace. Finally, the original image is projected into the ship subspace, and the ship data in the ship subspace are rearranged to obtain the precise position of the ship with significantly suppressed clutter. To verify the effectiveness of the proposed method, the ESSP method is compared with other detection methods on four images at different sea conditions. The results show that the detection accuracy of the ESSP method reaches 89.87% in complex scenes. Compared with other methods, the proposed method can extract ship targets from sea clutter more accurately and reduce the number of false alarms, which has obvious advantages in terms of detection accuracy and timeliness.

When the general preceding vehicle detection is carried for monocular vision, the accuracy of the detection is affected by the dynamic background, illumination and occlusion. This paper proposed a preceding vehicle detection method fusing monocular and binocular vision method. Firstly, the potential area of the preceding vehicle was established by using SSD (Single Shot Multibox Detection) algorithm, then, the binocular vision-based vehicle detection method for the potential area was used, its U-V disparity was calculated, and the accurate preceding vehicle position by the vehicle depth information in the image was obtained; finally, the missed detection and false detections in the monocular vision detector were removed with the U-V disparity detections obtained by binocular vision detector. And the final results combined with the type and position information were outputted. Thereby the accuracy of the preceding vehicle detection was improved. The test result showed that on the condition of KITTI date set the visual fusion method can effectively improve the accuracy of vehicle detection. And compared with SSD algorithm in monocular, the Detection Rate was increased by 1.46%, the Recall Rate was increased by 2.83%, the Missed Rate was reduced by 2.83% and the False Rate was reduced by 1.10% than the monocular SSD algorithm.