Single Shot Research Articles

Proposing an Efficient Deep Learning Algorithm Based on Segment Anything Model for Detection and Tracking of Vehicles through Uncalibrated Urban Traffic Surveillance Cameras

In this study, we present a novel approach leveraging the segment anything model (SAM) for the efficient detection and tracking of vehicles in urban traffic surveillance systems by utilizing uncalibrated low-resolution highway cameras. This research addresses the critical need for accurate vehicle monitoring in intelligent transportation systems (ITS) and smart city infrastructure. Traditional methods often struggle with the variability and complexity of urban environments, leading to suboptimal performance. Our approach harnesses the power of SAM, an advanced deep learning-based image segmentation algorithm, to significantly enhance the detection accuracy and tracking robustness. Through extensive testing and evaluation on two datasets of 511 highway cameras from Quebec, Canada and NVIDIA AI City Challenge Track 1, our algorithm achieved exceptional performance metrics including a precision of 89.68%, a recall of 97.87%, and an F1-score of 93.60%. These results represent a substantial improvement over existing state-of-the-art methods such as the YOLO version 8 algorithm, single shot detector (SSD), region-based convolutional neural network (RCNN). This advancement not only highlights the potential of SAM in real-time vehicle detection and tracking applications, but also underscores its capability to handle the diverse and dynamic conditions of urban traffic scenes. The implementation of this technology can lead to improved traffic management, reduced congestion, and enhanced urban mobility, making it a valuable tool for modern smart cities. The outcomes of this research pave the way for future advancements in remote sensing and photogrammetry, particularly in the realm of urban traffic surveillance and management.

Extended X-ray absorption spectroscopy using an ultrashort pulse laboratory-scale laser-plasma accelerator

Laser-driven compact particle accelerators can provide ultrashort pulses of broadband X-rays, well suited for undertaking X-ray absorption spectroscopy measurements on a femtosecond timescale. Here the Extended X-ray Absorption Fine Structure (EXAFS) features of the K-edge of a copper sample have been observed over a 250 eV window in a single shot using a laser wakefield accelerator, providing information on both the electronic and ionic structure simultaneously. This capability will allow the investigation of ultrafast processes, and in particular, probing high-energy-density matter and physics far-from-equilibrium where the sample refresh rate is slow and shot number is limited. For example, states that replicate the tremendous pressures and temperatures of planetary bodies or the conditions inside nuclear fusion reactions. Using high-power lasers to pump these samples also has the advantage of being inherently synchronised to the laser-driven X-ray probe. A perspective on the additional strengths of a laboratory-based ultrafast X-ray absorption source is presented.

Effects of the stretching program in male volleyball players with posterior shoulder tightness

Effects of the stretching program in male volleyball players with posterior shoulder tightness

Single-shot dual-wavelength telecentric in-line-and-off-axis hybrid digital holography with non-prior reconstruction.

Dual-wavelength in-line-and-off-axis hybrid digital holography (iohDH) can achieve high-resolution holographic dynamic imaging. However, it requires the prediction of the diffraction distance and the complex amplitude of the reference beam, which is time consuming and results in complications and accuracy limitations. While telecentric imaging technique can obtain nondiffractive images without predicting the diffraction distance, it also can even eliminate spherical aberration and astigmatic aberration. Therefore, a dual-wavelength telecentric iohDH is proposed to realize non-prior high-resolution reconstruction in a single shot. Employing the dual-wavelength telecentric iohDH, our approach acquires the focused in-line-and-off-axis hologram using a color camera in a single shot. In this case, we perform wavelength conversion on the phase and low-frequency information about the off-axis hologram as constraints for in-line iteration. Then, the in-line amplitude constraints are performed in the spatial and frequency domains until the algorithm converges. Compared to the state-of-the-art dual-wavelength iohDH, our approach can streamline the reconstructed processes without demanding a priori information of the diffraction distance and the complex amplitude of the reference beam. More importantly, our approach enables higher quality and efficient reconstruction under the telecentric system. We verified our approach using simulations and experiments, and the results indicate that our approach can allow the amplitude and phase reconstruction with high resolution in a single shot.

EDGE AI BASED OBJECT DETECTION SYSTEM USING TFLITE

Edge computing has gained prominence in recent years due to its ability to process data closer to the source, reducing latency and bandwidth requirements. In this paper, we propose an Edge AI Based Object Detection System using TensorFlow Lite (TFLite), designed to perform real-time object detection on resource-constrained edge devices. The system leverages the efficiency and portability of TFLite, a lightweight framework for deploying machine learning models on edge devices, to enable efficient inference without relying on cloud connectivity. Our proposed system integrates state-of-the-art object detection models, such as SSD (Single Shot Multibox Detector) and YOLO (You Only Look Once), into the TFLite runtime environment. Through optimization techniques such as model quantization, pruning, and architecture modifications, we tailor these models to meet the computational and memory constraints of edge devices while maintaining high detection accuracy. Furthermore, we explore hardware acceleration options, including GPU and DSP (Digital Signal Processor), to further enhance inference speed and energy efficiency. We evaluate the performance of the Edge AI Based Object Detection System on various edge devices, including smartphones, IoT (Internet of Things) devices, and embedded systems. Real-world deployment scenarios are considered, encompassing applications such as smart surveillance, industrial automation, and autonomous vehicles. The results demonstrate the system's ability to achieve real-time object detection with low latency and minimal resource consumption, making it well-suited for edge computing environments where real-time responsiveness and privacy are paramount concerns. Keywords: object Detection, Machine Learning, Tensor Flow lite, deep learning.

Highly sensitive volumetric single-molecule imaging.

Volumetric subcellular imaging has long been essential for studying structures and dynamics in cells and tissues. However, due to limited imaging speed and depth of field, it has been challenging to perform live-cell imaging and single-particle tracking. Here we report a 2.5D fluorescence microscopy combined with highly inclined illumination beams, which significantly reduce not only the image acquisition time but also the out-of-focus background by ∼2-fold compared to epi-illumination. Instead of sequential z-scanning, our method projects a certain depth of volumetric information onto a 2D plane in a single shot using multi-layered glass for incoherent wavefront splitting, enabling high photon detection efficiency. We apply our method to multi-color immunofluorescence imaging and volumetric super-resolution imaging, covering ∼3-4 µm thickness of samples without z-scanning. Additionally, we demonstrate that our approach can substantially extend the observation time of single-particle tracking in living cells.

Advanced home security: detecting unusual movements using the single shot detector technique

As area surveillance technology, the camera is still suboptimal because it cannot detect suspicious human movement and there is no real-time security alert. Although motion detection is implemented, it is only activated when a person passes the PIR sensor, triggering the camera to capture the object. Due to its lengthy process, it is less effective. This study aims to develop a home surveillance system that uses object detection technology to detect unusual human movements. The system is also equipped with real-time early warning through a Telegram Messenger application. The system is then tested using various parameters that may impact the precision of detection results, including object poses, camera height, and camera distance. The system can detect objects that make unusual movements in 69 images or 57.5% of the tests, based on the analysis of 120 test data. Through the integration of object detection technology and real-time Telegram-based alerts, this home surveillance system significantly demonstrates the capability to accurately identify suspicious human motions thereby enhancing area surveillance effectiveness and adaptability to various environmental conditions.

Faster R–CNN, RetinaNet and Single Shot Detector in different ResNet backbones for marine vessel detection using cross polarization C-band SAR imagery

Faster R–CNN, RetinaNet and Single Shot Detector in different ResNet backbones for marine vessel detection using cross polarization C-band SAR imagery

MetaHDR: single shot high-dynamic range imaging and sensing using a multifunctional metasurface.

We present MetaHDR, which is a single-shot high-dynamic range (HDR) imaging and sensing system using a multifunctional metasurface. The metasurface is capable of splitting an incident beam into multiple focusing beams with different amounts of power, simultaneously forming multiple low dynamic range (LDR) images with distinct irradiance on a photosensor. Then, the LDR images are jointly processed using a gradient-based HDR fusion algorithm, which is shown to be effective in attenuating the residual light artifacts incurred by the metasurface and the lens flare. MetaHDR achieves single-shot HDR photography and videography that increases the dynamic range by at least 50 dB compared to the original dynamic range of the photosensor. It can also perform single-shot HDR sensing, including reflectance calibration and surface curvature estimation of reflective materials. MetaHDR's demonstrated functionalities could be broadly applied in surveillance and security, microscopic imaging, advanced manufacturing, etc.

Normal ovarian sizes on MRI in pediatric patients: a preliminary study.

Ovarian enlargement is one of several findings of pathology, including ovarian torsion. With increasing use of MRI for acute abdominal pain in children, data for normal ovary size and appearance are needed. To provide preliminary data on normal sizes of ovaries on MRI in pediatric patients. This retrospective IRB-approved study included girls (5 to 17years of age) with MRI examinations performed for indications not related to the ovaries from 2018 to 2022. For each MRI, coronal T2-weighted single shot fast spin echo and axial T2-weighted fat-saturated images were independently reviewed by three pediatric radiologists who recorded ovary visualization and ovarian linear measurements (3 planes). Ovarian volumes were calculated from linear measurements. Agreement among observers was calculated using kappa statistics and intraclass correlation coefficients. A total of 181 MRIs were reviewed. The left ovary was visualized in 166-176 (92-97%) cases (R1-R3) and the right ovary was visualized in 165-174 (91-96%) cases with excellent agreement among reviewers (left: K = 0.89 [0.84-0.94], right: K = 0.85 [0.79-0.91]). Interrater class coefficient (ICC) for largest single dimension of the ovary was left: 0.83 (CI 0.79-0.87) and right: 0.85 (CI 0.81-0.89). There were significant moderate to strong correlations between ovarian volume and age (left: 0.67 [0.58-0.75], right: 0.66 [0.57-0.74]). The ovaries can be adequately visualized and measured on MRI with excellent inter-reader agreement. This study serves as the foundation for developing normative values for ovarian volumes by age on MRI.

Comparative Evaluation of Convolutional Neural Network Object Detection Algorithms for Vehicle Detection.

The domain of object detection was revolutionized with the introduction of Convolutional Neural Networks (CNNs) in the field of computer vision. This article aims to explore the architectural intricacies, methodological differences, and performance characteristics of three CNN-based object detection algorithms, namely Faster Region-Based Convolutional Network (R-CNN), You Only Look Once v3 (YOLO), and Single Shot MultiBox Detector (SSD) in the specific domain application of vehicle detection. The findings of this study indicate that the SSD object detection algorithm outperforms the other approaches in terms of both performance and processing speeds. The Faster R-CNN approach detected objects in images with an average speed of 5.1 s, achieving a mean average precision of 0.76 and an average loss of 0.467. YOLO v3 detected objects with an average speed of 1.16 s, achieving a mean average precision of 0.81 with an average loss of 1.183. In contrast, SSD detected objects with an average speed of 0.5 s, exhibiting the highest mean average precision of 0.92 despite having a higher average loss of 2.625. Notably, all three object detectors achieved an accuracy exceeding 99%.

Surface defect detection of strip steel based on GT-CutMix augmentation algorithm and improved DSSD model

Abstract Nowadays, defect detection technology based on deep learning continuously increases the surface quality requirements of hot-rolled strip steel. However, due to limitations in industrial production, defect datasets often suffer from insufficient training samples and imbalanced categories. This paper proposes effective solutions, namely the GT-CutMix offline data augmentation algorithm and lightweight small sample defect detection models. The GT-CutMix augmentation algorithm significantly improves defect utilization by accurately sampling defect locations and integrating them into the original data set. We design the S-DSSD defect detection model by constructing a lightweight SI-MobileNet to replace the ResNet101 backbone of the Deconvolutional Single Shot Detector (DSSD) network. This can reduce the resource parameters and consumption. At the same time, it can speed up training and inference. To further improve the detection accuracy, we integrate the Pyramid Split Attention (PSA) attention mechanism into the prediction module of DSSD and construct the SA-DSSD model. Under the GT-CutMix augmentation algorithm, the mAP of S-DSSD and SA-DSSD models on X-SDD dataset are 76.83% and 78.63%, respectively. Meanwhile, the corresponding detection speeds are 45 FPS and 40 FPS, respectively. In addition, on the NEU-DET cross-dataset experiment, the mAP of the SA-DSSD model reaches 74.88%. Our methods are highly effective and generalized for small sample defect detection, which can provide selective solutions for specific needs such as high speed and precision in different industrial production scenarios.

Effects of Continuous versus Single Dose Spinal Anesthesia in Octogenarians Undergoing Hip Surgery: Randomized Control Trial

Abstract Background Continuous spinal anesthesia (CSA) is an anesthetic technique that offers several clinical advantages for anesthesia and analgesia in elderly patients. The level of sensory blockade can be titrated to the desired dermatomal level with great precision with intrathecal (IT) catheters, allowing better control of the hemodynamic consequences of sympathetic blockade associated with spinal anesthesia compared to epidural or single shot spinal techniques. Octogenarians are expected to suffer more from hemodynamic instability with spinal anesthesia. Objective The primary outcome is to compare the incidence of hypotension (defined as decrease in mean arterial blood pressure > 20% from the base line) in continuous spinal anesthesia CSA versus single dose spinal anesthesia in octogenarians undergoing hip surgery. The secondary outcome is to determine the total use of vasopressor (Ephedrine) and the incidence of spinal complications as nausea, vomiting and post Dural puncture headache. Methods This is a randomized controlled clinical trial done at Ain-shams University Hospitals, Cairo, Egypt within a period of 6 months from approval of medical ethics committee. Twenty patients in CSA group received increments of (0.5 ml) of plain bupivacaine 0.5% until T10 level blockade is achieved. Twenty patients in SDA group received single shot of (2.5ml) of bupivacaine 0.5%. Results The main finding of this study is that while MAP was significantly lower between 5-35 minutes (<0.001), it was significantly higher between 40-75 minutes in SDA group than CSA group (0.05).Total bupivacaine dose was significantly higher in SDA (12.5±0.8) group than CSA group (7.6±1.3) (p < 0.001). The total ephedrine dose needed was significantly higher in the SDA group (19.5 ±11.3) than in CSA group (4.5±1.7) (p.0.006). Conclusion The main finding of this study is that for octogenarians undergoing hip surgery, while MAP was significantly lower between 5-35 minutes, it was significantly higher between 40-75 minutes in single dose spinal anesthesia group than continuous spinal anesthesia group. Episodes of bradycardia were similar in both groups. The bupivacaine dose as well as total ephedrine dose was significantly higher in SDA group than CSA group. Groups were similar in the incidence of postoperative complications related to the neuraxial blockade. The impact of these changes on the overall cardiovascular status and outcome in octogenarians undergoing hip surgery could not be determined from our study design.

Overexpressing the PRSS1 Protein Specifically in the Pancreatic Islets by Nano-Celery Provided Protection against Streptozotocin-Induced Diabetes Mellitus in Male Rat

The goal of this study was to find out how giving whole barley grain to rats that had been given streptozotocin (STZ) affected lipid peroxidation (LPO), the activities of antioxidant enzymes in erythrocytes, and the production of insulin genes in the pancreas. A single shot of STZ (60 mg/kg, i.p.) caused diabetes in the experiment. The oxidative stress was measured by the amount of LPO in the tissue, the amount of reduced glutathione (GSH), and the activities of SOD, CAT, GPx, and GR enzymes in erythrocytes. The most important things that were seen in diabetic control rats were higher blood sugar and LPO levels, lower GSH levels, and lower enzyme functions. When diabetic rats (group G2) were given barley seed whole grain by mouth for 30 days, their LPO level dropped significantly compared to rats that were given STZ (group G3). Furthermore, diabetic rats (group G4) that were fed barley had higher levels of both enzyme- and non-enzymatic antioxidants, as well as higher levels of insulin and regeneration (PRSS1) genes, compared to diabetic normal rats (group G2). The results make it clear that oxidative stress plays a part in causing diabetes and suggest that adding barley to an animal's diet might help protect them.

Comparison of Analgesic Efficacy between Bupivacaine with Dexamethasone versus Bupivacaine in Caudal Block for Pediatric Patients Undergoing Lower Abdominal Surgeries

Abstract Background Caudal analgesia is one of the most popular regional blocks in paediatric patients undergoing lower abdominal surgeries but with the drawback of short duration of action after single shot local anaesthetic injection. We evaluated whether caudal dexamethasone as an adjuvant to the Bupivacaine improves analgesic efficacy after paediatric lower abdominal surgeries. Aim of the Study The current study is conducted to evaluate the analgesic effect of dexamethasone when given caudally as an adjuvant to bupivacaine for children undergoing lower abdominal surgeries eg: open inguinal hernia repair, hypospidius, orchidopexy and circumcision surgeries. Methods Totally 60 patients of 1–3 years age group, American Society of Anaesthesiologists physical status I and II undergoing elective lower abdominal surgeries were randomly allocated to two groups in double-blind manner. Group B (the control group) received 1 ml/kg of 0.25% bupivacaine caudally for lower abdominal surgeries and 0.5 ml/kg for anal and penile surgeries and Group BD received 1 ml/kg of 0.25% bupivacaine for lower abdominal surgeries and 0.5 ml/kg for anal and penile surgeries, in which 0.1 mg/kg dexamethasone was added for caudal analgesia. Post operative pain by FLACC scale (faces, legs, activity, cry and consolability tool score), rescue analgesic requirement and adverse effects were noted for 24 h. Results Results were statistically analysed using KRUSKAL-WALLIS TEST. Pain scores measured at 4,8 and 12h post-operative, were lower in Group BD as compared to Group B Mean duration of analgesia in Group BD 1026±139,8 min and in Group B was 465,6± 79,2 min with P = 0.001. Rescue analgesic requirement was more in Group B as compared to Group BD. Adverse effects after surgery were comparable between the two groups. Conclusion Caudal dexamethasone added to bupivacaine is a good alternative to prolong post-operative analgesia with less pain score compared to caudal bupivacaine alone.

Simulation of femtosecond laser-induced periodic surface structures on fused silica by considering intrapulse and interpulse feedback

The formation of laser-induced periodic surface structures (LIPSSs) on fused silica upon irradiation with plane wave, double pulse, spot processing, and scanning processing (pulse duration tp = 35 fs, center wavelength λ = 800 nm, low repetition rate ≈1 kHz) is studied theoretically with an improved three-dimensional finite-difference time-domain plasma model. The model covers both intrapulse feedback under single shot and interpulse feedback under multi-shots, thus enabling better prediction of transient responses during laser–material interaction and the evolution of the ablated morphology and accumulated defects’ density with more shots. In simulations of a single plane wave, a double pulse can modulate LIPSS periodicity. In simulations of spot processing with Gaussian beam, an increase in the number of shots results in a noticeable ablation pattern where high-spatial-frequency LIPSS surrounds low-spatial-frequency LIPSS at a fluence of 2.8 J/cm2. Moreover, simulations of scanning processing with Gaussian beam showcase the broad applicability of this model, revealing that the orientation of the LIPSS depends on the polarization direction rather than the scanning path. This new model provides a powerful tool to simulate the formation of LIPSS on silica, particularly when temporally modulated laser is involved or predicting the evolution of morphology dependent on the number of shots.

Combined General Anaesthesia with Retrolaminar Block for Breast Cancer Surgery in Pompe’s Disease

Pompe’s disease is a rare metabolic disease that results in progressive muscle weakness which culminates in respiratory failure in the late onset type. Patients with Pompe’s disease are at high risk of cardiac and respiratory complications under general anaesthesia owing to their premorbid cardiac and respiratory impairments, as well as the respiratory depressant effects of anaesthetic and analgesic agents. We present a high-risk case of a patient with late onset Pompe’s disease complicated by severe restrictive lung disease scheduled for breast cancer surgery under general anaesthesia with a single shot retrolaminar nerve block for analgesia.

The effect of ultrasound-guided bilateral single shot pecto-intercostal plane block on recovery after on-pump coronary bypass graft surgery, randomized controlled trial

Background: Fast-track anaesthesia and ultra-fast track anaesthesia are techniques used in cardiac anaesthesia aiming for early extubation in the intensive care unit. This study assessed the efficacy and safety of pecto-intercostal plane blocks (PIFB) guided by ultrasonography following on-pump coronary artery bypass graft (CABG) surgery. Methods: 40 Patients of both genders aged > 40 years scheduled for on-pump CABG surgery were randomly distributed either; Group I (Control group): bilateral PIFB with normal saline (1 ml), Group II (PIFB group): bilateral PIFB with local anaesthetics. The extubation time was the primary outcome while the secondary outcome were postoperative pain scores, intraoperative and postoperative opioid consumption, the ICU stay duration and the incidence of postoperative complications. Results: There were statistically significant reductions in the extubation time, ICU length stay, intraoperative fentanyl, and postoperative morphine consumption in the PIFB group compared with the control group (P value ˂ 0.05). Pain scores were lower in PIFB group at 2, 4, 12, 16, 20, and 24 h after extubation than Control group. Compared to the control group, the PIFB group experienced a significantly longer time to first morphine requirement as rescue analgesic analgesia. Between the two groups, there were insignificant differences in the frequency of complications, diaphragmatic dysfunction, postoperative reintubation, and 30-day mortality. The intraoperative PIFB in patients scheduled for on-pump CABG surgery shortened the extubation time and the ICU length, decreased intraoperative fentanyl and postoperative morphine consumption and postoperative pain scores, prolonged 1st time of rescue analgesia. Trial registration: ClinicalTrials.gov ID: NCT04343105 at the date of May 2020.

Efficacy of quadratus lumborum block as a relatively new analgesic technique in patients undergoing open inguinal hernia surgical repair

Study objective To determine the analgesic efficacy of ultrasonographic guided transmuscular graduatus lumborum block (QLB) in patients undergoing open inguinal hernia surgery. Design Prospective randomized double-blinded study. Methodology and interventions This prospective randomized double-blinded study was carried out at Sohag University hospital, after local research ethical committee approval and obtaining informed written consent from all patients participating in the study or their guardians. A total of 50 patients (ASA grade I to II) were posted for open inguinal hernia surgery. All patients underwent the operation under general anesthesia. Then patients were randomly divided into two equal groups: group A (QLB group, N=25): were underwent a transmuscular QLB approach, after wound dressing with a single shot of a total volume of 20 ml of mixture (10 ml bupivacaine 0.5% and10 ml normal saline). Group B (control group N=2): patients received only general anesthesia with conventional intravenous analgesia. Measurements Pain intensity between groups was compared using the Visual Analog Score (VAS), furthermore, analgesic consumption (morphine and ketorolac) and additional rescue analgesic requirements were also calculated. Results Postoperative VAS scores at rest and during movement were significantly lower in group (QLB) A than the control group B at 1, 5, 7, 8, 9, 10, and 12 h, the time of first rescue analgesia was significantly delayed in QLB group (15.8±3.94 h) than the control group (8.5±4.29 h). Number of patients required morphine was significantly different between both groups. Number of patients required ketorolac was significantly lower in QLB group than in the control group. Total morphine and ketorolac requirements were significantly lower in group A (2.5±0.71 mg, 75±25.1), respectively than those consumed by the control group B (4.7±0.49, 126±23.24), respectively. Conclusions QLB significantly improves the analgesic quality in patients undergoing inguinal hernia repair compared to the standard intravenous analgesia regimen.

A Cross-Sectional Study of Labor Analgesia Practices Across India

Introduction: Labour analgesia practices have evolved significantly over the past years, with most of the current practices being evidence-based. Labour analgesia is considered a standard of care in resource-rich countries. However, in resource-limited countries such as India, there is a lack of awareness, and round the clock availability of labour analgesia services across the country. This raises significant challenges in establishing successful labour analgesia programs. Methods: This survey was conducted using multi-question Google Form@, so as to improve our understanding of labour analgesia practices in India. Our primary objective was to study the prevalence of labour analgesia practices amongst anaesthesiologists across India. Our secondary objectives included the work profile of anaesthesiologists providing labour analgesia, common techniques of labour analgesia practised, drugs used and common complications as well as side-effects encountered. Results: The results of our survey showed that 72.9% of the respondents practised labour analgesia in one form or the other. Practitioners in non-government facilities such as private hospitals, private medical colleges, and nursing homes accounted for more than 60% of the total labour analgesia delivered. Government medical colleges fared the best among practitioners at government-owned facilities. Approximately 85% of those polled agreed that the most common way of pain relief in a labouring patient was regional analgesia. The most prevalent was labour epidural (59.4%), followed by a single shot spinal analgesic, while 29% of anaesthesiologists used systemic analgesia. Conclusion: The impediments to delivering widespread labour analgesia services across India were poor infrastructure and high costs.