Learn OpenCV: Build # 30 Apps with OpenCV, YOLOv8 & YOLO-NAS

In this lecture, we will learn how to read Image, Video and Live Webcam Feed.

In this lecture, we will learn some basic OpenCV functions which include how to

• Convert an Image to GrayScale

• Blur an Image

• Detect the Edges in an Image

• Dilation and Erosion of Images

In this lecture, we will cover how to crop and resize an image using OpenCV

In this lecture, we will cover how to draw shapes on images. We will learn how to draw Lines, Rectangles, Circles on images and we will also learn how to put text on images

In this lecture we will be provided with a card image. We will take the king of spades and we will try to get this as flat as possible. We will need 4 points and using these 4 points we are going to apply the warp perspective.

So, first we need to define 4 corner points of the cards. We will declare points as a numpy array of float and then using these 4 points we will apply Warp Perspective.

In this lecture, we will learn how we can join/stack images together horizontally and vertically using np.vstack and np.hstack.

There are two issues with this method

1. If the images are not of the same size then they cannot be stacked

2. If the images donot have the same number of channels then the stack function will not work, so all the images which we are joining or applying horizontal or vertical should have the same number of channels

In this lecture, we will learn how to detect a specific color in an image using OpenCV. As an example, we will focus on detecting the orange color of a car in the given image.

Contours are defined as the line joining all the points along the boundary of an image that are having the same intensity.

In this lecture, we will first find and draw contours in an image, using the contours we will find the corner points of each of the shape in the image and using these corner points we will draw the bounding boxes around each of the shape and using the length of the corner points we will find whether it is a Circle, Square or Rectangle.

OpenCV provides default cascades that can detect different things such as face, eye, number plates and so on.

Using OpenCV Haar Cascade Classifier, in this lecture we are going to detect the Faces.

Link:

https://github.com/opencv/opencv/tree/master/data/haarcascades

In this lecture, using OpenCV Haar Cascade Classifier we will see how we can detect the Number Plate

In this lecture, we will learn how we can create a Document Scanner using OpenCV

In this lecture, we will learn how we can detect the mouse clicks on an Image. If we click on 4 points on an Image we get the Warp Perspective as the output.

In this lecture, I will be creating an authentication application, where we will check whether the person is authorized or not based on the QR code or Bar code. I will be using the pyzbar library that allows us to detect and localize the Bar codes and QR codes, the great thing about this library is that it will decode the information in the Bar code or QR code and it will also tell the location of the QR code or the Bar code.

In this lecture, we will explore how we can do Lane Detection using OpenCV. We will do the Lane Detection in our defined Region of Interest (ROI). We will apply different image processing techniques in this project.

In this lecture, we will learn how we can measure the size of different objects using OpenCV. We will have a white paper in which we have different objects placed. We will be provided the size of the paper as well which is 297 mm x 210 mm. In the first step, we will extract the paper for this we will use find contours function in OpenCV to find the biggest contour which will be our paper.  After extracting the paper, in the next step, we will apply different image processing techniques, we will find the corner points, we will also reorder the corner points. Using the Euclidean Distance Formula, then we will calculate the height and width of the object on the paper.

In this lecture, we will learn how we can create an Optical Mark Recognition Algorithm in Python using OpenCV

In this lecture, we will learn how we can create an Optical Mark Recognition Algorithm in Python using OpenCV

In this lecture, we will learn how we can create an Optical Mark Recognition Algorithm in Python using OpenCV

In this lecture, we will learn how we can create an Optical Mark Recognition Algorithm in Python using OpenCV

In this lecture, we will learn how we can create an Optical Mark Recognition Algorithm in Python using OpenCV

In this lecture, we will learn how we can create an Optical Mark Recognition Algorithm in Python using OpenCV

In this lecture, we will learn how we can create a Basket Ball Shot Predictor Application using OpenCV Python.

In this lecture, we will create a Parking Space Counter Application, to count the number of free parking slots available.

In this lecture, we will be creating a Pong Game using Hand Gestures. We will be using MediaPipe Library for hand tracking. MediaPipe finds the 21 hand landmarks on the cropped image of the hand.

In this lecture, we will learn how to change the volume of the computer using Gesture Control.  We will first implement  hand tracking using MediaPipe library. MediaPipe finds the 21 hand landmarks on the cropped image of the hand. Then we will use hand landmarks to find the gesture of our hand to change the volume.

In the lecture, the following topics are covered.

1. What is YOLO

2. Image Classification

3. Object Localization

4. Training of a Neural Network

5. Why we need YOLO

6. YOLO Algorithm

In the lecture, the following topics are covered

1. Convolutional Neural Network (CNN)

2. Region Based Convolutional Neural Network (R-CNN)

3. Fast R-CNN

4. Faster R-CNN

5. Mask R-CNN

In the lecture, the following topics are covered

1. What is YOLOv8

2. Key Features of YOLOv8

3. What are the reasons for using YOLOv8

4. Architecture of YOLOv8

In this lecture, we will implement YOLOv8 for Object Detection and Segmentation in Google Colab.  We will test YOLOv8 model on images and videos.

In this lecture, we will learn how we can read and display an image using OpenCV

In this lecture we will learn how we can read and display a video using OpenCV

In this lecture, we will learn how we can read, write and display a video using OpenCV

In this lecture, we will learn how we can capture video from camera using OpenCV

In this lecture, we will learn how we can do Object Detection on images using YOLOv8

In this lecture, we will learn how we can do Object Detection on Videos using YOLOv8

In this lecture, we will see how we can do Object Detection in Real Time with Webcam using YOLOv8

In this lecture, we will be implementing Object Tracking from Scratch using YOLOv8 and OpenCV

In this lecture, we will be implementing Object Tracking from Scratch using YOLOv8 and OpenCV

In this lecture, we will be implementing Object Tracking from Scratch using YOLOv8 and OpenCV

In this lecture, we will be implementing Object Tracking from Scratch using YOLOv8 and OpenCV

In this lecture, we will be implementing Object Tracking from Scratch using YOLOv8 and OpenCV

In this lecture, we will be implementing Object Tracking from Scratch using YOLOv8 and OpenCV

In this lecture, we will learn how we can predict the trajectory of the basket ball using Kalman Filter. We will first detect the Basket Ball using YOLOv8 and then we will predict the trajectory of the Basket Ball using Kalman Filter.

In this lecture, we will learn how we can predict the trajectory of the basket ball using Kalman Filter. We will first detect the Basket Ball using YOLOv8 and then we will predict the trajectory of the Basket Ball using Kalman Filter.

In this lecture, we will learn how we can predict the trajectory of the basket ball using Kalman Filter. We will first detect the Basket Ball using YOLOv8 and then we will predict the trajectory of the Basket Ball using Kalman Filter.

In this lecture, the YOLOv8 Model was trained for the PPE Detection, the whole workflow can be split into multiple steps.

In the first step, all the required libraries are imported.

In the second step, the YOLOv8 is installed via pip.

In the third step, the Personal Protective Equipment (PPE) dataset is exported from Roboflow into the google colab.

In the fourth step, the YOLOv8 model is trained on the PPE dataset.

In the fifth step, the model performance analysis is done considering the Mean Average Precision, Confusion Matrix, training and the validation loss.

In the sixth step, the fine tuned YOLOv8 model for PPE Detection  is tested on Images and Videos.

In this Lecture, we tested our trained YOLOv8 Model for PPE Detection on Live Webcam, Although, i was only wearing a mask and no other Personal Protective Equipment, the Model was able to detect the Mask Successfully.

This lecture presents an introduction to Object Segmentation using YOLOv8

This video tutorial provides a step by step guide, on how we can implement YOLOv8 segmentation on Images and Videos plus and how we can export the YOLOv8 segmentation model in the ONNX format.

This lecture provides a step by step guideline on how to train the YOLOv8 Segmentation Model on Custom Dataset.

Following are the steps involved in training the YOLOv8 Segmentation Model on Custom Dataset.

1. Preparing the Dataset

2. Fine Tuning/ Training the YOLOv8 Segmentation Model on Custom Dataset

3. Validating the Trained  YOLOv8  Segmentation Model.

4. Testing the Trained  YOLOv8  Segmentation Model on Sample Images and Videos

This lecture provides a step by step guideline on how to train the YOLOv8 Segmentation Model on Custom Dataset.

Following are the steps involved in training the YOLOv8 Segmentation Model on Custom Dataset.

1. Preparing the Dataset

2. Fine Tuning/ Training the YOLOv8 Segmentation Model on Custom Dataset

3. Validating the Trained  YOLOv8  Segmentation Model.

4. Testing the Trained  YOLOv8  Segmentation Model on Sample Images and Videos

This lecture provides a step by step guideline on how to train the YOLOv8 Segmentation Model on Custom Dataset.

Following are the steps involved in training the YOLOv8 Segmentation Model on Custom Dataset.

1. Preparing the Dataset

2. Fine Tuning/ Training the YOLOv8 Segmentation Model on Custom Dataset

3. Validating the Trained  YOLOv8  Segmentation Model.

4. Testing the Trained  YOLOv8  Segmentation Model on Sample Images and Videos

This lecture presents an introduction to YOLO-NAS : A New Foundation Model for Object Detection

In this lecture, we will learn how we can do object detection with YOLO-NAS in Google Colab

In this lecture, we will learn how we can read and display and image using OpenCV

In this lecture, we will learn how we can read and display a video using OpenCV

In this lecture, we will learn how we can read, display and save the video using OpenCV

In this lecture, we will learn how we can capture video from the camera using OpenCV

In this lecture, we will learn how we can do Object Detection on images using YOLO-NAS

In this lecture, we will learn how we can do Object Detection on Videos using YOLO-NAS

In this lecture we will learn how we can track each of the detected object by integrating YOLO-NAS with the SORT Algorithm

In this lecture we will learn how we can create a Vehicles Counting Application to count the vehicles entering and leaving using YOLO-NAS and SORT Algorithm.

In this lecture, we will learn how we can train YOLO-NAS model on the custom dataset and track each of the detected object using SORT algorithm

This lecture presents an introduction to Object Tracking using YOLO-NAS and DeepSORT Algorithm.

In this lecture, we will learn how we can track each of the detected object using YOLO-NAS and DeepSORT Algorithm.

In this lecture, we will train the YOLO-NAS model on a custom dataset (Vehicles Dataset) and then we will track each of the detected vehicles using the DeepSORT algorithm.

In this lecture, we will learn how we can detect potholes in images and videos using YOLO-NAS

In this lecture, we will learn how we can detect Grocery Items in a Retail Store using YOLO-NAS

In this lecture, we will learn how we can do Personal Protective Equipment (PPE)  Detection using YOLO-NAS

In this lecture, we will learn how we can create Vehicles Intensity Heatmaps using YOLO-NAS

In this lecture, we will learn how we can create Vehicles Intensity Heatmaps using YOLO-NAS

In this lecture, we will learn how we can do Image and Video Segmentation using YOLO-NAS and Segment Anything Model (SAM)