A lightweight YOLOv3 algorithm used for safety helmet detection.
Ontology highlight
ABSTRACT:
SUBMITTER: Deng L
PROVIDER: S-EPMC9243020 | biostudies-literature | 2022 Jun
REPOSITORIES: biostudies-literature
Publications
A lightweight YOLOv3 algorithm used for safety helmet detection.
Deng Lixia L Li Hongquan H Liu Haiying H Gu Jason J
Scientific reports 20220629 1
YOLOv3 is a popular and effective object detection algorithm. However, YOLOv3 has a complex network, and floating point operations (FLOPs) and parameter sizes are large. Based on this, the paper designs a new YOLOv3 network and proposes a lightweight object detection algorithm. First, two excellent networks, the Cross Stage Partial Network (CSPNet) and GhostNet, are integrated to design a more efficient residual network, CSP-Ghost-Resnet. Second, combining CSPNet and Darknet53, this paper design ...[more]
Similar Datasets
Project description:Object detection based on deep learning has made great progress in the past decade and has been widely used in various fields of daily life. Model lightweighting is the core of deploying target detection models on mobile or edge devices. Lightweight models have fewer parameters and lower computational costs, but are often accompanied by lower detection accuracy. Based on YOLOv5s, this article proposes an improved lightweight target detection model, which can achieve higher detection accuracy with smaller parameters. Firstly, utilizing the lightweight feature of the Ghost module, we integrated it into the C3 structure and replaced some of the C3 modules after the upsample layer on the neck network, thereby reducing the number of model parameters and expediting the model's inference process. Secondly, the coordinate attention (CA) mechanism was added to the neck to enhance the model's ability to pay attention to relevant information and improved detection accuracy. Finally, a more efficient Simplified Spatial Pyramid Pooling-Fast (SimSPPF) module was designed to enhance the stability of the model and shorten the training time of the model. In order to verify the effectiveness of the improved model, experiments were conducted using three datasets with different features. Experimental results show that the number of parameters of our model is significantly reduced by 28% compared with the original model, and mean average precision (mAP) is increased by 3.1%, 1.1% and 1.8% respectively. The model also performs better in terms of accuracy compared to existing lightweight state-of-the-art models. On three datasets with different features, mAP of the proposed model achieved 87.2%, 77.8% and 92.3%, which is better than YOLOv7tiny (81.4%, 77.7%, 90.3%), YOLOv8n (84.7%, 77.7%, 90.6%) and other advanced models. When achieving the decreased number of parameters, the improved model can successfully increase mAP, providing great reference for deploying the model on mobile or edge devices.
| S-EPMC10909222 | biostudies-literature
Project description:In order to address the challenges of identifying, detecting, and tracking moving objects in video surveillance, this paper emphasizes image-based dynamic entity detection. It delves into the complexities of numerous moving objects, dense targets, and intricate backgrounds. Leveraging the You Only Look Once (YOLOv3) algorithm framework, this paper proposes improvements in image segmentation and data filtering to address these challenges. These enhancements form a novel multi-object detection algorithm based on an improved YOLOv3 framework, specifically designed for video applications. Experimental validation demonstrates the feasibility of this algorithm, with success rates exceeding 60% for videos such as "jogging", "subway", "video 1", and "video 2". Notably, the detection success rates for "jogging" and "video 1" consistently surpass 80%, indicating outstanding detection performance. Although the accuracy slightly decreases for "Bolt" and "Walking2", success rates still hover around 70%. Comparative analysis with other algorithms reveals that this method's tracking accuracy surpasses that of particle filters, Discriminative Scale Space Tracker (DSST), and Scale Adaptive Multiple Features (SAMF) algorithms, with an accuracy of 0.822. This indicates superior overall performance in target tracking. Therefore, the improved YOLOv3-based multi-object detection and tracking algorithm demonstrates robust filtering and detection capabilities in noise-resistant experiments, making it highly suitable for various detection tasks in practical applications. It can address inherent limitations such as missed detections, false positives, and imprecise localization. These improvements significantly enhance the efficiency and accuracy of target detection, providing valuable insights for researchers in the field of object detection, tracking, and recognition in video surveillance.
| S-EPMC10984955 | biostudies-literature
Project description:The detection of objects concealed under people's clothing is a very challenging task, which has crucial applications for security. When testing the human body for metal contraband, the concealed targets are usually small in size and are required to be detected within a few seconds. Focusing on weapon detection, this paper proposes using a real-time detection method for detecting concealed metallic weapons on the human body applied to passive millimeter wave (PMMW) imagery based on the You Only Look Once (YOLO) algorithm, YOLOv3, and a small sample dataset. The experimental results from YOLOv3-13, YOLOv3-53, and Single Shot MultiBox Detector (SSD) algorithm, SSD-VGG16, are compared ultimately, using the same PMMW dataset. For the perspective of detection accuracy, detection speed, and computation resource, it shows that the YOLOv3-53 model had a detection speed of 36 frames per second (FPS) and a mean average precision (mAP) of 95% on a GPU-1080Ti computer, more effective and feasible for the real-time detection of weapon contraband on human body for PMMW images, even with small sample data.
| S-EPMC7147325 | biostudies-literature
Project description:Wearing a safety helmet is important in construction and manufacturing industrial activities to avoid unpleasant situations. This safety compliance can be ensured by developing an automatic helmet detection system using various computer vision and deep learning approaches. Developing a deep-learning-based helmet detection model usually requires an enormous amount of training data. However, there are very few public safety helmet datasets available in the literature, in which most of them are not entirely labeled, and the labeled one contains fewer classes. This paper presents the Safety HELmet dataset with 5K images (SHEL5K) dataset, an enhanced version of the SHD dataset. The proposed dataset consists of six completely labeled classes (helmet, head, head with helmet, person with helmet, person without helmet, and face). The proposed dataset was tested on multiple state-of-the-art object detection models, i.e., YOLOv3 (YOLOv3, YOLOv3-tiny, and YOLOv3-SPP), YOLOv4 (YOLOv4 and YOLOv4pacsp-x-mish), YOLOv5-P5 (YOLOv5s, YOLOv5m, and YOLOv5x), the Faster Region-based Convolutional Neural Network (Faster-RCNN) with the Inception V2 architecture, and YOLOR. The experimental results from the various models on the proposed dataset were compared and showed improvement in the mean Average Precision (mAP). The SHEL5K dataset had an advantage over other safety helmet datasets as it contains fewer images with better labels and more classes, making helmet detection more accurate.
| S-EPMC8950768 | biostudies-literature
Project description:BackgroundThe aim of this study was to explore the value of using the YOLOv3 algorithm for detection and diagnosis of dental caries in oral photographs taken with mobile phones.MethodsOral photographs taken with the mobile phones of 570 patients were used as 3 datasets: the augmented images (n=3,990), the enhanced images (n=3,990), and the combined augmented and enhanced images (n=7,980). Oral photographs taken by mobile phones from another 70 patients were used as an independent test set. We used the YOLOv3 network for migration learning for modelling. Diagnostic precision, recall, F1-score, and mean average precision (mAP) were calculated to obtain the detection and diagnostic performance of the YOLOv3 algorithm.ResultsAfter 3 independent training, the mAP value of the original group YOLOv3 algorithm was 56.20%, in which the precision for primary caries recognition was 76.92%, recall was 49.59%, and F1-score was 0.60; the precision for secondary caries recognition was 91.67%, recall was 52.38%, and F1-score was 0.67. The mAP value of the enhance group algorithm was 66.69%, in which the precision for primary caries identification was 81.82%, recall was 52.07%, and F1-score was 0.64, and the precision for secondary caries identification was 100%, recall was 33.33%, and F1-score was 0.50. The mAP value of the comprehensive group algorithm was 85.48%, in which the precision for primary caries identification was 93.33%, recall was 69.42%, F1-score was 0.80, and the F1-score for secondary caries identification was 0.50; precision was 100%, recall was 52.38%, and F1-score was 0.69.ConclusionsThe caries detection capability based on the YOLOv3 algorithm highlights the potential utility of deep learning in caries detection and diagnosis. Comparing the 3 experiments, the detection of the model trained after using image augmented and enhancement techniques was significantly improved.
| S-EPMC8640896 | biostudies-literature
Project description:In response to the issues of low precision, a large number of parameters and high model complexity in steel surface defect detection, a lightweight algorithm using improved YOLOv8 is proposed. Firstly, GhostNet is utilized as the backbone network in order to reduce the number of model parameters and computational complexity. Secondly, the MPCA (MultiPath Coordinate Attention) attention mechanism is integrated to enhance feature extraction capabilities. Finally, the SIoU (Simplified IoU ) is used to replace the traditional CIoU loss function, which can make the anchor frame more fast and accurate in the regression process, to improve the stability and the robustness of detection. The experimental results indicate that these enhancements have led to a reduction of 37% in calculation amount for the improved YOLOv8n algorithm, a decrease of 32% in parameter count, and an increase in average detection accuracy ( mAP ) by 1.2%. This model achieves a balance between lightweighting and detection accuracy while providing a viable solution for deployment in computationally resource-constrained edge computing environments such as embedded systems and mobile devices.
| S-EPMC11910532 | biostudies-literature
Project description:As the UAV(Unmanned Aerial Vehicle) carrying target detection algorithm in transmission line insulator inspection, we propose a lightweight YOLOv7 insulator defect detection algorithm for the problems of inferior insulator defect detection speed and high model complexity. Firstly, a lightweight DSC-SE module is designed using a DSC(Depthwise Separable Convolution) fused SE channel attention mechanism to substitute the SC(Standard Convolution) of the YOLOv7 backbone extraction network to decrease the number of parameters in the network as well as to strengthen the shallow network's ability to obtain information about target features. Then, in the feature fusion part, GSConv(Grid Sensitive Convolution) is used instead of standard convolution to further lessen the number of parameters and the computational effort of the network. EIoU-loss(Efficient-IoU) is performed in the prediction head part to make the model converge faster. According to the experimental results, the recognition accuracy rate of the improved model is 95.2%, with a model size of 7.9M. Compared with YOLOv7, the GFLOPs are reduced by 54.5%, the model size is compressed by 37.8%, and the accuracy is improved by 4.9%. The single image detection time on the Jetson Nano is 105ms and the capture rate is 13FPS. With guaranteed accuracy and detection speed, it meets the demands of real-time detection.
| S-EPMC10732421 | biostudies-literature
Project description:Tomatoes, widely cherished for their high nutritional value, necessitate precise ripeness identification and selective harvesting of mature fruits to significantly enhance the efficiency and economic benefits of tomato harvesting management. Previous studies on intelligent harvesting often focused solely on identifying tomatoes as the target, lacking fine-grained detection of tomato ripeness. This deficiency leads to the inadvertent harvesting of immature and rotten fruits, resulting in economic losses. Moreover, in natural settings, uneven illumination, occlusion by leaves, and fruit overlap hinder the precise assessment of tomato ripeness by robotic systems. Simultaneously, the demand for high accuracy and rapid response in tomato ripeness detection is compounded by the need for making the model lightweight to mitigate hardware costs. This study proposes a lightweight model named PDSI-RTDETR to address these challenges. Initially, the PConv_Block module, integrating partial convolution with residual blocks, replaces the Basic_Block structure in the legacy backbone to alleviate computing load and enhance feature extraction efficiency. Subsequently, a deformable attention module is amalgamated with intra-scale feature interaction structure, bolstering the capability to extract detailed features for fine-grained classification. Additionally, the proposed slimneck-SSFF feature fusion structure, merging the Scale Sequence Feature Fusion framework with a slim-neck design utilizing GSConv and VoVGSCSP modules, aims to reduce volume of computation and inference latency. Lastly, by amalgamating Inner-IoU with EIoU to formulate Inner-EIoU, replacing the original GIoU to expedite convergence while utilizing auxiliary frames enhances small object detection capabilities. Comprehensive assessments validate that the PDSI-RTDETR model achieves an average precision mAP50 of 86.8%, marking a 3.9% enhancement over the original RT-DETR model, and a 38.7% increase in FPS. Furthermore, the GFLOPs of PDSI-RTDETR have been diminished by 17.6%. Surpassing the baseline RT-DETR and other prevalent methods regarding precision and speed, it unveils its considerable potential for detecting tomato ripeness. When applied to intelligent harvesting robots in the future, this approach can improve the quality of tomato harvesting by reducing the collection of immature and spoiled fruits.
| S-EPMC11257922 | biostudies-literature
Project description:Currently robotic motion control algorithms are tedious at best to implement, are lacking in automatic situational adaptability, and tend to be static in nature. Humanoid (human-like) control is little more than a dream, for all, but the fastest computers. The main idea of the work presented in this paper is to define a radically new, simple, and computationally lightweight approach to humanoid motion control. A new Proportional-Integral-Derivative (PID) controller algorithm called PID++ is proposed in this work that uses minor adjustments with basic arithmetic, based on the real-time encoder position input, to achieve a stable, precise, controlled, dynamic, adaptive control system, for linear motion control, in any direction regardless of load. With no PID coefficients initially specified, the proposed PID++ algorithm dynamically adjusts and updates the PID coefficients Kp, Ki and Kd periodically. No database of values is required to be stored as only the current and previous values of the sensed position with an accurate time base are used in the computations and overwritten in each read interval, eliminating the need of deploying much memory for storing and using vectors or matrices. Complete in its implementation, and truly dynamic and adaptive by design, engineers will be able to use this algorithm in commercial, industrial, biomedical, and space applications alike. With characteristics that are unmistakably human, motion control can be feasibly implemented on even the smallest microcontrollers (MCU) using a single command and without the need of reprogramming or reconfiguration.
| S-EPMC7826970 | biostudies-literature
Project description:In-flight system failure is one of the major safety concerns in the operation of unmanned aerial vehicles (UAVs) in urban environments. To address this concern, a safety framework consisting of following three main tasks can be utilized: (1) Monitoring health of the UAV and detecting failures, (2) Finding potential safe landing spots in case a critical failure is detected in step 1, and (3) Steering the UAV to a safe landing spot found in step 2. In this paper, we specifically look at the second task, where we investigate the feasibility of utilizing object detection methods to spot safe landing spots in case the UAV suffers an in-flight failure. Particularly, we investigate different versions of the YOLO objection detection method and compare their performances for the specific application of detecting a safe landing location for a UAV that has suffered an in-flight failure. We compare the performance of YOLOv3, YOLOv4, and YOLOv5l while training them by a large aerial image dataset called DOTA in a Personal Computer (PC) and also a Companion Computer (CC). We plan to use the chosen algorithm on a CC that can be attached to a UAV, and the PC is used to verify the trends that we see between the algorithms on the CC. We confirm the feasibility of utilizing these algorithms for effective emergency landing spot detection and report their accuracy and speed for that specific application. Our investigation also shows that the YOLOv5l algorithm outperforms YOLOv4 and YOLOv3 in terms of accuracy of detection while maintaining a slightly slower inference speed.
| S-EPMC8778480 | biostudies-literature