인프런 영문 브랜드 로고
인프런 영문 브랜드 로고
AI

/

Computer Vision

Computer Vision All-in-One: 10 Real-World Projects in 12 Hours

Easy to learn and use right away: Computer Vision Practical Project: Learn computer vision projects that can be used right away in practice, step by step. Increase your expertise through practical cases.

(2.8) 4 reviews

33 students

Python
OpenCV
Deep Learning(DL)
Machine Learning(ML)
yolo

This course is prepared for Basic Learners.

What you will learn!

  • Image and Video Processing with OpenCV: Learn from basic image preprocessing to advanced image analysis.

  • Object Detection Detect objects accurately with the latest model: apples, vehicles, people, and more.

  • Real-time Face Recognition and Emotion Analysis: Detect faces and analyze emotions in real-time.

  • Sports motion and posture analysis: Track and visualize the position and movement of athletes.

  • Road Traffic Sign Recognition: Learn the traffic sign and traffic light detection technology needed for autonomous vehicles.

  • Store Traffic and Customer Behavior Analytics: Analyze customer path and behavior data to optimize the retail environment.

  • Pose Estimation and Action Recognition: Accurately estimate hand gestures and 2D/3D poses with Mediapipe.

  • Deep Learning Model Design and Training: Implement and train custom AI models using TensorFlow and PyTorch.

  • Segmentation techniques: Separate objects and remove background with UNet.

Computer Vision in Practice: From Theory to Project 👍

Learn computer vision and deep learning systematically with an 'L'-shaped learning structure that can be applied directly to practice. From basic theories to advanced techniques, you can acquire all the capabilities needed in the field through practical projects. Open the path to becoming an AI expert with 10 practical projects using Python, OpenCV, and deep learning.

💡 L-shaped learning structure: from theory to practice

This course is designed to systematically learn from the basics of computer vision to practical projects through an innovative 'L-shaped learning structure'. This structure is organized around two axes:

Vertical Axis: Basic Concepts and Practice

  • Python and OpenCV Basics : Learn step-by-step from the basics of programming to the core of image processing

  • Deep Learning and Computer Vision Theory : Understanding the core concepts of AI technology that underlies computer vision

  • Step-by-step practice : A systematic practical course that allows you to apply the theory right away.

Horizontal axis: Practical projects

  • 10 different projects : Perform projects that apply technologies used in real industrial settings.

  • Build your portfolio : Complete projects that can be used immediately for employment and practice

  • Solve real-world problems : Learn how to apply AI technologies to real-world data and environments.

Beyond simply imparting skills, this course demonstrates how to apply computer vision in real-world settings. The L-shaped learning structure integrates theory and practical experience, providing a foundation for learners to grow into AI developers. Enroll now and expand the possibilities of computer vision!

10 Real-World Projects: Experience the Core of Computer Vision! ✌

In addition to the six projects introduced below, this course offers many more exciting and practical projects. You will be able to further enhance your computer vision skills through projects applicable to various fields such as product defect inspection, real-time facial emotion analysis, abnormal behavior detection, and disaster prevention.

Going beyond theory and solving real-world problems will greatly enhance your capabilities as an AI developer.

Sports Project

Real-time soccer object detection and tracking

Autonomous driving sign recognition project

Stop sign detection and save CSV information

Traffic Analysis Project

Vehicle Detection and Tracking Using DeepSORT

Motion Recognition Project

Landmark Analysis and Gesture Classification (Rock Paper Scissors Game)

Customer Analysis Project

Escalator Object Tracking Real-Time Analysis

Access Control Project

Person identification using facial recognition

Computer Vision: A New World of Vision Opened by AI 🤔

Computer vision technology is revolutionizing our daily lives. This field of AI is moving beyond simply viewing images to understanding and interpreting the world around us.

Computer Vision in Our Lives

Computer vision is already being used in a variety of fields:

  • Smartphone Face Recognition Unlock

  • Road situation recognition for autonomous vehicles

  • Diagnosing diseases through medical imaging

  • Detection of defects in manufacturing processes

The potential of future technologies

Changes we will experience in the future:

  • Fully autonomous car

  • Smart devices that provide information through cameras

  • AI-based early disease detection system

AI is moving beyond image processing to understanding and creating images.

Life-Changing Technology

Computer vision is a revolutionary tool that has the potential to fundamentally change our lives and work. For example, personalized exercise coaching through 3D motion analysis or AI-based professional video production tools will become possible. The future of computer vision is full of infinite possibilities. Learning and utilizing this technology will be a smart choice to prepare for the future.

Why this course? 😊

📌 A composition that even beginners can follow

  • Even if you are new to deep learning and computer vision, it's okay.

  • We explain complex concepts in a friendly, easy-to-understand manner.

  • A friendly explanation of Python grammar and OpenCV basics.

📌 Practical lectures

  • We don't just focus on theory, we practice in real time using actual data.

  • Examples: facial recognition projects, defect detection projects, motion tracking projects.

📌 Reflecting the latest technology

  • We cover cutting-edge tools and techniques such as YOLO, U-Net, and Mediapipe.

  • We will systematically introduce technologies that will be continuously updated in the future.

💡 An environment where you can practice anywhere: Learning cloud AI with Google Colab

Our computer vision course using Google Colab completely breaks down the barriers to learning.

Now you can learn cutting-edge AI technologies without complex setups or expensive equipment.

  • Zero stress on setup : All code runs in Colab, so no need to worry about installation errors.

  • Ready-to-run hands-on materials : Get results and improve your skills right away with the code provided.

  • Supports various devices : laptops, desktops, tablets, etc. All you need is an internet connection

I recommend this to these people 😎

I want to learn CV basics.

Beginner learners who are new to tools like OpenCV, YOLO, and Mediapipe, or who want to learn the fundamentals of computer vision.

I would like to try out CV skills.

Anyone who wants to know how technologies like object detection, hand gesture recognition, and face recognition are used in real-world projects.


I want to gain practical experience in CV writing.

Those who want to develop practical skills through real-world problem-solving projects such as sports analysis, autonomous driving, and factory automation.

💡 This course is optimized for:

In this course, you will learn everything about computer vision from A to Z, from basic theory to practical projects. Start learning computer vision, the core of future technology, now!

  • Computer Vision Beginner

    • For those who are new to core tools such as OpenCV and YOLO

    • Those who want to systematically learn the basic principles of image processing

    • "I want to know how computers 'understand' images"

  • Learners who want hands-on project experience

    • For those who want to implement real models such as face recognition and object detection

    • Anyone who wants to bridge the gap between theory and practical application

    • "I want to apply what I've learned to solving real-world problems."

  • Aspiring Developers Preparing for Employment

    • Job seekers who need hands-on project experience

    • Anyone who wants to add a real project to their portfolio

    • "I need a real-world project that will captivate the interviewer."

  • Professionals interested in AI applications across industries

    • Anyone who wants to apply computer vision technology to their field

    • Anyone who wants to learn about AI use cases in various industries

    • “How can it apply to our company/industry?”

  • People interested in AI and deep learning

    • Anyone who wants to understand the principles of image-based AI technology

    • Anyone who wants to learn how deep learning processes visual data

    • "I wonder how AI 'sees' and judges images"

  • For those looking for a systematic learning path

    • Those who feel the limitations of self-study

    • Those who want to learn from basic theory to practical application in one stop

    • "I want to systematically master everything from basics to advanced techniques."

💡 After taking the course, it is your future.

This course will help you become a computer vision expert. It introduces the core competencies and opportunities you will gain after taking the course.

  • Master the core computer vision technologies

    • Skillful use of industry standard tools such as OpenCV, YOLO, and Mediapipe

    • Understanding and implementing core technology principles from image preprocessing to object detection and pose estimation

  • Gain practical experience through real-world projects

    • Carry out various projects based on real data

      Developing advanced solutions leveraging the synergy of computer vision and deep learning

    • Learn practical optimization and application methods for the latest technologies such as YOLO and Mediapipe.

    • Improve your ability to develop solutions by applying theory to real-world problems

  • Building a strong portfolio for employment

    • Completed practical projects such as "Soccer Match Analysis", "Traffic Sign Detection", and "Safety Equipment Wear Detection"

    • Create a differentiated portfolio that catches the interviewer's eye

  • Gain practical, actionable skills that you can apply immediately

    • Ability to design and prototype computer vision-based solutions

    • Know-how applied to various industries such as sports, retail, and logistics

  • Strengthening AI and deep learning convergence capabilities

    • Developing advanced solutions leveraging the synergy of computer vision and deep learning

    • Learn practical optimization and application methods for the latest technologies such as YOLO and Mediapipe.

  • Laying the foundation for career growth

    • Ready for employment in machine learning, deep learning, and data analysis

    • Building a differentiated career based on practical project experience

Things to note before taking the class 🙌

Where can I find the study materials?

  • Section 1. ‘Lecture Preparation’ -> ‘Lecture Materials’ are provided, so please make good use of them after attending the class.

Are the lecture contents updated?

  • Of course, we will develop the content based on technological advancements and your valuable opinions.

Recommended for
these people!

Who is this course right for?

  • From beginners interested in AI and deep learning to developers who want hands-on projects

  • Those who want to strengthen their portfolio by utilizing computer vision technology

  • Practitioners who want to develop deep learning models that can be used immediately in the workplace

  • Those who want to start a new career with artificial intelligence and computer vision

Need to know before starting?

  • Basic IT environment usage experience

  • Passion to learn

Hello
This is

21,807

Students

434

Reviews

556

Answers

4.3

Rating

25

Courses

"노마드크리에이터: 당신의 꿈, 우리의 여정"

대한민국과 NVIDIA가 인정한 딥테크, 싱가포르가 선택한 핀테크 스타트업, 글로벌 무대에서 당신의 가능성을 실현합니다.

노마드크리에이터는 개인의 성장을 넘어, 스타트업으로 도약하며 전 세계를 무대로 전문적인 IT 강의를 제공하고 있습니다.
2019년, 싱가포르 정부의 Entrepass Innovator 프로그램을 통해 시작된 우리의 여정은 곧 혁신적인 스타트업의 이야기로 확장되었습니다.
2020년에는 대한민국에서 인공지능 핀테크 솔루션을 개발하며 딥테크 분야의 선두주자로 자리매김했고, NVIDIA 협업 프로그램 최우수 프로젝트와 ASUS Global Startup Challenge Award를 포함한 다양한 글로벌 인정과 성과를 이뤘습니다.
2023년에는 NVIDIA의 지원으로 미국에 회사를 설립하며 글로벌 시장을 향한 도약을 시작했습니다.

image.png

경험을 넘어, 비전을 공유합니다.

스타트업 창업 이전, LG CNS와 티머니 등에서 25년간 System Engineer, Project Manager, IT Consultant로서 글로벌 프로젝트를 이끌며 실전 경험과 전문성을 쌓았습니다.
PMP, SAP BW, SCJP, MCSE+DBA, OCP-DBA와 같은 전문 자격을 기반으로, 프로그램 개발, 프로젝트 관리, IT 솔루션 설계 등 다양한 분야에서 성공적인 도전을 이어왔습니다.

이제, 노마드크리에이터는 이러한 경험과 노하우를 집약하여 누구나 쉽고 재미있게 배울 수 있는 교육 콘텐츠를 제공합니다. 실무 중심의 강의부터 최신 기술 트렌드를 반영한 전문 과정까지, 개인의 성장을 위한 맞춤형 학습을 제안합니다.

우리의 미션: "꿈을 현실로, 도전을 기회로"

기술과 교육의 융합으로 더 많은 사람들이 자신만의 가능성을 실현하도록 돕습니다.

노마드크리에이터와 함께라면, 당신의 꿈은 더 이상 멀리 있지 않습니다.

지금 이 순간에도 누군가는 새로운 것을 배우고, 더 나은 자신이 되기 위해 노력하고 있습니다.

하지만 정보의 홍수 속에서 필요한 지식을 찾는 데 소중한 시간을 잃는 일이 얼마나 많습니까?

노마드크리에이터는 이 문제를 해결하고자 합니다.

우리는 지식을 창의적으로 엮어내어, 시간을 아끼고, 가치를 극대화하는 경험을 제공합니다. 우리의 목표는 단순한 정보 전달을 넘어, 지식을 작품처럼 아름답게 전달하는 것입니다.

노마드크리에이터와 함께라면, 당신의 배움은 더 쉽고, 빠르며, 가치 있는 결과를 만들어낼 것입니다.

"배움의 여정에 가치를 더하다, 노마드크리에이터."

이것이 우리가 꿈꾸는 미래입니다.

Curriculum

All

65 lectures ∙ (10hr 56min)

Course Materials:

Lecture resources
Published: 
Last updated: 

Reviews

Not enough reviews.
Become the author of a review that helps everyone!