完整计算机视觉实战课：从YOLO到多模态AI

这是一门名为《完整计算机视觉实战课：从YOLO到多模态AI》的综合性课程，旨在带学员从YOLO11基础入门，逐步掌握目标检测、分割、姿态估计等核心任务，并拓展至多模态AI应用的构建。课程通过Google Colab实践YOLO11的各项功能，包括生成分析图表、结合DeepSORT实现物体进出计数，并教您用Streamlit搭建交互式应用。进阶部分涵盖使用SAHI优化无人机影像中的小目标检测、通过Depth Pro估算真实距离，以及运用Qwen2.5-VL、Florence 2和Google Gemini 2.5等前沿模型进行零样本检测、图像描述与OCR。学员需具备Python基础，最终将获得解决实际计算机视觉问题的全方位实战能力。
由 Muhammad Moin 创建
MP4 | 视频：h264、1280×720 | 音频：AAC，44.1 KHz，2 声道
级别：全部 | 类型：电子学习 | 语言：英语 | 时长：10 讲（4 小时 13 分钟）| 大小：4.8 GB

Complete Computer Vision Bootcamp: YOLO to Multimodal AI。Build practical applications with YOLO, DeepSORT, Streamlit, and state-of-the-art vision-language models。This course takes you from the basics of YOLO11 to advanced computer vision applications. You’ll explore object detection, segmentation, pose estimation, and image classification, while also learning to create analytical graphs and track object movements. Beyond YOLO11, you’ll build real-world projects with Streamlit, enhance detection with SAHI, estimate distances with Depth Pro, and explore cutting-edge multimodal AI models like Qwen2.5-VL, Florence 2, and Google Gemini 2.5. By the end, you’ll have hands-on experience with modern tools to solve practical computer vision challenges.What You Will Learn:Getting Started with YOLO11:YOLO11 Updates and New FeaturesImplementing YOLO11 in Google Colab:YOLO11 for Object Detection, Segmentation, Pose Estimation & ClassificationCreating Analytical Graphs and Visualizing Data with YOLO11:How to Generate Analytical Graphs with YOLO11Counting Object Entries and Exits using YOLO11 and DeepSORT:Tracking Objects with YOLO11 and DeepSORT for Entry–Exit CountsStreamlit Application: Object Detection, Segmentation & Pose Estimation:Building a Streamlit App for Object Detection, Segmentation, and Pose EstimationUsing Ultralytics YOLO11 with SAHI for Object Detection in Drone Footage:YOLO11 + SAHI = Better Detection for Small Objects! (Step-by-Step Guide)Estimate Real Distance to Objects with ML Depth Pro and YOLO11:Learn how to estimate real distances to objects using Depth Pro and YOLO11.Performing Zero-Shot Object Detection with Qwen2.5-VL:Zero-Shot Object Detection Using Qwen2.5-VLRun Vision Tasks: Object Detection, Image Captioning & OCR with Florence 2:How to use Florence 2 for Object Detection, Image Captioning and OCRGoogle Gemini 2.5 Pro: Detect Objects, Generate Captions & OCR:How to do Object Detection, Image Captioning, Reasoning and OCR with Gemini-2.5。What you’ll learn
Getting Started with YOLO11
YOLO11 Implementation | Google Colab
Creating Analytical Graphs and Visualizing Data with YOLO11
Counting Object Entries and Exits using YOLO11 and DeepSORT
Streamlit Application: Object Detection, Segmentation & Pose Estimation
Using Ultralytics YOLO11 with SAHI for Object Detection in Drone Footage
Estimate Real Distance to Objects with ML Depth Pro and YOLO11
Performing Zero-Shot Object Detection with Qwen2.5-VL
Run Vision Tasks: Object Detection, Image Captioning & OCR with Florence 2
Google Gemini 2.5 Pro: Detect Objects, Generate Captions & OCR

Requirements
Basic knowledge of Python programming