基于Python和OpenCV的目标跟踪学习教程 Object Tracking using Python and OpenCV

实现12种不同的算法来跟踪视频和网络摄像头中的对象！

你会学到:
使用Python和OpenCV跟踪视频和网络摄像头中的对象
理解跟踪算法的基本直觉
实现12种跟踪算法
了解对象检测和对象跟踪之间的区别

要求
程序设计逻辑
基本Python编程

MP4 |视频:h264，1280×720 |音频:AAC，44.1 KHz，2 Ch
语言：英语+中英文字幕（云桥CG资源站 机译） |时长:33节课(4h 44m) |大小解压后:2.33 GB

描述
目标跟踪是计算机视觉的一个子领域，其目标是在视频的连续帧中定位目标。一个应用的例子是视频监控和安全系统，其中可以检测到可疑的行动。其他的例子还有高速公路上交通的监控，以及足球比赛中球员运动的分析！在最后一个例子中，可以追踪球员在比赛中走的完整路线。

为了带您进入这一领域，在本课程中，您将学习使用Python语言和OpenCV库的主要对象跟踪算法！你将学习关于12(十二)种算法的基本直觉，并一步一步地实现它们！在课程结束时，您将知道如何将跟踪算法应用于视频，因此您将能够开发自己的项目。将涵盖以下算法:Boosting、MIL(多实例学习)、KCF(核相关滤波器)、CSRT(具有通道和空间可靠性的鉴别相关滤波器)、MedianFlow、TLD(跟踪学习检测)、MOSSE(最小输出平方和)误差)、Goturn(使用回归网络的通用对象跟踪)、Meanshift、CAMShift(连续自适应Meanshift)、光流稀疏和光流密集。

您将学习所有算法的基本直觉，然后，我们将使用PyCharm IDE实现和测试它们。需要强调的是，课程的目标是尽可能的实用，所以，不要对理论期望太高，因为你将只学习每个算法的基本方面。展示所有这些算法的目的是让你有一个观点，根据应用的类型可以使用不同的算法，所以你可以根据你试图解决的问题选择最好的算法。

这门课是给谁的
刚开始学习计算机视觉和目标跟踪的初学者
正在学习人工智能相关学科的本科生
任何对人工智能或计算机视觉感兴趣的人
希望扩大投资组合的数据科学家

MP4 | Video: h264, 1280×720 | Audio: AAC, 44.1 KHz, 2 Ch
Genre: eLearning | Language: English + srt | Duration: 33 lectures (4h 44m) | Size: 2 GB

Implement 12 different algorithms for tracking objects in videos and webcam!

What you’ll learn:
Track objects from videos and from the webcam using Python and OpenCV
Understand the basic intuition about tracking algorithms
Implement 12 tracking algorithms
Understand the differences between object detection and object tracking

Requirements
Programming logic
Basic Python programming

Description
Object tracking is a subarea of Computer Vision which aims to locate an object in successive frames of a video. An example of application is a video surveillance and security system, in which suspicious actions can be detected. Other examples are the monitoring of traffic on highways and also the analysis of the movement of players in a soccer match! In this last example, it is possible to trace the complete route that the player followed during the match.

To take you to this area, in this course you will learn the main object tracking algorithms using the Python language and the OpenCV library! You will learn the basic intuition about 12 (twelve) algorithms and implement them step by step! At the end of the course you will know how to apply tracking algorithms applied to videos, so you will able to develop your own projects. The following algorithms will be covered: Boosting, MIL (Multiple Instance Learning), KCF (Kernel Correlation Filters), CSRT (Discriminative Correlation Filter with Channel and Spatial Reliability), MedianFlow, TLD (Tracking Learning Detection), MOSSE (Minimum Output Sum of Squared) Error), Goturn (Generic Object Tracking Using Regression Networks), Meanshift, CAMShift (Continuously Adaptive Meanshift), Optical Flow Sparse, and Optical Flow Dense.

You’ll learn the basic intuition about all algorithms and then, we’ll implement and test them using PyCharm IDE. It’s important to emphasize that the goal of the course is to be as practical as possible, so, don’t expect too much from the theory since you are going to learn only the basic aspects of each algorithm. The purpose of showing all these algorithms is for you to have a view that different algorithms can be used according to the types of applications, so you can choose the best ones according to the problem you are trying to solve.

Who this course is for
Beginners who are starting to learn Computer Vision and Object Tracking
Undergraduate students who are studying subjects related to Artificial Intelligence
Anyone interested in Artificial Intelligence or Computer Vision
Data scientists who want to grow their portfolio

云桥CG资源站 为三维动画制作，游戏开发员、影视特效师等CG艺术家提供视频教程素材资源！