|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/yolov8-the-ultimate-course-for-object-detection-tracking/
课程评论：没有评论
课程名称：YOLOv8与YOLO11：定制目标检测与Web应用（2025） 课程概述： YOLOv8和YOLO11是Ultralytics最新推出的先进目标检测模型，这些模型在速度和准确性上超越了之前的版本。该课程围绕这两款模型的架构与训练改进，探讨其在多种计算机视觉任务中的应用，包括目标检测、实例分割、图像分类、姿态估计和定向目标检测。 课程结构： 本课程分为两个部分： 第一部分：YOLOv8 - YOLO简介 - CNN、RCNN、Fast RCNN、Faster RCNN、Mask R-CNN概述 - YOLOv8介绍 - YOLOv8与YOLOv7的比较，重点在车牌检测上 - YOLOv8的运行设置，包括在Windows和Google Colab上的配置 - 数据集准备，包括数据集查找、标注和自动分割 - YOLOv8的训练与微调定制模型，项目包括： - 坑洞检测 - 个人防护装备（PPE）检测 - 笔与书籍检测 - 多目标追踪与Traffic Analysis（车辆计数与速度计算） - YOLOv8的高级应用，如： - 带追踪的分割 - 交通信号灯检测与颜色识别 - 裂缝分割 - 头盔检测与分割 - 自动车辆方向检测与计数 - 人脸检测、性别分类、人员计数与追踪 - 车牌检测与识别 - 目标模糊处理与目标追踪 - 车辆分割、计数和速度估算 - Web集成，利用Flask创建PPE检测的完整Web应用。 第二部分：YOLO11 - YOLO11的最新功能与特点 - 使用YOLO11进行各种任务，包括对象检测、实例分割、姿态估计和图像分类 - 模型性能评估，测试与分析YOLO11的性能 - YOLO11的训练与微调，包括： - 针对PPE检测的自定义数据集 - 坑洞检测的实例分割模型 - 人类活动识别的姿态估计模型 - 植物分类的图像分类模型 - 高级多目标追踪，利用Bot-SORT与ByteTrack算法实现 - 特殊项目，包含使用YOLO11和EasyOCR进行车牌检测与识别 - 利用YOLO11与Flask集成构建Web应用 - 创建Streamlit Web应用进行对象检测。 此课程适合希望深入学习YOLOv8与YOLO11并应用于定制项目与Web开发的学员。
YOLOv8 and YOLO11: Cutting-Edge Object Detection ModelsYOLOv8 and YOLO11 are the latest state-of-the-art object detection models from Ultralytics, surpassing previous versions in both speed and accuracy. These models build upon the advancements of earlier YOLO versions, introducing significant architectural and training improvements, making them versatile tools for a variety of computer vision tasks.The YOLOv8 and YOLO11 models support a wide range of applications, including object detection, instance segmentation, image classification, pose estimation, and oriented object detection (OBB).Course StructureThis course is divided into two parts:Part 1: YOLOv8Introduction to YOLOOverview of CNN, RCNN, Fast RCNN, Faster RCNN, Mask R-CNNIntroduction to YOLOv8Comparison of YOLOv8 and YOLOv7 with a focus on License Plate DetectionRunning YOLOv8Setting up YOLOv8 on WindowsUsing YOLOv8 in Google ColabDataset PreparationHow to find datasetsData annotation, labeling, and automatic dataset splittingTraining YOLOv8Train/ Fine-Tune YOLOv8 Model on a Custom DatasetCustom Projects:Potholes DetectionPersonal Protective Equipment (PPE) DetectionPen and Book DetectionMulti-Object TrackingIntroduction to Multi-Object TrackingImplementing YOLOv8 with the DeepSORT algorithmRunning on Google ColabTraffic Analysis:Vehicle counting and car velocity calculationVehicle entry and exit countingYOLOv8 Segmentation with TrackingAdvanced ApplicationsPotholes SegmentationTraffic Lights Detection and Color RecognitionCracks SegmentationHelmet Detection and SegmentationAutomated Vehicle Direction Detection and CountingFace Detection, Gender Classification, Crowd Counting, and TrackingLicense Plate Detection and Recognition with EasyOCRObject Blurring with Object TrackingVehicle Segmentation, Counting, and Speed EstimationWeb IntegrationIntegrating YOLOv8 with FlaskCreating a Complete Web App for PPE DetectionPart 2: YOLO11What's New in YOLO11Key updates and features in Ultralytics YOLO11Using YOLO11 for Various TasksObject Detection, Instance Segmentation, Pose Estimation, and Image Classification on Windows/Linux.Model Performance EvaluationTesting and analyzing YOLO11 performanceTraining YOLO11Train/ Fine-Tune YOLO11 Object Detection Model on a Custom Dataset for Personal Protective Equipment Detection.Train/ Fine-Tune YOLO11 Instance Segmentation Model on a Custom Dataset for Potholes Detection.Fine-Tune YOLO11 Pose Estimation Model on a Custom Dataset for Human Activity Recognition.Train/ Fine-Tune YOLO11 Image Classification Model on a Custom Dataset for Plant Classification.Advanced Multi-Object TrackingImplementing Multi-Object tracking with Bot-SORT and ByteTrack algorithmsSpecialized ProjectsLicense Plate Detection & Recognition with YOLO11 and EasyOCRCar and License Plate Detection & Recognition with YOLO11 and PaddleOCRWeb Integration with YOLO11Integrating YOLO11 with Flask to build a web appCreating a Streamlit Web App for object detection
