斯坦福大学-源地址： CS231A: Computer Vision, From 3D Reconstruction to Recognition

CS231AGitHub笔记：https://github.com/kenjihata/cs231a-notes

代码和笔记：https://github.com/chizhang529/cs231a

作业答案：https://github.com/zyxrrr/cs231a

CSDN笔记博客：https://blog.csdn.net/qq_40166295/article/details/104031016

 

目录

1. 课程简介

2. 课程要求

Prerequisites

先决条件

3. 课程总览

---

1. 课程简介

An introduction to the concepts and applications in computer vision. Topics include: cameras and projection models, low-level image processing methods such as filtering and edge detection; mid-level vision topics such as segmentation and clustering; shape reconstruction from stereo, as well as high-level vision tasks such as object recognition, scene recognition, face detection and human motion categorization. Prerequisites: linear algebra, basic probability and statistics. 

计算机视觉的概念及应用介绍。主题包括: 相机与投影模型、低层图像处理方法如过滤与边缘检测、中层视觉主题如分割与聚类、立体形状重建，以及高层视觉任务如目标识别、场景识别、人脸检测与人体运动分类。先修条件: 线性代数，基本概率统计。

2. 课程要求

Prerequisites

先决条件

• Proficiency in Python, high-level familiarity in C/C++ 熟练掌握 Python 语言，高度熟悉 c/c + +
  All class assignments will be in Python (and use numpy) (CS231N provides a very nice tutorial 所有的类分配都将使用 Python (并使用 numpy)(CS231N 提供了一个非常好的教程here 这里 for those who aren't as familiar with Python), but some of the deep learning libraries that you may want to use for your projects are written in C++. If you have a lot of programming experience but in a different language (e.g. C/C++/Matlab/Javascript) you will probably be fine. 对于那些不太熟悉 Python 的人) ，但是一些深度学习库是用 c + + 编写的，你可能想用它们来完成你的项目。如果你有丰富的编程经验，但使用不同的语言(例如 c/c + +/Matlab/Javascript) ，你可能会做得很好
• College Calculus, Linear Algebra 大学微积分，线性代数 (e.g. MATH 19 or 41, MATH 51) (例如，MATH 19或41，MATH 51)
  You should be comfortable taking derivatives and understanding matrix vector operations and notation. 你应该可以很轻松地计算导数，理解矩阵向量运算和符号
• Basic Probability and Statistics 基本概率统计 (e.g. CS 109 or other stats course) (例如 cs109或其他统计学课程)
  You should know basics of probabilities, gaussian distributions, mean, standard deviation, etc. 你应该知道概率的基本知识，高斯分布，平均值，标准差，等等
• Equivalent knowledge of CS131, CS221, or CS229. 具备 CS131、 CS221或 CS229的相关知识
  You should be familiar with basic machine learning or computer vision techniques. 你应该熟悉基本的机器学习或计算机视觉技术

3. 课程总览

Lecture	Date	Title	Download	Reading	Instructor
1	1/08/2018	Introduction	[slides]		Silvio Savarese
	1/08/2018	Problem Set 0 Released	[pdf] [code]
2	1/10/2018	Camera Models	[slides]	[FP] Ch.1 [HZ] Ch.6	Silvio Savarese
	1/10/2018	Problem Set 1 Released	[pdf] [code]
TA 1	1/12/2018	Python Introduction and Linear Algebra Review	[slides]	Any linear algebra textbook [HZ] ch.2,4	Kuan Fang
	1/15/2018	Martin Luther King Jr. Day (No class)
3	1/17/2018	Camera Models II and Camera Calibration	[slides]	[FP] Ch.1 [HZ] Ch.7	Silvio Savarese
	1/17/2018	Problem Set 0 Due : 11:59PM
TA 2	1/19/2018	Problem Set 1 Review	[slides]		Danfei Xu
4	1/22/2018	Single View Metrology	[slides]	[HZ] Ch.2,3,8 [Hoiem & Savarese] Ch.2	Silvio Savarese
5	1/24/2018	Epipolar Geometry	[slides]	[HZ] Ch.4,9,11 [FP] Ch.7,8	Silvio Savarese
	1/26/2018	Problem Set 2 Released	[pdf][code]
	1/26/2018	Problem Set 1 Due: 11:59PM
TA 3	1/26/2018	Course Project Outline	[slides]		Amir Sadeghian
6	1/29/2018	Stereo Systems	[slides]	[HZ] Ch.9, 18 [FP] Ch.7,8	Silvio Savarese
7	1/31/2018	Structure from Motion	[slides]	[HZ] Ch.10,18,19 [FP] Ch.13 [Szelisky] Ch.7	Silvio Savarese
	2/01/2018	Project Proposal Due: 11:59PM
TA 4	2/02/2018	Problem Set 2 Review	[slides]		Fei Xia
8	2/05/2018	Fitting and Matching	[slides]	[HZ] Ch.4,11 [FP] Ch.10	Animesh Garg
9	2/07/2018	Detectors and Descriptors	[slides]		Marynel Vazquez
TA 5	2/09/2018	Computer Vision Libraries	[slides]		Amir Sadeghian
	2/09/2018	Problem Set 2 Due: 11:59PM
	2/09/2018	Problem Set 3 Released	[pdf] [code]
10	2/12/2018	Active Stereo & Volumetric Stereo	[slides]	[Szelisky] Ch.11 [Savarese et al.] [Seitz et al.]	Silvio Savarese
11	2/14/2018	Introduction to Recognition : Image Classification	[slides]	[FP] Ch.6,16 [Hosang et. al.]	Silvio Saverese
TA 6	2/16/2018	Problem Set 3 Review	[slides]		Kuan Fang
	2/19/2018	Presidents' Day (No class)
12	2/21/2018	Image Classification & 2D Object Detection	[slides]		Silvio Savarese
TA 7	2/23/2018	Introduction to Convolutional Neural Networks	[slides]		Julian Gao
13	2/26/2018	2D Scene Understanding	[slides]		Christopher B. Choy
	2/26/2018	Project Milestone Due: 11:59PM
	2/28/2018	Problem Set 3 Due: 11:59PM
14	2/28/2018	3D Object Detection	[slides]		Silvio Savarese
	3/01/2018	Problem Set 4 Released	[pdf][code]
TA 8	3/02/2018	Midterm Review	[slides]		Fei Xia
	3/05/2018	Midterm	[midterm 2017][midterm 2017 with solution]	The midterm is open book and open note. No electronics will be allowed. The midterm will be held in class (Skilling Auditorium)
15	3/07/2018	Learning Visual Representations by Neural Networks	[slides]		Amir Zamir
TA 9	3/09/2018	Problem Set 4 Review	[slides]		Danfei Xu
16	3/12/2018	3D Scene Understanding	[slides]		Silvio Savarese
	3/14/2018	No class due to ECCV deadline
TA 10	3/16/2018	Final Project Presentation Guidelines	[slides]		Kuan Fang
	3/17/2018	Problem Set 4 Due: 11:59PM
	3/19/2018	Project Presentations		12:30pm - 2:30pm, Room 1: Oshman 125 map Room 2: 450 Serra Mall, 300-300 map
	3/22/2018	Project Final Report Due: 11:59PM