Target Detection Research Articles

A Dynamic False Alarm Rate Control Method for Small Target Detection in Non-Stationary Sea Clutter

Sea surface non-stationarity poses significant challenges to sea-surface small target detection, particularly in maintaining a stable false alarm rate (FAR). In dynamic maritime scenarios with non-stationary characteristics, the non-stationarity of sea clutter can easily cause significant changes in the clutter feature space, leading to a notable deviation between the preset FAR and the measured FAR. By analyzing the temporal and spatial variations in sea clutter, we model the relationship between the preset FAR and the measured FAR as a two-parameter linear function. To address the impact of sea surface non-stationarity on FAR, the model parameters are estimated in real time within the environment and used to guide the dynamic adjustment of the decision region. We applied the proposed method to both convex hull and support vector machine (SVM) detectors and conducted experiments using measured X-band sea-detecting datasets. Experiments demonstrate that the proposed method effectively reduces the deviation between the measured mean FAR and the preset FAR. When the preset FAR is 10−2, the proposed method achieves an average FAR of 1.067 × 10−2 with the convex hull detector and 1.043 × 10−2 with the SVM detector.

Joint LPI waveform and passive beamforming design for FDA-MIMO-DFRC systems

Dual-functional Radar-Communication (DFRC) systems have been recognized as one of the most promising technologies in the field of wireless communications. Nevertheless, the low probability of intercept (LPI) performance in the DFRC systems cannot be overlooked. Based on the frequency diverse array multiple-input–multiple output (FDA-MIMO) radar, a DFRC system is proposed to enhance target detection in clutter environment and achieve desirable LPI against an underlying hostile interceptor. The issue can be cast into an optimization problem that maximizes the radar signal-to-interference-plus-noise ratio (SINR) while satisfying the communication quality-of-service (QoS) requirement of each user under one of three metrics, the required LPI performance and the constant-modulus waveform constraint. To solve this challenging problem, we reformulate it into an equivalent but more tractable form by resorting to an auxiliary variable. Subsequently, we employ the alternative direction method of multipliers (ADMM) and majorization-minimization (MM) algorithms to solve the resultant problem. Simulation results validate that the proposed LPI FDA-MIMO-DFRC scheme exhibits superior sensing performance over the conventional scheme with MIMO.

Chunk Duration Limits the Learning of Multiword Chunks: Behavioral and Electroencephalogram Evidence from Statistical Learning.

Language comprehension involves the grouping of words into larger multiword chunks. This is required to recode information into sparser representations to mitigate memory limitations and counteract forgetting. It has been suggested that electrophysiological processing time windows constrain the formation of these units. Specifically, the period of rhythmic neural activity (i.e., slow-frequency neural oscillations) may set an upper limit of 2-3 sec. Here, we assess whether learning of new multiword chunks is also affected by this neural limit. We applied an auditory statistical learning paradigm of an artificial language while manipulating the duration of to-be-learnt chunks. Participants listened to isochronous sequences of disyllabic pseudowords from which they could learn hidden three-word chunks based on transitional probabilities. We presented chunks of 1.95, 2.55, and 3.15 sec that were created by varying the pause interval between pseudowords. In a first behavioral experiment, we tested learning using an implicit target detection task. We found better learning for chunks of 2.55 sec as compared to longer durations in line with an upper limit of the proposed time constraint. In a second experiment, we recorded participants' electroencephalogram during the exposure phase to use frequency tagging as a neural index of statistical learning. Extending the behavioral findings, results show a significant decline in neural tracking for chunks exceeding 3 sec as compared to both shorter durations. Overall, we suggest that language learning is constrained by endogenous time constraints, possibly reflecting electrophysiological processing windows.

Fiddler crabs (Afruca tangeri) detect second-order motion in both intensity and polarization

Motion vision is vital for a wide range of animal behaviors. Fiddler crabs, for example, rely heavily on motion to detect the movement of avian predators. They are known to detect first-order motion using both intensity (defined by spatiotemporal correlations in luminance) and polarization information (defined separately as spatiotemporal correlations in the degree and/or angle of polarization). However, little is known about their ability to detect second-order motion, another important form of motion information; defined separately by spatiotemporal correlations in higher-order image properties. In this work we used behavioral experiments to test how fiddler crabs (Afruca tangeri) responded to both second-order intensity and polarization stimuli. Fiddler crabs responded to a number of different intensity based second-order stimuli. Furthermore, the crabs also responded to second-order polarization stimuli, a behaviorally relevant stimulus applicable to an unpolarized flying bird when viewed against a polarized sky. The detection of second-order motion in polarization is, to the best of our knowledge, the first demonstration of this ability in any animal. This discovery therefore opens a new dimension in our understanding of how animals use polarization vision for target detection and the broader importance of second-order motion detection for animal behavior.

Coastline target detection based on UAV hyperspectral remote sensing images

Timely and accurate monitoring of typical coastal targets using remote sensing technology is crucial for maintaining marine ecological stability. Hyperspectral target detection technology proves to be an effective tool in extracting various typical materials along the coastline. Traditional target detection methods using spectral domain information can effectively retain the intrinsic properties of the material. However, it is difficult to effectively recognize targets in homogeneous regions by using only spectral domain information, which may lead to insufficient utilization of spatial information. In this study, a detector based on signal-to-noise ratio fusion constrained energy minimization with low-rank sparse decomposition (SFLRSD) is proposed. This detector improves the separability of background and target by obtaining spatial domain information from hyperspectral images and fusing spectral domain information. First, total variation regularization and fractional Fourier transform are applied to process spatial and spectral domain information, respectively. The constrained energy minimization (CEM) detector is used to improve the separability between the target and background of the processed data. Then, the background and anomalies are represented as low-rank and sparse components, respectively, using low-rank sparse matrix factorization. This transforms the model solution into a covariance matrix problem, which is then solved using marginal distance difference (MDD) to isolate anomalous parts. Subsequently, the anomaly parts are fused with CEM detector results, weighted by their respective signal-to-noise ratios. This detection model leverages unified hyperspectral image features, enhancing spectral discreteness of anomalous targets and backgrounds. Finally, experiments on custom created hyperspectral dataset show that the proposed method outperforms other baseline methods in terms of visualization and quantitative performance. In this paper, we not only propose a new hyperspectral target detection method, but we also collect three typical marine litter of different materials by means of airborne hyperspectral remote sensing and construct four hyperspectral datasets in a real environment. All the simulation experiments in this paper are conducted in these four datasets.

A-272 Evaluation of a Real-Time Multiplex Polymerase Chain Reaction Assay for Simultaneous Detection of Respiratory Pathogens in Nasopharyngeal Specimens

Abstract Background Respiratory infections present a significant challenge due to the diverse range of pathogens involved and the possibility of concurrent infections, emphasizing the importance of rapid and accurate detection for effective treatment. Advancements in molecular methods have provided cost-effective and reliable solutions for the identification of respiratory pathogens. In this study, we aimed to assess performance characteristics of the Seegene Allplex™ 2019-nCoV Assay and Seegene Novaplex™ Respiratory Panel Assays for simultaneous amplification and detection of 22 respiratory pathogens using real-time multiplex polymerase chain reaction (PCR). Methods Nucleic acid extraction was performed using the MagMAX™ Viral/Pathogen Nucleic Acid Isolation Kit (Thermo Fisher Scientific, MA) on the CyBio® FeliX liquid handler (Analytik Jena, Germany). PCR amplification and detection were performed using the Seegene Novaplex™ Respiratory Panels 1A, 2, 3, PneumoBacter Assay, and Allplex™ 2019-nCoV Assay (Seegene Inc, South Korea) on the CFX96™ System (Bio-Rad Laboratories, CA). The assays utilize Seegene MuDT™ technology that allows for the detection of multiple targets in a single channel without the need for melt curve analysis. For method validation, precision studies were performed within-run and over 4 days. The limit of detection was verified by using plasmids from Seegene containing the target sequence for each pathogen at known concentrations. Method comparison studies were carried out by extracting and analyzing a range of 41 to 79 split samples for each pathogen against the BioFire® Respiratory 2.1 Panel (bioMérieux, France), cobas® Influenza A/B & RSV Assay on the cobas® liat system (Roche Diagnostics, IN), and Lyra® SARS-CoV-2 Assay (Quidel, CA) on the CFX96™ system. Additional accuracy studies were performed by spiking negative patient samples with standards from ZeptoMetrix® (Antylia Scientific, IL) containing known concentrations of the targeted respiratory pathogens. Results Precision studies demonstrated consistent and reproducible results for all pathogens. The limit of detection was verified at 1000 copies/reaction for human parainfluenza virus 4 and human metapneumovirus, and at 100 copies/reaction for all other pathogens. Results of the spike-and-recovery studies were consistent with expected results for all targets. Patient correlation studies showed 100% agreement with expected pathogen identification for 19 pathogens, and greater than 97.9% agreement for influenza B virus, respiratory syncytial virus, human parainfluenza virus 4, and human coronavirus 229E. Conclusions The Seegene Allplex™ 2019-nCoV Assay and Novaplex™ Respiratory Panel Assays offer a rapid and reliable method for detecting respiratory pathogens in nasopharyngeal specimens. The capability of the assays to detect multiple targets in a single well enhances efficiency, cost-effectiveness, and turnaround time.

B-291 Validation of a Simple Qualitative Immunoassay for 21 Drugs of Abuse in Meconium on a Single Biochip Array

Abstract Background Drugs use during pregnancy is a major social and medical issue, which may lead to significant pre- and post-natal complications, such as preterm birth and newborn mortality. Exposed newborns may have long-term behavioral, cognitive, and developmental problems. Accurate detection of in utero drug exposure is crucial for timely medical intervention for the newborn and the mother. Meconium is the ‘gold standard' matrix for detection of drugs in newborn which reflects drug exposure during pregnancy. This study aims to develop and optimize a clinical assay for simultaneous screening of 21 drugs in meconium using a custom biochip array. Methods Custom biochip array (Randox Laboratories Ltd.) included 21 discrete test regions (DTRs) for amphetamine, methamphetamine, opioids/opiates (targeting morphine, oxymorphone, oxycodone, hydrocodone, 6-monoacetyl morphine, tramadol, buprenorphine, fentanyl, and methadone), phencyclidine (PCP), cocaine (targeting benzoylecgonine), benzodiazepines (targeting oxazepam, lorazepam, and clonazepam), zolpidem, barbiturates (targeting phenobarbital), ethyl glucuronide, methylphenidate, and marijuana metabolite (targeting Delta-9-Carboxy-Tetrahydrocannabinol [THC-COOH]). Patient samples were obtained from the residual meconium samples that had been previously used for other tests. Blank meconium samples were spiked at in-house cutoff, negative and positive assay control levels. All samples were extracted in specimen diluent using Biotage® Lysera and centrifuged. The supernatant was analyzed on a fully automated Randox Evidence+® Analyzer. A robotic arm pipetted 60 µL sample on to a biochip and then the analyzer performed a competitive chemiluminescent immunoassay. The results were generated as relative light units (RLUs). Results The sample results were determined to be “positive” or “negative” based on average RLU of cutoff controls for each analyte on an assay. The intra-assay (CV ≤ 15%) and inter-assay (CV ≤ 18%) precision was 100% agreement for positive and negative controls and there was no observed carryover for any of the analytes. The sample recovery was excellent with minimal to no matrix suppression for all analytes. Accuracy was performed by comparing spiked analyte results from Randox Evidence+® Analyzer with the expected results and all the spiked samples matched (positive or negative). When authentic patient or spiked results were compared with external laboratory test results, some discordant results were obtained. However, the discrepancies could be explained based on the different cutoffs (e.g., the Randox assay had lower cutoffs) or the known assay cross reactivities within the analytes of same class. These deviations did not affect clinical utility of the assay. Conclusions We validated a novel and simple qualitative chemiluminescent immunoassay in meconium using a custom biochip array. Unlike other routine screening/ELISA methods, which require separate assays for detection of similar drug targets, the custom biochip array offers a convenient, rapid and efficient method that utilizes only a single sample preparation for the screening of all 21 drug targets. Therefore, this technology has potential to be utilized as high-throughput screening assay. Like all qualitative assays, the limitation of this test is that all positive results will need to be assessed quantitatively for a definitive interpretation.

A-264 Validation of a Novel Real-Time PCR Assay for Identification of Mycobacterium species Isolates Recovered from Clinical Culture

Abstract Background Historically, clinical mycobacteriology laboratories used the nucleic acid hybridization-based AccuProbe assay manufactured by Hologic, Inc., to rapidly rule in or rule out Mycobacterium tuberculosis (MTB) and members of the M. avium-intracellulare complex (MAC). The clinical value of this test was in its ability to rapidly rule in/out MTB from positive broth cultures and allow the initiation of appropriate antimicrobial therapy and infection prevention practices. Recent discontinuation of this commercial assay left a gap in testing available for the rapid identification of these organisms, which allowed us to develop an in-house real-time PCR test. Methods A replacement assay was developed by Labcorp R & D based on real-time PCR amplification of extracted nucleic acids from positive culture growth. Aliquots from positive AFB VersaTREK broth cultures were heat inactivated, and nucleic acids were extracted using the MagNA Pure 24 (MP24) instrument (Roche). Real-time PCR using published primer probe sets (Rocchetti, et al 2016) was performed on the QuantStudio™ 7 (QS7) instrument (Applied Biosystems®). The assay was designed with three independent primer/probe sequence targets: one for MTB Complex (IS6110), one for MAC (ITS), and one pan-target for the Mycobacterium genus (16s rRNA). Results Procedural verification was performed using 100 residual clinical specimens previously identified using the Hologic AccuProbe® assay. Categorical concordance was 97% (97/100). The three discrepant results were identified as MAC positive by PCR; however, these were not identified as MAC on the predicate assay. Analytical sensitivity for the PCR assay was established to be 1,000 CFU/mL for each target. Analytical specificity was assessed in vitro for nine Mycobacterium species, with no cross-reactivity observed. In vitro analysis of target detection in the presence of yeast (Candida glabrata) was also performed, and we saw no inhibition. Analysis of the primer/probe sets for all targets was performed in silico using XploreDB database of microbial genomes, with confirmed 100% matches for both MAC and MTB genomes compared to hundreds of species. By comparison, the PAN-Myco primer set showed decreased performance, having three mismatches (two on forward primer and one on the probe). As this target sequence is used as an Internal Control (IC) this was not problematic for overall assay performance. The assay demonstrated excellent precision (%CV) for each target: MTB = 0.74%, MAC = 1.10%, PAN-Myco = 3.19%. Conclusions Utilizing the depth of molecular methodologies available in our laboratories, we developed a rapid method for identification of MAC and MTB from positive broth cultures, which had excellent performance compared to the predicate assay. The PCR ID LDT test is now available and allows testing to continue with no interruption in patient care.

UAV detection technology research based on deep learning

Abstract In the process of UAV target recognition, the target is small, the feature is not obvious, and the recognition accuracy is low, a UAV target detection method called YOLOv8-UD is proposed based on YOLOv8. This method replaces downsampling layers with SPD convolutions to mitigate fine-grained feature loss issues. It employs a BiFPN structure to get information which is multi-scale, enhancing representation of global semantic message and Improve awareness of small goals. As a result, to target detection, it significantly enhances the correctness and effectiveness. Additionally, to address difficulty of detecting low-resolution small targets, the network structure was modified by adding a detection head, for small target, thereby enhancing capability to detect it. Combining an improved loss function based on Inner-IoU accelerated model convergence and improved detection accuracy of samples at high IoU thresholds. We can tell by experiments that The algorithm proposed in this paper have 0.805 and 0.334 in mAP(0.5) and mAP(0.5:0.95) metrics, respectively. Compared to YOLOv8, improvements of 4.6% and 7% are achieved in mAP(0.5) and mAP (0.5:0.95) metrics. The experiments validate that the proposed way significantly enhances accuracy to UAV small target detection.

Automatic location and recognition of horse freezing brand using rotational YOLOv5 deep learning network

Individual livestock identification is of great importance to precision livestock farming. Liquid nitrogen freezing labeled horse brand is an effective way for livestock individual identification. Along with various technological developments, deep-learning-based methods have been applied in such individual marking recognition. In this research, a deep learning method for oriented horse brand location and recognition was proposed. Firstly, Rotational YOLOv5 (R-YOLOv5) was adopted to locate the oriented horse brand, then the cropped images of the brand area were trained by YOLOv5 for number recognition. In the first step, unlike classical detection methods, R-YOLOv5 introduced the orientation into the YOLO framework by integrating Circle Smooth Label (CSL). Besides, Coordinate Attention (CA) was added to raise the attention to positional information in the network. These improvements enhanced the accuracy of detecting oriented brands. In the second step, number recognition was considered as a target detection task because of the requirement of accurate recognition. Finally, the whole brand number was obtained according to the sequences of each detection box position. The experiment results showed that R-YOLOv5 outperformed other rotating target detection algorithms, and the AP (Average Accuracy) was 95.6 %, the FLOPs were 17.4 G, the detection speed was 14.3 fps. As for the results of number recognition, the mAP (mean Average Accuracy) was 95.77 %, the weight size was 13.71 MB, and the detection speed was 68.6 fps. The two-step method can accurately identify brand numbers with complex backgrounds. It also provides a stable and lightweight method for livestock individual identification.

Research on Improved Lightweight Fish Detection Algorithm Based on Yolov8n

The fish detection algorithm is of great significance for obtaining aquaculture information, optimizing prey allocation in aquaculture, and improving the growth efficiency and survival rate of fish. To address the challenges of high complexity, large computational load, and limited equipment resources in existing fish target detection processes, a lightweight fish detection and recognition method based on the Yolov8 network, called the CUIB-YOLO algorithm, is proposed. This method introduces a secondary innovative C2f-UIB module to replace the original C2f module in the Yolov8 neck network, effectively reducing the model’s parameter count. Additionally, the EMA mechanism is incorporated into the neck network to enhance the feature fusion process. Through optimized design, the Params and FLOPs of the CUIB-YOLO algorithm model are reduced to 2.5 M and 7.5 G, respectively, which represent reductions of 15.7% and 7.5% compared to the original YOLOv8n model. The mAP @ 0.5–0.95/% value reaches 76.4%, which is nearly identical to that of the Yolov8n model. Experimental results demonstrate that compared with current mainstream target detection and recognition algorithms, the proposed model reduces computational load without compromising detection accuracy, achieves model lightweighting, improves inference speed, and enhances the algorithm’s real-time performance.

EKF-based parameter estimation method for radar maneuvering target with unknown time information

Moving target detection (MTD) is a research hotspot in radar signal processing. Generally, the time information of non-cooperative moving targets entering and leaving a radar coverage area is unknown, which would lead to severe performance loss for target parameter estimation, detection, and imaging. Unlike our previous research work, this paper addresses the motion parameters estimation and refocusing problem for a radar maneuvering target with unknown entry and departure time. A computationally efficient method that utilizes extended Kalman filtering (EKF) for phase tracking is proposed to estimate the entry and departure times. The proposed method first performs range cell migration correction (RCMC) on the pulse compression echo signal. Then, the maneuvering target signal is modeled as a polynomial phase signal (PPS) and utilizes the EKF to construct a binary state-space equation for polynomial phase tracking. Finally, by comparing the phase tracking results of the noise cell and the signal cell, one can derive estimates for the entry/departure time and motion parameters. Compared with existing methods, the proposed method avoids multi-dimension searching on the parameter space, so it has a prominent advantage in computational complexity. Moreover, the core of the proposed method lies in tracking the polynomial phase, which is not constrained by the order of target motion, and has wider applicability in practice. Both simulated and public radar data are used to validate the effectiveness of the proposed method.

Investigating the radiative properties of large dust aggregate particles via the Monte Carlo ray tracing method

Understanding the radiative properties of particles is essential for interpreting and analyzing atmospheric remote sensing, target detection, combustion diagnostics, etc. At present, there is a relative lack of studies and understanding of the radiative properties of large aggregate particles. In this work, we comprehensively investigate the radiative properties of large dust aggregate particles via the developed Monte Carlo ray tracing method. Large dust aggregate models with monodisperse and polydisperse monomers are constructed, respectively. The effects of various factors on the radiative properties of large dust aggregate particles are analyzed. We find that the larger geometric standard deviation and the greater number of monomers lead to slightly larger backscattering and an increase of the overall radiative energy distribution on the receiving surface. With increasing the size parameter, the scattering phase function becomes smoother and the difference between the scattering phase function of spheres and aggregates diminishes. The absorptivity is proportional to the size parameter and inversely proportional to the number of monomers. At a size parameter of 100, the absorptivity and the peak of the radiative energy distribution of monodisperse monomer aggregates are higher than those of polydisperse monomer aggregates, and gradually converge with the increase of particle size parameter. Overall, this work helps to enhance the knowledge of the radiative properties of large aggregate particles.

Open Domain Target Detection Based on Image-text Alignment Large Model under Railway Smart Construction Site

Abstract Open domain target detection plays a crucial role in ensuring people’s life safety in Railway Smart Construction Site. This paper proposes a target detection method that is not limited by the number of labels, which is different from traditional models that are usually trained and tested on a fixed set of object categories (or a set of labels). Firstly, the pre-training GLIP model is utilized to train the collected image-text pairing data to generate grounding boxes. Secondly, the pseudo-labeled data formed by associating these boxes with the corresponding text descriptions were combined with the original image-text data to form an enhanced dataset. The final model performs inference based on the prompt and incoming image data to determine the localization information. The GLIP model effectively aligns image and text information and enhances its ability to recognize and handle problems by observing and understanding new situations.

Persistence of respiratory, enteric, and fecal indicator viruses in fecal sludge from on-site sanitation in Dakar, Senegal

ABSTRACT As wastewater-based epidemiology (WBE) broadens to include prevalent diseases with significant global health impact, existing surveillance systems concentrate on sewer-based infrastructure, which excludes the 2.7 billion people using non-sewered systems. To address this gap, our study explores the potential of fecal sludge treatment plants for WBE, emphasizing the stability of virus RNA targets within pooled fecal sludge. We screened fecal sludge from a centralized treatment facility in Dakar, Senegal for SARS-CoV-2, human norovirus, and microbial source trackers pepper mild mottle virus and tomato brown rugose fruit virus (ToBRFV). Decay kinetics of viral genomic RNA markers were examined at 4, 15, and 30 °C over 70 days. Results indicate the high persistence of viral targets in fecal sludge (T90 value of 3.3 months for exogenous SARS-CoV-2 N1 and N2 and 6.2 months for ToBRFV), with all targets detected throughout the 70-day experiment under various temperatures with limited decay (<90% reduction). This study addresses a crucial gap in understanding virus persistence in on-site sanitation systems by providing essential decay rate constants for effective target detection. Our results indicate that sampling at centralized facilities treating fecal sludge from on-site sanitation could facilitate localized pathogen surveillance in low-income settings.

Detection of walnut internal quality via improved YOLOv5 and x‐ray imaging

AbstractThis study proposes a walnut target detection algorithm based on improved YOLOv5 and x‐ray imaging to meet the demand for internal quality detection and removal in the Xinjiang walnut industry. By replacing the C3 module in the backbone layer with the C2f module and the couple‐head in the head layer with the decouple‐head, the algorithm reduces computational complexity, enhances robustness and generalizability, and retains more spatial information, thereby improving the performance of multicategory small target detection. In addition, this paper replaces the original CIOU loss function with the EIOU loss function to improve the convergence speed of the algorithm's accuracy and boundary aspect ratio. Compared with the original model, the improved model, improved YOLOv5, maintains the same average precision for normal walnuts while increasing the average precision for shriveled walnuts and empty‐shell walnuts by 8.2% and 0.4%, respectively. Compared with other mainstream models, such as VGG16, ResNet50, YOLOv5s, YOLOv7, YOLOv8s, YOLOv9s, and YOLOv10s, this model achieves the highest detection accuracy and good detection performance, with a single‐image detection time of 11.9 ms, meeting the requirements for real‐time detection. This work lays a foundation for automatic robot detection of the internal quality and removal of walnuts, showing practical application potential.Practical applicationsXinjiang stands as a prominent producer of walnuts; however, due to the decentralized nature of its cultivation and management processes, a notable prevalence of internal empty shells and shrinkage is observed, which substantially diminishes their commercial value. The integration of YOLOv5 with x‐ray imaging technology promises to enhance the precision of internal quality assessments of walnuts. The improved YOLOv5 model, as delineated in this study, exhibits the highest detection accuracy when benchmarked against a multitude of other models. It achieves a detection latency of merely 11.9 ms per image, thereby satisfying the stringent demands for real‐time detection applications. This model is designed for integration into x‐ray systems with an adjunctive sorting mechanism, which facilitates the inspection and exclusion of defective walnuts on conveyor belts.

Automated construction safety reporting system integrating deep learning-based real-time advanced detection and visual question answering

The construction sector is globally acknowledged as one of the most hazardous industries, owing to the vulnerability of its workers to accidents, injuries, and even loss of life. Effective precautionary measures are necessary and ensuring the use of personal protective equipment (PPE) by workers is crucial for protecting them from accidents. Existing deep learning-based PPE detection systems mainly use simple vision-based target detection methods for tasks such as the identification of helmets or vests, and they tend to be task-specific. However, the identification of specific PPE based on respective job types and maintaining detailed safety records, requires further innovative approaches. In this paper, we propose an innovative intelligent system that not only accurately recognizes specific PPE according to the needs of different work types but also automatically generates safety inspection reports and establishes complete safety records, thus providing critical data to support accident investigations. The proposed system integrates a target detection model, visual question answering model, and text-based analysis of the relevant regulations to realize real-time detection of PPE and automatic generation of safety inspection reports. The experimental results show that the proposed YOLOv8n-DCA network strikes a good balance between performance and computational cost—, with a mAP value of 86%. Compared to the original YOLOv8n network, the mAP value is improved by 5.1%, while the model parameters and size are significantly reduced. Further, the visual question answering model exhibited a precision is 95.9. Finally, the automatic generation of safety inspection reports was successfully realized, verifying the feasibility of the developed system. This innovative system promises a comprehensive and efficient PPE management solution for the construction industry to ensure worker safety and provide strong data support.

Moving ships detection via the trajectory feature extraction from spatiotemporal slices of infrared maritime videos

In practical application scenarios, maritime infrared videosoften contain different types of sea state scenes, weather conditions, shooting time, shooting distance, etc. In these different types of maritime videos, ship targets have great differences in size, grayscaledistribution and contrast, which brings difficulties to ship target detection.At the same time, the diversity of fluctuation, grayscale distribution and reflected light of the sea surface will bring unpredictable interference noise to ship target detection.How to accurately detect ship targets in complex and changeable maritime infrared videos is a challenging task and research focus.The key to achieving accurate ship detection is to extract robust target features that can effectively distinguish targets from all thebackground noises.In this paper, a novel infrared video ship target detection algorithm based on spatiotemporal slice target trajectory features extraction is proposed. The algorithm is very sensitive to real targets and has excellentanti-noise ability.The main innovation of the algorithm is to extract the target trajectory feature from the spatiotemporal slice of the sequence image and generate the trajectory feature map.We use the trajectory texture formed by the ship target in the spatiotemporal slice to extract the target feature, which can greatly suppress the background noise.The adaptive dilation linear model algorithm can effectively detect the target trajectory line in the spatiotemporal slice. In addition, we also make full use of the gradient of the target trajectory line to distinguish different target trajectory pixels, and propose an adaptive iterative dilation target region localization algorithm combined with gradient consistency.For object segmentation, we calculate the segmentation double-threshold using the adjacent surrounding background pixels of the target, so as to achievetarget segmentationof multiple grayscaledistribution types. Finally, in the comparison experiment, our algorithm shows superior target detection performance, especially when detecting ships from a large number of highlighted sea clutter background, the robust anti-noise ability of the algorithm can be highlighted.

UAV Vehicle Detection System Based on YOLOv8

Abstract To utilize the drone vehicle detection technology to observe the road traffic conditions in real-time, thereby improving the operational effectiveness and safety of the traffic system, this paper adopts a vehicle target detection algorithm based on YOLOv8. YOLOv8 is the latest iteration developed by Ultralytics, which has further improvements and enhancements compared to YOLOv5. In the backbone network, YOLOv8 employs a C2f structure with richer gradient flow, boosting feature selection capabilities, and enhancing target detection performance and accuracy; In the detection head, YOLOv8 utilizes a Decoupled Head design and uses an improved Anchor-Free method to reduce computational complexity while improving detection efficiency; In terms of loss function, YOLOv8 utilizes the The Task-Aligned Assigner positive sample allocation strategy, and adds the Distribution Focal Loss to improve the model’s generalization ability. This paper divides the vehicles data set into 5 types, trains it using a pre-training model, and optimizes the network parameters through multiple iterations to achieve better detection performance. The experimental results indicate that YOLOv8 reaches the mAP of over 97% on the experimental data set, which is an improvement of approximately 8% compared to YOLOv5, and achieves a good detection performance, and is highly practical.

A Target Collision Algorithm of Autonomous Mobile Robot for Two-player Competition

Abstract A variety of robot competitions are held to train and attract students everywhere. This paper studies the algorithm of autonomous robot with two-player competition. The autonomous robots in a two-player competition takes the scoring form of collision and wins first. The impact object is the enemy target. The key algorithms in a two-player competition are target detection, target path decision, and collision target motion control. First, the vehicle target data set was established and enhanced, the lightweight detection algorithm model was screened and trained, the model pruning optimization experiment and the model deployment optimization experiment were carried out, and then the TensorRT framework was used for inter-layer fusion and data quantification processing. After hitting the target path decision algorithm after detecting the target target, it finally integrates the decision in simple and complex situations. The collision target motion control is the scheme of more intelligent and self-adjustable parameters of fuzzy Radial Basis Function (RBF) network Proportional Integral Derivative (PID) controller. Finally, the collision target implementation algorithm is tested in a real environment, and the results show that the task requirements can be met.