|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/yolov9-learn-object-detection-tracking-with-webapps/
课程评论：没有评论
课程名称：YOLOv9, YOLOv10 & YOLO11：学习物体检测与网络应用 课程概述：欢迎参加YOLOv9, YOLOv10 & YOLO11课程，这是一个三合一的课程，涵盖计算机视觉物体检测模型的最新进展。课程首先介绍计算机视觉的基础知识，包括非最大抑制（Non-Maximum Suppression）和平均精度均值（Mean Average Precision）。接下来，我们深入探讨YOLOv9，学习其架构并突出其优于其他物体检测模型的特点。在第四部分，我们演示使用YOLOv9在图像和视频上进行物体检测，并评估其在多个参数下的性能。随后，在第五部分，我们在自定义数据集上训练YOLOv9模型，进行个人防护设备（PPE）检测。此外，第六部分专注于物体跟踪，我们将YOLOv9与DeepSORT和SORT算法集成，并开发一个使用YOLOv9和DeepSORT算法进行人员/车辆计数的应用程序。第七部分回顾YOLO-World，并逐步指导如何使用YOLO-World执行物体检测。最后，第八部分中，我们将YOLOv9与Flask整合，创建网络应用。 第九部分介绍YOLOv10，包括YOLOv10的工作原理及其架构增强，此外还进行YOLOv10与其他YOLO模型的性能比较。在第十部分，我们演示如何使用YOLOv10在图像和视频上进行物体检测。随后在第十一部分，我们在自定义数据集上训练YOLOv10模型进行个人防护设备（PPE）检测。在第十二部分，我们使用YOLOv10和PaddleOCR进行车牌检测和识别。类似地，在第十三部分，我们展示使用YOLOv10和DeepSORT算法进行实时物体跟踪。 第十四部分介绍YOLO11。在第十五部分，我们演示如何使用YOLO11在图像和视频上进行物体检测。在第十六部分，我们使用YOLO11在Windows和Linux上进行物体检测、实例分割、姿态估计和图像分类。随后，在第十七部分，我们深入测试和分析YOLO11模型的性能。在第十八部分，我们探索在自定义数据集上训练YOLO11物体检测模型进行PPE检测。在第十九部分，我们专注于训练或微调YOLO11实例分割模型在自定义数据集中进行坑洞检测。在第二十部分，我们训练或微调YOLO11分类模型在自定义数据集中进行植物分类。最后，在第二十一部分，我们微调YOLO11姿态估计模型用于人类活动识别。 本课程涵盖的内容包括： - 平均精度均值（mAP） - 非最大抑制（NMS） - YOLOv9架构 - 使用YOLOv9进行物体检测 - 在图像、视频和实时网络摄像头上测试YOLOv9模型性能 - 在自定义数据集上训练YOLOv9 - 使用YOLOv9进行个人防护设备（PPE）检测 - 使用YOLOv9和DeepSORT进行物体跟踪 - 使用YOLOv9和SORT进行物体跟踪 - 使用YOLOv9和DeepSORT算法进行人员/车辆计数 - YOLO-World简介 - 使用YOLO-World在图像和视频上进行物体检测 - 将YOLOv9与Flask整合，创建网络应用 - 浏览器中使用YOLOv9进行物体检测 - YOLOv10简介及架构深入分析 - 使用YOLOv10在图像和视频上进行物体检测 - 在自定义数据集上训练/微调YOLOv10模型进行个人防护设备（PPE）检测 - 使用YOLOv10和PaddleOCR进行车牌检测和识别 - 使用YOLOv10和DeepSORT算法进行实时物体跟踪 - YOLO11简介 - 使用YOLO11进行物体检测、实例分割、姿态估计和图像分类 - 评估YOLO11模型性能：测试和分析 - 在自定义数据集上微调YOLO11物体检测模型进行PPE检测 - 在自定义数据集上使用YOLO11进行坑洞检测的实例分割 - 微调YOLO11图像分类模型进行植物分类 - 使用YOLO11进行人类活动识别的姿态估计模型微调。
Welcome to the YOLOv9, YOLOv10 & YOLO11 Course, a 3-in-1 course. YOLO11, YOLOv10 & YOLOv9 represent the latest advancements in computer vision object detection models. This course begins by covering the fundamentals of computer vision, including Non-Maximum Suppression and Mean Average Precision. Moving forward, we delve deeply into YOLOv9, exploring its architecture and highlighting how it surpasses other object detection models. In Section 04, we demonstrate object detection on images and videos using YOLOv9, evaluating its performance across various parameters.Subsequently, in Section 05, we train the YOLOv9 model on a custom dataset for Personal Protective Equipment (PPE) detection. Additionally, Section 06 focuses on object tracking, where we integrate YOLOv9 with the DeepSORT & SORT algorithms. Here, we also develop an application for person/vehicle counting (entry and exit) using YOLOv9 and the DeepSORT algorithm.Section 07 provides a review of YOLO-World and a step by step guide to perform object detection using YOLO-World. Finally, in Section 08, we will create web applications by integrating YOLOv9 with Flask.Section 09, provides an introduction to YOLOv10, which includes what is YOLOv10, how YOLOv10 works, what architecture enhancements are made in YOLOv10, furthermore a performance comparison of YOLOv10 with other YOLO models is also presented in this section.In Section 10, we demonstrate object detection in images and videos using YOLOv10. Subsequently, in Section 11, we train the YOLOv10 model on a custom dataset for Personal Protective Equipment (PPE) detection. In Section 12, we perform License Plate Detection and Recognition using YOLOv10 and PaddleOCR. Similarly, in Section 13, we showcase Real-Time Object Tracking using YOLOv10 and the DeepSORT algorithm.Section 14 introduces YOLO11. In Section 15, we demonstrate object detection in images and videos using YOLO11. In Section 16, we perform object detection, instance segmentation, pose estimation, and image classification using YOLO11 on both Windows and Linux. Subsequently, in Section 17, we delve into testing and analyzing the performance of the YOLO11 model.In Section 18, we explore training the YOLO11 object detection model on a custom dataset for PPE detection. In Section 19, we focus on training or fine-tuning the YOLO11 instance segmentation model on a custom dataset for pothole detection. In Section 20, we train or fine-tune the YOLO11 classification model on a custom dataset for plant classification. Finally, in Section 21, we fine-tune the YOLO11 pose estimation model for human activity recognition.This comprehensive course covers a range of topics, including:Mean Average Precision (mAP).Non Maximum Suppression (NMS).What is YOLOv9 Architecture of YOLOv9.Object Detection using YOLOv9.Testing YOLOv9 Model Performance on Images, Videos and on the Live Webcam Feed. Training YOLOv9 on a Custom Dataset.Personal Protective Equipment (PPE) Detection using YOLOv9.Object Tracking using YOLOv9 and DeepSORT.Object Tracking using YOLOv9 and SORT.Person/ Vehicles Counting (Entering and Leaving) using YOLOv9 and DeepSORT algorithm.Introduction to YOLO-World.Object Detection on Images and Videos using YOLO-World.Integrating YOLOv9 with Flask and Creating Web Apps.Object Detection in the Browser using YOLOv9 and FlaskWhat is YOLOv10? An architecture deep diveObject Detection in Images and Videos using YOLOv10Training/ fine-tuning the YOLOv10 model on custom dataset for Personal Protective Equipment (PPE) DetectionLicense Plate Detection & Recognition with YOLOv10 and PaddleOCRReal-Time Object Tracking using YOLOv10 and DeepSORT AlgorithmIntroduction to YOLO11Object Detection, Instance Segmentation, Pose Estimation & Image Classification using YOLO11Evaluating YOLO11 Model Performance: Testing and AnalysisFine-Tune YOLO11 Object Detection Model on Custom Dataset for PPE DetectionInstance Segmentation using YOLO11 on a Custom Dataset for Potholes DetectionFine-Tune YOLO11 Image Classification Model for Plants ClassificationHuman Activity Recognition with YOLO11: Fine-Tune YOLO11 Pose Estimation Model
