Hybrid YOLOv3 and ReID intelligent identification statistical model for people flow in public places.

The statistical model for automatic flow recognition is significant for public place management. However, the current model suffers from insufficient statistical accuracy and low lightweight. Therefore, in this study, the structure of the lightweight object detection model "You Only Live Once v3" is optimized, and the "Deep Simple Online Real-Time Tracking" algorithm with the "Person Re-Identification" module is designed, so as to construct a statistical model for people flow recognition. The results showed that the median PersonAP of the designed model was 94.2%, the total detection time was 216 ms, the Rank-1 and Rank-10 were 87.2% and 98.6%, respectively, and the maximum occupied memory of the whole test set was 2.57 MB, which was better than all comparison models. The results indicate that the intelligent identification statistical model for public crowd flow obtained through this design and training has higher statistical accuracy, less computational resource consumption, and faster computing speed. This has certain application space in the management and guidance of crowd flow in public places.

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.

An effective electricity worker identification approach based on Yolov3-Arcface.

To address the issues of low efficiency and high complexity of detection models for electric power workers in distribution rooms, the electric power worker identification approach is proposed. The ArcFace loss function is used as the coordinate regression loss of the target box. According to the score, the template box with the highest score is selected for prediction, which speeds up the rate of convergence. Dimensional clustering is used to set template boxes for bounding box prediction. The experimental results show that the improved YOLOv3 is a high-performance and lightweight model. The electric power worker identification approach proposed in this paper has a high-speed recognition process, accurate recognition results. The effectiveness of the approach is verified with better detection performance and robustness.

Construction and Application of Rib Fracture Diagnosis Model Based on YOLOv3 Algorithm.

OBJECTIVES: The artificial intelligence-aided diagnosis model of rib fractures based on YOLOv3 algorithm was established and applied to practical case to explore the application advantages in rib fracture cases in forensic medicine. METHODS: DICOM format CT images of 884 cases with rib fractures caused by thoracic trauma were collected, and 801 of them were used as training and validation sets. A rib fracture diagnosis model based on YOLOv3 algorithm and Darknet53 as the backbone network was built. After the model was established, 83 cases were taken as the test set, and the precision rate, recall rate, F1-score and radiology interpretation time were calculated. The model was used to diagnose a practical case and compared with manual diagnosis. RESULTS: The established model was used to test 83 cases, the fracture precision rate of this model was 90.5%, the recall rate was 75.4%, F1-score was 0.82, the radiology interpretation time was 4.4 images per second and the identification time of each patient's data was 21 s, much faster than manual diagnosis. The recognition results of the model was consistent with that of the manual diagnosis. CONCLUSIONS: The rib fracture diagnosis model in practical case based on YOLOv3 algorithm can quickly and accurately identify fractures, and the model is easy to operate. It can be used as an auxiliary diagnostic technique in forensic clinical identification.

Defect Detection in Steel Using a Hybrid Attention Network.

Defect detection in steel surface focuses on accurately identifying and precisely locating defects on the surface of steel materials. Methods of defect detection with deep learning have gained significant attention in research. Existing algorithms can achieve satisfactory results, but the accuracy of defect detection still needs to be improved. Aiming at this issue, a hybrid attention network is proposed in this paper. Firstly, a CBAM attention module is used to enhance the model's ability to learn effective features. Secondly, an adaptively spatial feature fusion (ASFF) module is used to improve the accuracy by extracting multi-scale information of defects. Finally, the CIOU algorithm is introduced to optimize the training loss of the baseline model. The experimental results show that the performance of our method in this work is superior on the NEU-DET dataset, with an 8.34% improvement in mAP. Compared with major algorithms of object detection such as SSD, EfficientNet, YOLOV3, and YOLOV5, the mAP was improved by 16.36%, 41.68%, 20.79%, and 13.96%, respectively. This demonstrates that the mAP of our proposed method is higher than other major algorithms.

Fast and Accurate Defects Detection for Additive Manufactured Parts by Multispectrum and Machine Learning.

Traditional defect detection methods for metal additive manufacturing (AM) have the problems of low detection efficiency and accuracy, while the existing machine learning detection algorithms are of poor adaptability and complex structure. To address the above problems, this article proposed an improved You Only Look Once version 3 (YOLOv3) algorithm to detect the surface defects of metal AM based on multispectrum. The weighted k-means algorithm is used to cluster the target samples to improve the matching degree between the prior frame and the feature layer. The network structure of YOLOv3 is modified by using the lightweight MobileNetv3 to replace the Darknet-53 in the original YOLOv3 algorithm. Dilated convolution and Inceptionv3 are added to improve the detection capability for surface defects. A multispectrum measuring system was also developed to obtain the AM surface data with defects for experimental verification. The results show that the detection accuracy in the test set by YOLOv3-MobileNetv3 network is 11% higher than that by the original YOLOv3 network on average. The detection accuracy for cracking defects of the three types of defects is significantly increased by 23.8%, and the detection speed is also increased by 18.2%. The experimental results show that the improved YOLOv3 algorithm realizes the end-to-end surface defect detection for metal AM with high accuracy and fast speed, which can be further applied for online defect detection.

Evaluation of automated detection of head position on lateral cephalometric radiographs based on deep learning techniques.

BACKGROUND: Lateral cephalometric radiograph (LCR) is crucial to diagnosis and treatment planning of maxillofacial diseases, but inappropriate head position, which reduces the accuracy of cephalometric measurements, can be challenging to detect for clinicians. This non-interventional retrospective study aims to develop two deep learning (DL) systems to efficiently, accurately, and instantly detect the head position on LCRs. METHODS: LCRs from 13 centers were reviewed and a total of 3000 radiographs were collected and divided into 2400 cases (80.0 %) in the training set and 600 cases (20.0 %) in the validation set. Another 300 cases were selected independently as the test set. All the images were evaluated and landmarked by two board-certified orthodontists as references. The head position of the LCR was classified by the angle between the Frankfort Horizontal (FH) plane and the true horizontal (HOR) plane, and a value within - 3°- 3° was considered normal. The YOLOv3 model based on the traditional fixed-point method and the modified ResNet50 model featuring a non-linear mapping residual network were constructed and evaluated. Heatmap was generated to visualize the performances. RESULTS: The modified ResNet50 model showed a superior classification accuracy of 96.0 %, higher than 93.5 % of the YOLOv3 model. The sensitivity&recall and specificity of the modified ResNet50 model were 0.959, 0.969, and those of the YOLOv3 model were 0.846, 0.916. The area under the curve (AUC) values of the modified ResNet50 and the YOLOv3 model were 0.985 ± 0.04 and 0.942 ± 0.042, respectively. Saliency maps demonstrated that the modified ResNet50 model considered the alignment of cervical vertebras, not just the periorbital and perinasal areas, as the YOLOv3 model did. CONCLUSIONS: The modified ResNet50 model outperformed the YOLOv3 model in classifying head position on LCRs and showed promising potential in facilitating making accurate diagnoses and optimal treatment plans.

Deep Learning Based Vehicle Detection on Real and Synthetic Aerial Images: Training Data Composition and Statistical Influence Analysis.

The performance of deep learning based algorithms is significantly influenced by the quantity and quality of the available training and test datasets. Since data acquisition is complex and expensive, especially in the field of airborne sensor data evaluation, the use of virtual simulation environments for generating synthetic data are increasingly sought. In this article, the complete process chain is evaluated regarding the use of synthetic data based on vehicle detection. Among other things, content-equivalent real and synthetic aerial images are used in the process. This includes, in the first step, the learning of models with different training data configurations and the evaluation of the resulting detection performance. Subsequently, a statistical evaluation procedure based on a classification chain with image descriptors as features is used to identify important influencing factors in this respect. The resulting findings are finally incorporated into the synthetic training data generation and in the last step, it is investigated to what extent an increase of the detection performance is possible. The overall objective of the experiments is to derive design guidelines for the generation and use of synthetic data.

Pedestrian detection model based on Tiny-Yolov3 architecture for wearable devices to visually impaired assistance.

Introduction: Wearable assistive devices for the visually impaired whose technology is based on video camera devices represent a challenge in rapid evolution, where one of the main problems is to find computer vision algorithms that can be implemented in low-cost embedded devices. Objectives and Methods: This work presents a Tiny You Only Look Once architecture for pedestrian detection, which can be implemented in low-cost wearable devices as an alternative for the development of assistive technologies for the visually impaired. Results: The recall results of the proposed refined model represent an improvement of 71% working with four anchor boxes and 66% with six anchor boxes compared to the original model. The accuracy achieved on the same data set shows an increase of 14% and 25%, respectively. The F1 calculation shows a refinement of 57% and 55%. The average accuracy of the models achieved an improvement of 87% and 99%. The number of correctly detected objects was 3098 and 2892 for four and six anchor boxes, respectively, whose performance is better by 77% and 65% compared to the original, which correctly detected 1743 objects. Discussion: Finally, the model was optimized for the Jetson Nano embedded system, a case study for low-power embedded devices, and in a desktop computer. In both cases, the graphics processing unit (GPU) and central processing unit were tested, and a documented comparison of solutions aimed at serving visually impaired people was performed. Conclusion: We performed the desktop tests with a RTX 2070S graphics card, and the image processing took about 2.8 ms. The Jetson Nano board could process an image in about 110 ms, offering the opportunity to generate alert notification procedures in support of visually impaired mobility.

Real-Time Automatic Assisted Detection of Uterine Fibroid in Ultrasound Images Using a Deep Learning Detector.

OBJECTIVE: Uterine smooth muscle hyperplasia causes a tumor called a uterine fibroid. With an incidence of up to 30%, it is one of the most prevalent tumors in women and has the third highest prevalence of all gynecological illnesses. Although uterine fibroids are usually not accompanied by symptoms, there are physical effects, such as impairment of the ability to conceive. To reduce morbidity, early detection and treatment are crucial. Ultrasound imaging is a common method used for pre-operative guidance and interventional therapy. Many applications of object detection are performing well with the advancement of deep learning in the field of medical image analysis. To ensure accuracy, computer-assisted detection can further solve the subjective problem generated by different doctors when they read images. METHODS: Our research provides an improved YOLOv3 that combines the properties of EfficientNet and YOLOv3, which use a convolutional neural network to extract features, to detect uterine fibroid ultrasound images. RESULTS: Our approach attained an F1 score of 95% and an average precision of 98.38% and reached a detection speed of 0.28 s per image. We reviewed and analyzed several detection techniques and identified potential future research hotpots. CONCLUSION: This technique offers enough supplementary diagnostic tools for amateur or expert ultrasonologists and sets a solid foundation for future medical care and surgical excision.

A Unified Framework for Monitoring Social Distancing and Face Mask Wearing Using Deep Learning: An Approach to Reduce COVID-19 Risk.

Corona Virus Disease 2019 (COVID-19) is caused by Severe Acute Syndrome Corona Virus 2 (SARS-COV-2). It has become a pandemic disease of the 21st century, killing many lives. During this pandemic situation, precautious measures like social distancing and wearing face mask are being followed globally to break the COVID chain. A pre-programmed viewing system is needed to monitor whether these COVID-19 appropriate behaviours are being followed by the commoners and to ensure COVID-19 preventive measures are followed appropriately. In this work, a deep learning based predictive model and live risk analysis application has been proposed, which detects the high-risk prone areas based on social distancing measures among individuals and face mask wearing tendency of the commoners. The proposed system utilizes ImageNet-1000 dataset for human detection using You Only Look Once (YOLOv3) object detection algorithm; Residual Neural Network (ResNet50v2) uses Kaggle dataset and Real-World Masked Face Dataset (RMFD) for detecting if the persons are face masked or not. Detected human beings (in side-view) are transformed to top view using Top-View Transform Model (TVTM) followed by the calculation of interpersonal distance between the pedestrians and categorized them into three classes include high risk, medium risk, low risk. This unified predictive model provided an accuracy of 97.66%, precision of 97.84%, and F1-Score of 97.92%.

Assessment of YOLOv3 for caries detection in bitewing radiographs based on the ICCMS™ radiographic scoring system.

OBJECTIVES: To assess the feasibility of the YOLOv3 model under the intersection over union (IoU) thresholds of 0.5 (IoU50) and 0.75 (IoU75) for caries detection in bitewing radiographs based on the International Caries Classification and Management System (ICCMS™). MATERIALS AND METHODS: We trained the YOLOv3 model by feeding 994 annotated radiographs with the IoU50 and IoU75 thresholds. The testing procedure (n = 175) was subsequently conducted to evaluate the model's prediction metrics on caries classification based on the ICCMS™ radiographic scoring system. RESULTS: Regarding the 4-class classification representing caries severity, YOLOv3 could accurately detect and classify enamel caries and initial dentin caries (class RA) (IoU50 vs IoU75: precision, 0.75 vs 0.71; recall, 0.67 vs 0.64). Concerning the 7-class classification signifying specific caries depth (class 0, healthy tooth; classes RA1-3, initial caries affecting outer half, inner half of enamel, and the outer 1/3 of dentin; class RB4, caries extending to the middle 1/3 of dentin; classes RC5-6, extensively cavitated caries affecting the inner 1/3 of dentin and involving the pulp chamber), YOLOv3 could accurately detect and classify caries with pulpal exposure (class RC6) (IoU50 vs IoU75: precision, 0.77 vs 0.73; recall, 0.61 vs 0.57) but it failed to predict the outer half of enamel caries (class RA1) (IoU50 vs IoU75: precision, 0.35 vs 0.32; recall, 0.23 vs 0.21). CONCLUSIONS: YOLOv3 yielded acceptable performances in both IoU50 and IoU75. Although the performance metrics decreased in the 7-class detection, the two thresholds revealed comparable results. However, the model could not consistently detect initial-stage caries affecting the outermost surface of the enamel. CLINICAL RELEVANCE: YOLOv3 could be implemented to detect and classify dental caries according to the ICCMS™ classification with acceptable performances to assist dentists in making treatment decisions.

Towards smart surveillance as an aftereffect of COVID-19 outbreak for recognition of face masked individuals using YOLOv3 algorithm.

The eruption of COVID-19 pandemic has led to the blossoming usage of face masks among individuals in the communal settings. To prevent the transmission of the virus, a mandatory mask-wearing rule in public areas has been enforced. Owing to the use of face masks in communities at different workplaces, an effective surveillance seems essential because several security analyses indicate that face masks may be used as a tool to hide the identity. Therefore, this work proposes a framework for the development of a smart surveillance system as an aftereffect of COVID-19 for recognition of individuals behind the face mask. For this purpose, transfer learning approach has been employed to train the custom dataset by YOLOv3 algorithm in the Darknet neural network framework. Moreover, to demonstrate the competence of YOLOv3 algorithm, a comparative analysis with YOLOv3-tiny has been presented. The simulated results verify the robustness of YOLOv3 algorithm in the recognition of individuals behind the face mask. Also, YOLOv3 algorithm achieves a mAP of 98.73% on custom dataset, outperforming YOLOv3-tiny by approximately 62%. Moreover, YOLOv3 algorithm provides adequate speed and accuracy on small faces.

Education robot object detection with a brain-inspired approach integrating Faster R-CNN, YOLOv3, and semi-supervised learning.

The development of education robots has brought tremendous potential and opportunities to the field of education. These intelligent machines can interact with students in classrooms and learning environments, providing personalized educational support. To enable education robots to fulfill their roles, they require accurate object detection capabilities to perceive and understand the surrounding environment of students, identify targets, and interact with them. Object detection in complex environments remains challenging, as classrooms or learning scenarios involve various objects, backgrounds, and lighting conditions. Improving the accuracy and efficiency of object detection is crucial for the development of education robots. This paper introduces the progress of an education robot's object detection based on a brain-inspired heuristic method, which integrates Faster R-CNN, YOLOv3, and semi-supervised learning. By combining the strengths of these three techniques, we can improve the accuracy and efficiency of object detection in education robot systems. In this work, we integrate two popular object detection algorithms: Faster R-CNN and YOLOv3. We conduct a series of experiments on the task of education robot object detection. The experimental results demonstrate that our proposed optimization algorithm significantly outperforms individual algorithms in terms of accuracy and real-time performance. Moreover, through semi-supervised learning, we achieve better performance with fewer labeled samples. This will provide education robots with more accurate perception capabilities, enabling better interaction with students and delivering personalized educational experiences. It will drive the development of the field of education robots, offering innovative and personalized solutions for education.

Construction and Application of Rib Fracture Diagnosis Model Based on YOLOv3 Algorithm / 法医学杂志

OBJECTIVES@#The artificial intelligence-aided diagnosis model of rib fractures based on YOLOv3 algorithm was established and applied to practical case to explore the application advantages in rib fracture cases in forensic medicine.@*METHODS@#DICOM format CT images of 884 cases with rib fractures caused by thoracic trauma were collected, and 801 of them were used as training and validation sets. A rib fracture diagnosis model based on YOLOv3 algorithm and Darknet53 as the backbone network was built. After the model was established, 83 cases were taken as the test set, and the precision rate, recall rate, F1-score and radiology interpretation time were calculated. The model was used to diagnose a practical case and compared with manual diagnosis.@*RESULTS@#The established model was used to test 83 cases, the fracture precision rate of this model was 90.5%, the recall rate was 75.4%, F1-score was 0.82, the radiology interpretation time was 4.4 images per second and the identification time of each patient's data was 21 s, much faster than manual diagnosis. The recognition results of the model was consistent with that of the manual diagnosis.@*CONCLUSIONS@#The rib fracture diagnosis model in practical case based on YOLOv3 algorithm can quickly and accurately identify fractures, and the model is easy to operate. It can be used as an auxiliary diagnostic technique in forensic clinical identification.

Traffic Sign Recognition Based on the YOLOv3 Algorithm.

Traffic sign detection is an essential component of an intelligent transportation system, since it provides critical road traffic data for vehicle decision-making and control. To solve the challenges of small traffic signs, inconspicuous characteristics, and low detection accuracy, a traffic sign recognition method based on improved (You Only Look Once v3) YOLOv3 is proposed. The spatial pyramid pooling structure is fused into the YOLOv3 network structure to achieve the fusion of local features and global features, and the fourth feature prediction scale of 152 × 152 size is introduced to make full use of the shallow features in the network to predict small targets. Furthermore, the bounding box regression is more stable when the distance-IoU (DIoU) loss is used, which takes into account the distance between the target and anchor, the overlap rate, and the scale. The Tsinghua-Tencent 100K (TT100K) traffic sign dataset's 12 anchors are recalculated using the K-means clustering algorithm, while the dataset is balanced and expanded to address the problem of an uneven number of target classes in the TT100K dataset. The algorithm is compared to YOLOv3 and other commonly used target detection algorithms, and the results show that the improved YOLOv3 algorithm achieves a mean average precision (mAP) of 77.3%, which is 8.4% higher than YOLOv3, especially in small target detection, where the mAP is improved by 10.5%, greatly improving the accuracy of the detection network while keeping the real-time performance as high as possible. The detection network's accuracy is substantially enhanced while keeping the network's real-time performance as high as possible.

An Optimization-Based Technology Applied for Face Skin Symptom Detection.

Face recognition segmentation is very important for symptom detection, especially in the case of complex image backgrounds or noise. The complexity of the photo background, the clarity of the facial expressions, or the interference of other people's faces can increase the difficulty of detection. Therefore, in this paper, we have proposed a method to combine mask region-based convolutional neural networks (Mask R-CNN) with you only look once version 4 (YOLOv4) to identify facial symptoms by this new method. We use the face image dataset from the public image databases DermNet and Freepic as the training source for the model. Face segmentation was first applied with Mask R-CNN. Then the images were imported into ResNet-101, and the facial features were fused with region of interest (RoI) in the feature pyramid networks (FPN) structures. After removing the non-face features and noise, the face region has been accurately obtained. Next, the recognized face area and RoI data were used to identify facial symptoms (acne, freckle, and wrinkles) with YOLOv4. Finally, we use Mask R-CNN, and you only look once version 3 (YOLOv3) and YOLOv4 are matched to perform the performance analysis. Although, the facial images with symptoms are relatively few. We still use a limited amount of data to train the model. The experimental results show that our proposed method still achieves 57.73%, 60.38%, and 59.75% of mean average precision (mAP) for different amounts of data. Compared with other methods, the mAP was more than about 3%. Consequently, using the method proposed in this paper, facial symptoms can be effectively and accurately identified.

Real-Time Detection of Drones Using Channel and Layer Pruning, Based on the YOLOv3-SPP3 Deep Learning Algorithm.

Achieving a real-time and accurate detection of drones in natural environments is essential for the interception of drones intruding into high-security areas. However, a rapid and accurate detection of drones is difficult because of their small size and fast speed. In this paper a drone detection method as proposed by pruning the convolutional channel and residual structures of YOLOv3-SPP3. First, the k-means algorithm was used to cluster label the boxes. Second, the channel and shortcut layer pruning algorithm was used to prune the model. Third, the model was fine tuned to achieve a real-time detection of drones. The experimental results obtained by using the Ubuntu server under the Python 3.6 environment show that the YOLOv3-SPP3 algorithm is better than YOLOV3, Tiny-YOLOv3, CenterNet, SSD300, and faster R-CNN. There is significant compression in the size, the maximum compression factor is 20.1 times, the maximum detection speed is increased by 10.2 times, the maximum map value is increased by 15.2%, and the maximum precision is increased by 16.54%. The proposed algorithm achieves the mAP score of 95.15% and the detection speed of 112 f/s, which can meet the requirements of the real-time detection of UAVs.

A Novel Improved YOLOv3-SC Model for Individual Pig Detection.

Pork is the most widely consumed meat product in the world, and achieving accurate detection of individual pigs is of great significance for intelligent pig breeding and health monitoring. Improved pig detection has important implications for improving pork production and quality, as well as economics. However, most of the current approaches are based on manual labor, resulting in unfeasible performance. In order to improve the efficiency and effectiveness of individual pig detection, this paper describes the development of an attention module enhanced YOLOv3-SC model (YOLOv3-SPP-CBAM. SPP denotes the Spatial Pyramid Pooling module and CBAM indicates the Convolutional Block Attention Module). Specifically, leveraging the attention module, the network will extract much richer feature information, leading the improved performance. Furthermore, by integrating the SPP structured network, multi-scale feature fusion can be achieved, which makes the network more robust. On the constructed dataset of 4019 samples, the experimental results showed that the YOLOv3-SC network achieved 99.24% mAP in identifying individual pigs with a detection time of 16 ms. Compared with the other popular four models, including YOLOv1, YOLOv2, Faster-RCNN, and YOLOv3, the mAP of pig identification was improved by 2.31%, 1.44%, 1.28%, and 0.61%, respectively. The YOLOv3-SC proposed in this paper can achieve accurate individual detection of pigs. Consequently, this novel proposed model can be employed for the rapid detection of individual pigs on farms, and provides new ideas for individual pig detection.

Identification and Localisation Algorithm for Sugarcane Stem Nodes by Combining YOLOv3 and Traditional Methods of Computer Vision.

Sugarcane stem node identification is the core technology required for the intelligence and mechanization of the sugarcane industry. However, detecting stem nodes quickly and accurately is still a significant challenge. In this paper, in order to solve this problem, a new algorithm combining YOLOv3 and traditional methods of computer vision is proposed, which can improve the identification rate during automated cutting. First, the input image is preprocessed, during which affine transformation is used to correct the posture of the sugarcane and a rotation matrix is established to obtain the region of interest of the sugarcane. Then, a dataset is built to train the YOLOv3 network model and the position of the stem nodes is initially determined using the YOLOv3 model. Finally, the position of the stem nodes is further located accurately. In this step, a new gradient operator is proposed to extract the edge of the image after YOLOv3 recognition. Then, a local threshold determination method is proposed, which is used to binarize the image after edge extraction. Finally, a localization algorithm for stem nodes is designed to accurately determine the number and location of the stem nodes. The experimental results show that the precision rate, recall rate, and harmonic mean of the stem node recognition algorithm in this paper are 99.68%, 100%, and 99.84%, respectively. Compared to the YOLOv3 network, the precision rate and the harmonic mean are improved by 2.28% and 1.13%, respectively. Compared to other methods introduced in this paper, this algorithm has the highest recognition rate.