Platelet Detection Based on Improved YOLO_v3

We propose a lightweight detection algorithm based on the Single Shot MultiBox Detector (SSD) algorithm in order to facilitate sheep management and to realize sheep facial identification, and we take the self-constructed dataset as the research object. First, the SSD replaces the VGG16 backbone network with MobileNetv3, a lightweight neural network, to create a hybrid model that is much smaller. Second, the ECA attention mechanism is incorporated into the backend of the 72 × 160 bottleneck layer. Finally, the SmoothL1 loss function is substituted with the BalancedL1 loss function. The optimized model’s size decreases significantly from the original SSD’s 132 MB to just 22.4 MB. It achieves a mean average precision of 83.47% and maintains an average frame rate of 68.53 frames per second. Compared to the basic SSD model, the mean average precision has increased by 3.25 percentage points, the model size has decreased by 109.6 MB, and the detection speed has improved by 9.55 frames per second. In comparative experiments using the same dataset with different object detection models, the proposed model outperforms the SSD, Faster R-CNN, Retinanet, and CenterNet in terms of mean average precision, with improvements of 3.25 percentage points, 4.71 percentage points, 2.38 percentage points, and 8.13 percentage points, respectively. The detection speed has shown significant improvements, increasing by 9.55, 58.55, 53.1, and 12.37 frames per second, respectively. The improved model presented in this paper significantly reduces the model’s size and computational requirements while maintaining an excellent performance. This provides a valuable reference for the digitalization of animal husbandry and livestock farming.

Foreign bodies such as a surgical gauze can be retained in the body after surgery and in some cases cannot be detected by postoperative radiography. The aim of this study was to develop an object detection model capable of postsurgical detection of retained gauze in the body. The object detection model used deep learning using abdominal radiographs, and a phantom study was performed to evaluate the ability of the model to automatically detect retained surgical gauze. The object detection model was constructed using a Single Shot MultiBox Detector (SSD) 300. In total, 268 abdominal phantom images were used: 180 gauze images were used as training data, 20 gauze images were used as validation data, and an additional 34 gauze images and 34 nongauze images were used as test data. To evaluate the performance of the object detection model, a confusion matrix was created and the accuracy and sensitivity were calculated. True-positive (TP) rate, true-negative (TN) rate, false-positive (FP) rate, and false-negative (FN) rate were 0.92, 1.00, 0.00, and 0.08, respectively. Accuracy was 0.96, and sensitivity was 0.92. The object detection model could detect surgical gauze on abdominal phantom images with a high accuracy and sensitivity.

Wild birds are monitored with the important objectives of identifying their habitats and estimating the size of their populations. Especially in the case of migratory bird, they are significantly recorded during specific periods of time to forecast any possible spread of animal disease such as avian influenza. This study led to the construction of deep-learning-based object-detection models with the aid of aerial photographs collected by an unmanned aerial vehicle (UAV). The dataset containing the aerial photographs includes diverse images of birds in various bird habitats and in the vicinity of lakes and on farmland. In addition, aerial images of bird decoys are captured to achieve various bird patterns and more accurate bird information. Bird detection models such as Faster Region-based Convolutional Neural Network (R-CNN), Region-based Fully Convolutional Network (R-FCN), Single Shot MultiBox Detector (SSD), Retinanet, and You Only Look Once (YOLO) were created and the performance of all models was estimated by comparing their computing speed and average precision. The test results show Faster R-CNN to be the most accurate and YOLO to be the fastest among the models. The combined results demonstrate that the use of deep-learning-based detection methods in combination with UAV aerial imagery is fairly suitable for bird detection in various environments.

Recently, Coronavirus Disease (COVID-19) has spread rapidly across the world and thus social distancing and face mask has become one of the mandatory preventive measures. The Artificial Intelligence community has been focusing on developments for monitoring social distancing and identifying face masks, which have become the hotspot and made the headlines. A powerful approach for fast and more accurate detection and monitoring would greatly enhance the sole purpose, save the lives of many and also alleviate the burden of doing it manually to some extent. You Only Look Once(Yolov3) and improved Single Shot multi-box Detector (SSD) algorithm has been deployed for an improved object detection model to lend a helping hand in the fight against this deadly disease. The proposed framework utilizes Single Shot multi-box Detector (SSD) with MobileNetV2, to enhance the feature extraction ability of the object detection model. After taking into account the significance of developing an accurate model and also the limitations of existing models, herein we have proposed a framework based on deep learning, which would automate and simplify the task of monitoring social distancing and face mask through intelligent video analytics.

Sea turtles exhibit high migratory rates and occupy a broad range of habitats, which in turn makes monitoring these taxa challenging. Applying deep learning (DL) models to vast image datasets collected from citizen science programs can offer promising solutions to overcome the challenge of monitoring the wide habitats of wildlife, particularly sea turtles. Among DL models, object detection models, such as the You Only Look Once (YOLO) series, have been extensively employed for wildlife classification. Despite their successful application in this domain, detecting objects in images with complex backgrounds, including underwater environments, remains a significant challenge. Recently, instance segmentation models have been developed to address this issue by providing more accurate classification of complex images compared to traditional object detection models. This study compared the performance of two state-of-the-art DL methods namely; the object detection model (YOLOv5) and instance segmentation model (YOLOv5-seg), to detect and classify sea turtles. The images were collected from iNaturalist and Google and then divided into 64% for training, 16% for validation, and 20% for test sets. Model performance during and after finishing training was evaluated by loss functions and various indexes, respectively. Based on loss functions, YOLOv5-seg demonstrated a lower error rate in detecting rather than classifying sea turtles than the YOLOv5. According to mean Average Precision (mAP) values, which reflect precision and recall, the YOLOv5-seg model showed superior performance than YOLOv5. The mAP0.5 and mAP0.5:0.95 for the YOLOv5 model were 0.885 and 0.795, respectively, whereas for the YOLOv5-seg, these values were 0.918 and 0.831, respectively. In particular, based on the loss functions and classification results, the YOLOv5-seg showed improved performance for detecting rather than classifying sea turtles compared to the YOLOv5. The results of this study may help improve sea turtle monitoring in the future.

This work presents an automated system for recognizing Brazilian vertical traffic signs and lights using artificial intelligence. The main objective of the system is to contribute to road safety by alerting drivers to potential risks such as speeding, alcohol consumption, and cell phone use, which could lead to severe accidents. The system’s core contribution lies in its ability to accurately recognize various traffic signs and lights, providing crucial warnings to drivers. To achieve this, the system utilizes a light version of the single shot multi box detector as its detection algorithm and experiments with three Mobilenet versions as base networks. The optimal Mobilenet version is selected based on a mean average precision higher than 80%, which guarantees reliable detection results. The dataset used for training and evaluation comprises images extracted from YouTube traffic videos, each annotated to create the necessary labels for training. Through this extensive experimentation, the system demonstrates its efficacy in achieving accurate and efficient detection. The results of the experiments are compared with other existing approaches and our work significantly advances the field by providing a tailored dataset, an optimized model, and also valuable insights into traffic sign and light recognition, collectively contributing to the improvement of road safety.

Prediction of plant pest detection using improved mask FRCNN in cloud environment

The timely and accurate mapping and monitoring of mine tailings dams is crucial to the improvement of management practices by decision makers and to the prevention of disasters caused by failures of these dams. Due to the complex topography, varying geomorphological characteristics, and the diversity of ore types and mining activities, as well as the range of scales and production processes involved, as they appear in remote sensing imagery, tailings dams vary in terms of their scale, color, shape, and surrounding background. The application of high-resolution satellite imagery for automatic detection of tailings dams at large spatial scales has been barely reported. In this study, a target detection method based on deep learning was developed for identifying the locations of tailings ponds and obtaining their geographical distribution from high-resolution satellite imagery automatically. Training samples were produced based on the characteristics of tailings ponds in satellite images. According to the sample characteristics, the Single Shot Multibox Detector (SSD) model was fine-tuned during model training. The results showed that a detection accuracy of 90.2% and a recall rate of 88.7% could be obtained. Based on the optimized SSD model, 2221 tailing ponds were extracted from Gaofen-1 high resolution imagery in the Jing–Jin–Ji region in northern China. In this region, the majority of tailings ponds are located at high altitudes in remote mountainous areas. At the city level, the tailings ponds were found to be located mainly in Chengde, Tangshan, and Zhangjiakou. The results prove that the deep learning method is very effective at detecting complex land-cover features from remote sensing images.

Several applications of machine learning and artificial intelligence, have acquired importance and come to the fore as a result of recent advances and improvements in these approaches. Autonomous cars are one such application. This is expected to have a significant and revolutionary influence on society. Integration with smart cities, new infrastructure and urban planning with sophisticated cyber-security are some of the current ramifications of self-driving automobiles. The autonomous automobile, often known as self-driving systems or driverless vehicles, is a vehicle that can perceive its surroundings and navigate predetermined routes without human involvement. Cars are on the verge of evolving into autonomous robots, thanks to significant breakthroughs in artificial intelligence and related technologies, and this will have a wide range of socio-economic implications. However, in order for these automobiles to become a reality, they must be endowed with the perception and cognition necessary to deal with high-pressure real-life events and make proper judgments and take appropriate action. The majority of self-driving car technologies are based on computer systems that automate vehicle control parts. From forward-collision warning and antilock brakes to lane-keeping and adaptive drive control, to fully automated driving, these technological components have a wide range of capabilities. A self-driving car combines a wide range of sensors, actuators, and cameras. Recent researches on computer vision and deep learning are used to control autonomous driving systems. For self-driving automobiles, lane-keeping is crucial. This study presents a deep learning approach to obtain the proper steering angle to maintain the robot in the lane. We propose an advanced control for a self-driving robot by using two controllers simultaneously. Convolutional neural networks (CNNs) are employed, to predict the car’ and a proportional-integral-derivative (PID) controller is designed for speed and steering control. This study uses a Raspberry PI based camera to control the robot car.

Object detection with deep learning model has achieved good results in many fields, but in some fields that think highly of data privacy, such as medical care, its applications is greatly limited by data. And Federated Learning allows clients to train a model together, while leaving their data in the local, without sharing with the server or other clients. Using the methods of Federated Learning, such as Federated Averaging(FedAvg), to train models can provide privacy, security benefits. Nonetheless, there is little experiment applying Federated Learning algorithms to train the model with a large number of parameters, such as deep learning object detection model. With non-IID data, the accuracy of object detection model trained by FedAvg reduces significantly, and need more rounds to coverage. In this work, we use Kullback-Leibler divergence(KLD) measure the weights divergence between different model trained with non-IID data. And we propose a useful scheme to improve FedAvg based Abnormal Weights Supression, reducing the influence of the weights divergence caused by non-IID and unbalanced data. As a representative of object detection, we choose Single Shot MultiBox Detector(SSD) as the base model. The results of the experiments show that the Mean Average Precision(mAP) get obvious improvement in Pascal VOC 2007 test dataset.

Object detection plays a crucial role in computer vision applications, ranging from autonomous vehicles to surveillance systems. One-stage object detectors have emerged as a powerful solution by simplifying detection pipelines, enabling real-time performance while maintaining competitive accuracy. This article provides a comprehensive survey of one-stage obj ect detection models, including you only look once (YOLO), single shot multibox detector (SSD), and PaddlePaddle YOLO (PP-YOLO) variants. A central question guides this exploration: How can incremental architectural refinements and training strategies improve the trade-off between speed, accuracy, and computational efficiency in object detection models for real-time applications? Through a detailed analysis of key innovations, performance metrics, and practical applications, this survey highlights the evolution of these models and their contributions to bridging the gap between research and deployment. Additionally, the paper identifies current challenges, such as small-object detection and resource efficiency, and proposes future research directions to advance the field further.

With the development of the new generation communication system in China, the application of intelligent transportation system is more extensive, which brings higher demands for vehicle flow detection and monitoring. Traditional traffic flow detection modes often cannot meet the high statistical accuracy requirement and high-speed detection simultaneously. Therefore, an improved Inception module is integrated into the single shot multi box detector algorithm. An intelligent vehicle flow detection model is constructed based on the improved single shot multi box detector algorithm. According to the findings, the convergence speed of the improved algorithm was the fastest. When the test sample was the entire test set, the accuracy and precision values of the improved method were 93.6% and 96.0%, respectively, which were higher than all comparison target detection algorithms. The experimental results of traffic flow statistics showed that the model had the highest statistical accuracy, which converged during the training phase. During the testing phase, except for manual statistics, all methods had the lowest statistical accuracy on motorcycles. The average accuracy and precision of the designed model for various types of images were 96.9% and 96.8%, respectively. The calculation speed of this intelligent model was not significantly improved compared to the other two intelligent models, but it was significantly higher than manual monitoring methods. Two experimental data demonstrate that the intelligent vehicle flow detection model designed in this study has higher detection accuracy. The calculation speed has no significant difference compared with the traditional method, which is helpful to the traffic flow management in intelligent transportation system.

After research, we find that the inner wheel difference has caused a large number of traffic accidents, and its harm cannot be ignored. In order to reduce traffic accidents, an Arduino-based warning device for inner wheel difference is designed in this paper. We first analyze the calculation model of inner wheel difference, then design and assemble each module separately based on the Arduino. In the visual warning part, the Single Shot MultiBox Detector (SSD) object detection model is used to locate and identify pedestrians and common objects, in order to realize a device for alerting both drivers and pedestrians based on vision and ultrasonic wave. Finally, based on the characteristics of the warning device and the social development, we analyze the advantages, technical feasibility and development prospects of the device.

Recent breakthroughs in artificial intelligence (AI) research include advancements in natural language processing (NLP) achieved by large language models (LLMs), and; in particular, generative pre–trained transformer (GPT) architectures. The latest GPT developed by OpenAI, GPT–4, has shown remarkable intelligence across various domains and tasks. It exhibits capabilities in abstraction, comprehension, vision, computer coding, mathematics, and more, suggesting it to be a significant step towards artificial general intelligence (AGI), a level of AI that possesses capabilities similar to human intelligence. This paper explores this AGI, its knowledge diffusive and societal influences, and its governance. In addition to coverage of the major associated topics studied in the literature, and making up for their loopholes, we scrutinize how GPT-4 can facilitate the diffusion of knowledge across different areas of science by promoting their interpretability and explainability (IE) to inexperts. Where applicable, the topics are also accompanied by their specific potential implications on medical imaging.

Intraoperative rapid diagnosis with pathological classification by pathologists plays a pivotal role in making appropriate surgical decisions.However, morphological evaluation of intraoperative frozen sections is apparently more difficult than that of formalin fixed paraffin embedded (FFPE) tissue because of their unavoidable tissueprocessing artifacts, which compels pathologists, even well-trained, more challenging to make an accurate diagnosis.Therefore, assisting the pathological diagnosis with artificial intelligence is anticipated.Here, we built the data set consisting of histopathological micrographs of intraoperative frozen sections and demonstrated an automatic breast carcinoma detection model based on a Single Shot Multibox Detector, an object detection method known for real-time, high-speed performance.The final 3-class classification model was trained on 943 intraoperative frozen section images and evaluated using 65 images, identifying benign lesions, non-invasive carcinoma, and invasive carcinoma.The 2-class (benign or malignant) and 3-class classification tasks achieved diagnostic accuracies for whole image of 92.3% and 89.2%, respectively.When we evaluated the performance of object detection in the 2-class task, the precision, recall and F1 scores for malignant detection are 70.3%, 74.4%, and 72.3%, respectively.Additionally, the model's object detection performance was assessed using FFPE images, yielding a precision of 55.1%, a sensitivity of 76.9%, and an F1 score of 64.2%, suggesting that it is particularly well-suited for intraoperative frozen sections.In conclusion, we presented the automatic breast carcinoma detection method, utilizing histopathological micrographs of intraoperative frozen sections.The present model may assist pathologists by reducing their workload and minimizing the risk of overlooking carcinoma cells in intraoperative diagnosis.