YOLOv3 Algorithm Research Articles

Multispectral pattern camouflage materials based on PU/Al-flake composite: A CNN-based evaluation

With the continuous progress in optical sensor technologies, the emergence of imagery detection systems operating in the infrared (IR) band has become a reality. In response, we present a novel approach designed to deceive imagery IR detectors targeting fighter jets. To implement this method, we developed a specialized coating technique using a Polyurethane (PU)/Aluminum (Al)-flake composite. This composite coating enables the precise application of IR camouflage patterns while preserving the existing visible camouflages on aircraft surfaces. We customized fighter jet IR image datasets by integrating flow and heat transfer numerical analysis results with real-world background measurements. We then employed the YOLOv3 algorithm, based on a convolutional neural network (CNN), which is known for its high performance in object detection. Through this approach, we analyzed the effects of various pattern shapes on camouflage performance. The proposed PU/Al-flake composite coating offers a versatile and effective solution for overlapping IR camouflage patterns onto existing visible camouflages, providing enhanced protection against advanced IR imagery detection systems. This study highlights the potential of a comprehensive approach to developing and evaluating multispectral camouflage materials and effective camouflage strategies, emphasizing practical applications and real-world performance against IR image detectors.

P-037 Deep learning for morphology classification of live stain-free human sperm

Abstract Study question Can a deep-learning algorithm classify live, stain-free human sperm cells based on the whole cell morphology in real-time? Summary answer Our model predicts sperm morphology with 94% precision and accuracy, maintaining performance despite over six-fold image quality reduction, demonstrating less than a 12% accuracy drop. What is known already Sperm morphology analysis plays a crucial role in infertility diagnosis and treatment. However, current clinical methods either use diagnostic staining, rendering sperm cells unsuitable for treatment or depend on subjective manual examination. While deep learning has presented new opportunities for morphology analysis, previous studies only evaluate sperm head morphology, neglecting other important morphological characteristics of sperm midpiece and tail. Additionally, these algorithms rely on fixed and stained images of sperm, preventing their applicability for the classification of live, unstained sperm cells for use in treatment cycles. Study design, size, duration Donor human semen samples (with a concentration range of 30-80 million/mL) comprising 8 technical replicates sourced from 6 biological replicates, were used to generate a dataset of 2254 stain-free single sperm images. Subsequently, three expert clinicians from two different fertility clinics labelled the images according to their morphological status (assessing head, midpiece, and tail morphology) as the ground truth for training our deep-learning model. Model development, training, testing, and analysis were then performed. Participants/materials, setting, methods Using the YOLOv3 algorithm, 2254 single sperm images were automatically extracted from 1000× magnification microscopy images. Three expert andrology scientists from Monash IVF classified and labelled these images based on the WHO morphological characteristics of the sperm head, midpiece, and tail. Then our optimized ensemble structure was trained using 80% of the images for morphology classification of the whole cell. Testing on the remaining unseen images was conducted to assess accuracy, precision, and processing time. Main results and the role of chance While our clinical labelling results highlighted the subjective nature of current manual morphology analysis practices in clinics, with only 16% agreement between experts, our model classifies human sperm images based on their whole morphology status with an accuracy and precision of 94% in real-time (less than a second per image). Testing our model across multiple image resolutions (800 × 800, 224 × 224, 192 × 192, and 128 × 128 pixels) revealed consistent performance, with less than a 12% variation. This underscores the robustness and compatibility of our model across various clinical imaging settings. Importantly, for more challenging images with 2-out-of-3 experts’ agreement (53% of the images) or images without an agreement between experts (25% of the images), our model consistently classified 96% and 97% of the images with at least 75% confidence, respectively. This demonstrates the performance of the model in classifying sperm images that pose difficulties for the experts to label. Consistency in operation and informing sperm selection with quantitative metrics through this platform offers promising opportunities to reduce day-to-day variability in fertility clinics when analysing or selecting sperm. Limitations, reasons for caution This study is confined to samples and clinics exclusively located in Australia, while a larger number of samples across multiple clinics could enhance the generalizability of findings. Additionally, real-time clinical implications and long-term performance evaluation are still needed. Wider implications of the findings This platform not only provides automated evaluation of live sperm as part of infertility diagnostics but also facilitates selection of the most morphologically normal sperm for treatment cycles, particularly in the context of Intracytoplasmic Sperm Injection (ICSI). Therefore, it can enhance positive long-term treatment outcomes by prioritizing normal sperm selection. Trial registration number 2017370

Deep Learning-based Detection of Bird’s Nests on Power Transmission Towers

Abstract The problem of birds building nests on high-altitude towers has posed a significant hidden danger to the safe operation of long-distance transmission lines. The current manual inspection method is inefficient and costly, while automatic inspection technology still faces challenges in accuracy and efficiency. This article mainly aims to propose a deep learning target detection algorithm YOLOV3 based on convolutional neural networks to monitor and retrieve bird damage faults on power towers. By constructing a large dataset of bird nests on power towers, deep learning training models are used to extract features of the detection targets, and the YOLOV3 algorithm is used to intelligentially identify images with bird damage faults. Experiments show that YOLOV3 can effectively detect bird nests on power towers.

Enhanced Area Defense: Magnetic Launcher and Sensor Integration

In this article, the most appropriate design method for a field defense system that operates with magnetic field laws by taking audio and video signals as reference is described. The study is important because it eliminates the operator (soldier) factor in the battlefield. Taking into account the effect of capacitor voltage, capacitance value and accelerator winding inductance value, the main criteria for determining the power supply and armature structure of the electromagnetic launcher are proposed. This proposal is made with MATLAB/Simulink software based mathematical model and the differences are explained by comparing with ANSYS Maxwell simulation. The simulated results show that the speed difference between the models is 7%. Additionally, the design methods of the audio and video-based positioning systems that control the system are explained in the study. In this system where signal receiving microphones are positioned in triangular form, a linear algorithm using the time difference method is utilized. By comparing the theoretical mathematical model with the experimental simulation model, the accuracy of the method and the method function is proved. In this study, a deep learning-based target detection system that operates with the YOLO v2 algorithm is used to increase the system's mission execution capacity. The operator is eliminated by switching the system with the signal received from the positioning systems.

Efficient Real time Zynq 7000 FPGA deployment of optimized YOLOv2 deep leaning model for target detection, based on HDL Coder Methodology

Field Programmable Gate Arrays (FPGAs) have garnered significant attention in the development and enhancement of target identification algorithms that employ YOLOv2 models and FPGAs, owing to their adaptability and user-friendliness. The Simulink HDL compiler was utilized to design, simulate, and implement our proposed design. In an effort to rectify this, this paper presents a comprehensive programming and design proposal. The implementation of the YOLOv2 algorithm for real-time vehicle detection on the Xilinx® Zynq-7000 System-on-a-chip is proposed in this work. Real-time testing of the synthesised hardware revealed that it can process Full HD video at a rate of 16 frames per second. On the Xilinx Zynq-7000 SOC, the estimated dynamic power consumption is less than 90 mW. When comparing the results of the proposed work to those of other simulations, it is observed that resource utilization is enhanced by around 204 k (75%) LUT, 305 (12%) DSP, and 224 k (41%) flip-flops at 200 MHz.

Detection of the Pine Wilt Disease Using a Joint Deep Object Detection Model Based on Drone Remote Sensing Data

Disease and detection is crucial for the protection of forest growth, reproduction, and biodiversity. Traditional detection methods face challenges such as limited coverage, excessive time and resource consumption, and poor accuracy, diminishing the effectiveness of forest disease prevention and control. By addressing these challenges, this study leverages drone remote sensing data combined with deep object detection models, specifically employing the YOLO-v3 algorithm based on loss function optimization, for the efficient and accurate detection of tree diseases and pests. Utilizing drone-mounted cameras, the study captures insect pest image information in pine forest areas, followed by segmentation, merging, and feature extraction processing. The computing system of airborne embedded devices is designed to ensure detection efficiency and accuracy. The improved YOLO-v3 algorithm combined with the CIoU loss function was used to detect forest pests and diseases. Compared to the traditional IoU loss function, CIoU takes into account the overlap area, the distance between the center of the predicted frame and the actual frame, and the consistency of the aspect ratio. The experimental results demonstrate the proposed model’s capability to process pest and disease images at a slightly faster speed, with an average processing time of less than 0.5 s per image, while achieving an accuracy surpassing 95%. The model’s effectiveness in identifying tree pests and diseases with high accuracy and comprehensiveness offers significant potential for developing forest inspection protection and prevention plans. However, limitations exist in the model’s performance in complex forest environments, necessitating further research to improve model universality and adaptability across diverse forest regions. Future directions include exploring advanced deep object detection models to minimize computing resource demands and enhance practical application support for forest protection and pest control.

A Deep Learning Method for Log Diameter Measurement Using Wood Images Based on Yolov3 and DeepLabv3+

Wood volume is an important indicator in timber trading, and log diameter is one of the primary parameters used to calculate wood volume. Currently, the most common methods for measuring log diameters are manual measurement or visual estimation by log scalers, which are laborious, time consuming, costly, and error prone owing to the irregular placement of logs and large numbers of roots. Additionally, this approach can easily lead to misrepresentation of data for profit. This study proposes a model for automatic log diameter measurement that is based on deep learning and uses images to address the existing problems. The specific measures to improve the performance and accuracy of log-diameter detection are as follows: (1) A dual network model is constructed combining the Yolov3 algorithm and DeepLabv3+ architecture to adapt to different log-end color states that considers the complexity of log-end faces. (2) AprilTag vision library is added to estimate the camera position during image acquisition to achieve real-time adjustment of the shooting angle and reduce the effect of log-image deformation on the results. (3) The backbone network is replaced with a MobileNetv2 convolutional neural network to migrate the model to mobile devices, which reduces the number of network parameters while maintaining detection accuracy. The training results show that the mean average precision of log-diameter detection reaches 97.28% and the mean intersection over union (mIoU) of log segmentation reaches 92.22%. Comparisons with other measurement models demonstrate that the proposed model is accurate and stable in measuring log diameter under different environments and lighting conditions, with an average accuracy of 96.26%. In the forestry test, the measurement errors for the volume of an entire truckload of logs and a single log diameter are 1.20% and 0.73%, respectively, which are less than the corresponding error requirements specified in the industry standards. These results indicate that the proposed method can provide a viable and cost-effective solution for measuring log diameters and offering the potential to improve the efficiency of log measurement and promote fair trade practices in the lumber industry.

Enhanced YOLO v3 for precise detection of apparent damage on bridges amidst complex backgrounds

A bridge disease identification approach based on an enhanced YOLO v3 algorithm is suggested to increase the accuracy of apparent disease detection of concrete bridges under complex backgrounds. First, the YOLO v3 network structure is enhanced to better accommodate the dense distribution and large variation of disease scale characteristics, and the detection layer incorporates the squeeze and excitation (SE) networks attention mechanism module and spatial pyramid pooling module to strengthen the semantic feature extraction ability. Secondly, CIoU with better localization ability is selected as the loss function for training. Finally, the K-means algorithm is used for anchor frame clustering on the bridge surface disease defects dataset. 1363 datasets containing exposed reinforcement, spalling, and water erosion damage of bridges are produced, and network training is done after manual labelling and data improvement in order to test the efficacy of the algorithm described in this paper. According to the trial results, the YOLO v3 model has enhanced more than the original model in terms of precision rate, recall rate, Average Precision (AP), and other indicators. Its overall mean Average Precision (mAP) value has also grown by 5.5%. With the RTX2080Ti graphics card, the detection frame rate increases to 84 Frames Per Second, enabling more precise and real-time bridge illness detection.

Implementation of Intelligent Indoor Service Robot Based on ROS and Deep Learning

When faced with challenges such as adapting to dynamic environments and handling ambiguous identification, indoor service robots encounter manifold difficulties. This paper aims to address this issue by proposing the design of a service robot equipped with precise small-object recognition, autonomous path planning, and obstacle-avoidance capabilities. We conducted in-depth research on the suitability of three SLAM algorithms (GMapping, Hector-SLAM, and Cartographer) in indoor environments and explored their performance disparities. Upon this foundation, we have elected to utilize the STM32F407VET6 and Nvidia Jetson Nano B01 as our processing controllers. For the program design on the STM32 side, we are employing the FreeRTOS operating system, while for the Jetson Nano side, we are employing ROS (Robot Operating System) for program design. The robot employs a differential drive chassis, enabling successful autonomous path planning and obstacle-avoidance maneuvers. Within indoor environments, we utilized the YOLOv3 algorithm for target detection, achieving precise target identification. Through a series of simulations and real-world experiments, we validated the performance and feasibility of the robot, including mapping, navigation, and target detection functionalities. Experimental results demonstrate the robot’s outstanding performance and accuracy in indoor environments, offering users efficient service and presenting new avenues and methodologies for the development of indoor service robots.

Image convolution techniques integrated with YOLOv3 algorithm in motion object data filtering and detection.

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.

Research on Intelligent Supervision System of Ore Pass

To prevent safety accidents caused by mining vehicles and personnel entering the operation area by mistakes, it is necessary to reduce the risk of the ore pass. However, the underground space of the mine is narrow, and factors such as dust and noise during the unloading process endanger the health of the personnel on duty in the ore pass. As such, the target detection technology based on deep learning is introduced into the underground monitoring system. The underground surveillance video samples are collected to establish a dataset for Yolov3 algorithm to identify minecarts. Through optimizing the Yolov3 model training process and algorithm, and using the dual-camera collaborative discrimination method, the influence of brightness on the recognition results when the loaders or trucks lights are turned on can be overcome. Four types of minecarts can be accurately identified from the underground surveillance video. On the basis of mining car recognition, an intelligent access control system for mine shafts based on Jetson Nano’s embedded development is developed. The on-site operation results show that the average accuracy of target vehicle recognition is within the range of 95%-100%. The system continuously recognizes the mine car 5 times from the detection program and sends the opening and closing command to complete a 90 ° rotation, which takes only 3 seconds，effectively meeting the needs of the mine for ore pass control.

Research on Key Technologies of Smart Breeding Platform Based on 5G

Abstract In modern animal husbandry, the application of 5G technology opens a new era of farming management, especially in intelligent farming. The high-speed and low-latency communication characteristics make remote monitoring, data transmission, and thoughtful decision-making possible, significantly improving breeding efficiency and management. It has great potential for monitoring animal health, preventing and controlling diseases, and improving production efficiency. This paper explores the application of 5G technology in an intelligent farming management platform and its key technologies. By analyzing the needs of smart farming, we clarify the key application areas of 5G technology. To identify sick pigs, measure their weight accurately using binocular vision technology, and combine with machine learning algorithms, the YOLO v3 algorithm is utilized. The accuracy of sick pig identification based on YOLO v3 reaches 98%, the error of pig weight measurement is controlled within ±2%, and the real-time data transmission and processing realized by 5G technology significantly improves the efficiency of disease prevention and control.5G technology can effectively support the efficient operation of the intelligent farming platform, which is of great significance to enhance the level of farming management and promote the sustainable development of the animal husbandry industry.

Exploration of the Integration and Innovation of Digital Art Elements and Traditional Cultural and Creative Designs

Abstract Combined with the modern development form of traditional cultural and creative design, this paper proposes to use digital art elements to assist traditional cultural and creative design. The symbols of cultural and creative design are extracted using digital-assisted design technology, and the grayscale image extraction method is chosen to process the images of cultural and creative design. Then, combined with the YOLO v3 algorithm, CMT algorithm, and spatial mapping to realize three-dimensional tracking of real objects and real-time tracking interactions in mixed reality, adding digitally assisted experience of cultural symbols. With that, the theoretical model of digital art elements and traditional cultural and creative design is designed, and the procedural method of the entire cultural and creative design is analyzed. Online shopping consumer evaluations are selected, high-frequency words are classified, and consumers’ emotional tendencies are analyzed as well. The comprehensive scores of digital art and cultural and creative products are calculated using sense-quality evaluations. Consumers’ positive and negative emotions accounted for 75.72% and 17.49%, respectively, with the general negative emotion field accounting for the highest proportion of 10.54% and the medium and high negative emotion fields accounting for a lower proportion. It can be seen that the response of digital art elements to the cultural and creative design market is better, and its innovative design has a certain consumer market.

Detection of Apparent Defects in HPLC/Dual Mode Portable Sorting Device Based on Deep Learning and Image Processing

Abstract As the growth of automated detection technology, traditional manual detection has gradually been replaced. To improve the effectiveness of defect detection, a HPLC/dual mode portable sorting device with deep learning and image processing is raised for apparent defect detection. The product image is segmented using flood filled mean shift method, and defect detection is achieved using Yolo v3 algorithm. An LME2918 chip is the main component of the communication module in the portable device. Based on experimental data, image segmentation accuracy can range from 80% to 100%, and image matching accuracy can range from 85% to 95%. Under the power line carrier mode, the average success rate of apparent defect detection in portable sorting devices can reach 85%, and the change in success rate is not significant, indicating that the detection is relatively stable; Under wireless communication mode, the average success rate can reach 83%, and the change in success rate is relatively obvious, because wireless communication is easily affected by the external environment. The experimental data shows that the defect detection effect of the HPLC/dual mode portable sorting device based on deep learning and image processing meets the design requirements.

Rapid and Accurate Identification of Concrete Surface Cracks via a Lightweight & Efficient YOLOv3 Algorithm

Rapid and Accurate Identification of Concrete Surface Cracks via a Lightweight & Efficient YOLOv3 Algorithm

Applications of artificial intelligence recognition technology on construction industry

In the construction industry, technology-based Artificial Intelligence (AI) has become the center of development. AI image recognition technology has been developed and applied to face various application scenarios on the construction site and help workers increase their efficiency and accuracy in recognized work. The purpose of this paper is to introduce two mature AI technologies: the reinforcement quantity identification system and the intelligent identification and evaluation method of typical damages to a fair-faced wall. The reinforcement quantity identification system uses the method to train a model on the Yolo v3 algorithm. It is able to help workers use an image taken to get the number of bars to be counted. The intelligent identification and evaluation method to a fair-faced wall is designed to focus on the three typical damages, weathering, efflorescence, and plant coverage. In the design model, the used algorithm is Yolo v4, and OpenCV is applied as a vision library to access the degree of damages. Workers only need to upload an image to the system, and then it will return an analysis result for the wall. Through this paper, readers will understand their main algorithms and models based on AI technology, as well as their practical applications in the construction industry, and provide a theoretical introduction for future AI image technology references.

Retracted: IOT Monitoring System for Ship Operation Management Based on YOLOv3 Algorithm

Retracted: IOT Monitoring System for Ship Operation Management Based on YOLOv3 Algorithm

Vehicle target detection method based on improved YOLO V3 network model

For the problem of insufficient small target detection ability of the existing network model, a vehicle target detection method based on the improved YOLO V3 network model is proposed in the article. The improvement of the algorithm model can effectively improve the detection ability of small target vehicles in aerial photography. The optimization and adjustment of the anchor box and the improvement of the network residual module have improved the small target detection effect of the algorithm. Furthermore, the introduction of the rectangular prediction frame with orientation angles into the model of this article can improve the vehicle positioning efficiency of the algorithm, greatly reduce the problem of wrong detection and missed detection of vehicles in the model, and provide ideas for solving related problems. Experiments show that the accuracy rate of the improved algorithm model is 89.3%. Compared to the YOLO V3 algorithm, it is improved by 15.9%. The recall rate is improved by 16%, and the F1 value is also improved by 15.9%, which greatly increased the detection efficiency of aerial vehicles.

Potato Malformation Identification and Classification Based on Improved YOLOv3 Algorithm

Potato malformation seriously affects commercial value, and its removal has become one of the core steps in the post-harvest and pre-sales process of potatoes. At present, this work mainly relies on manual visual inspection, which requires a lot of labor and incurs high investment costs. Therefore, precise and efficient automatic detection technology urgently needs to be developed. Due to the efficiency of deep learning based on image information in the field of complex object feature extraction and pattern recognition, this study proposes the use of the YOLOv3 algorithm to undertake potato malformation classification. However, the target box regression loss function MSE of this algorithm is prone to small errors being ignored, and the model code is relatively large, which limits its performance due to the high demand for computing hardware performance and storage space. Accordingly, in this study, CIOU loss is introduced to replace MSE, and thus the shortcoming of the inconsistent optimization direction of the original algorithm’s loss function is overcome, which also significantly reduces the storage space and computational complexity of the network model. Furthermore, deep separable convolution is used instead of traditional convolution. Deep separable convolution first convolves each channel, and then combines different channels point by point. With the introduction of an inverted residual structure and the use of the h-swish activation function, deep separable convolution based on the MobileNetv3 structure can learn more comprehensive feature representations, which can significantly reduce the computational load of the model while improving its accuracy. The test results showed that the model capacity was reduced by 66%, mAP was increased by 4.68%, and training time was shortened by 6.1 h. Specifically, the correctness rates of malformation recognition induced by local protrusion, local depression, proportional imbalance, and mechanical injury within the test set range were 94.13%, 91.00%, 95.52%, and 91.79%, respectively. Misjudgment mainly stemmed from the limitation of training samples and the original accuracy of the human judgment in type labeling. This study lays a solid foundation for the final establishment of an intelligent recognition and classification picking system for malformed potatoes in the next step.

An advanced YOLOv3 method for small object detection

Small object detection has important application value in the fields of autonomous driving and drone scene analysis. As one of the most advanced object detection algorithms, YOLOv3 suffers some challenges when detecting small objects, such as the problem of detection failure of small objects and occluded objects. To solve these problems, an improved YOLOv3 algorithm for small object detection is proposed. In the proposed method, the dilated convolutions mish (DCM) module is introduced into the backbone network of YOLOv3 to improve the feature expression ability by fusing the feature maps of different receptive fields. In the neck network of YOLOv3, the convolutional block attention module (CBAM) and multi-scale fusion module are introduced to select the important information for small object detection in the shallow network, suppress the uncritical information, and use the fusion module to fuse the feature maps of different scales, so as to improve the detection accuracy of the algorithm. In addition, the Soft-NMS and Complete-IOU (ClOU) strategies are applied to candidate frame screening, which improves the accuracy of the algorithm for the detection of occluded objects. The experimental results on MS COCO2017, VOC2007, VOC2012 datasets and the ablation experiments on MS COCO2017 datasets demonstrate the effectiveness of the proposed method.The experimental results show that the proposed method achieves better accuracy in small object detection than the original YOLOv3 model.