In today's lesson, you will learn the fundamentals of thermal/mid-far infrared vision. By the end of this lesson, you'll have measured the temperature value of each pixel in a thermal image and a thermal video in a very easy way, only using Python and OpenCV. In addition, you'll be able to get the video stream from a thermal camera and the temperature values in real time if you have one of these amazing cameras on hand. To learn how to measure your first temperature value from each pixel in a thermal image, just keep reading. Before we start measuring the temperature value of each pixel, we need to understand the different basic image formats that thermal cameras/images provide.

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!

This is the best course to quickly grasp the knowledge of Python and OpenCV and become proficient to design Computer Vision and Deep Learning solutions. With the AI-fueled organization trend getting momentum, the industry is in dire need of Computer Vision experts who are proficient in Python and OpenCV. This course has been designed to start with the basics of Python coding language comprising of Data Types, Operators, Loops, Functions, Modules, File Handling, Exception Handling along with Popular Coding Practices and then slowly take you through the advanced Python concepts such as Lambda, Map, Filter, Object Oriented Programming, Decorator, Generator, DateTime, Math, Random, Statistics, Sys, OS, Numpy, Pandas, Matplotlib and OpenPyXL in detail. Not only this, the course takes it one step further by providing comprehensive coverage of OpenCV topics including Image Thresholding, Image Noise Removal, Image Cropping & Rotation, Image Annotation, Image Detection and also OpenCV for Videos with 35 supporting notebooks available for download that contain examples for practice. The quiz at the end of each key topic helps you to assess your knowledge and identify the improvement areas.

Data augmentation is a technique to increase the diversity of dataset without an effort to collect any more real data but still help improve your model accuracy and prevent the model from overfitting. In this post, you will learn to implement the most popular and efficient data augmentation procedures for object detection task using Python and OpenCV. Firstly, let's import several libraries and prepare some necessary subroutines before going ahead. The below image is used as a sample image during this post. Random Crop selects randomly a region and crops it out to make a new data sample, the cropped region should have the same width/height ratio as the original image to maintain the shapes of objects.

Now we calculate the threshold value for every frame and determine the contours using cv2.findContours and return the max contours (the most outermost contours for the object) using the function segment. Using the contours we are able to determine if there is any foreground object being detected in the ROI, in other words, if there is a hand in the ROI. When contours are detected (or hand is present in the ROI), We start to save the image of the ROI in the train and test set respectively for the letter or number we are detecting it for. In the above example, the dataset for 1 is being created and the thresholded image of the ROI is being shown in the next window and this frame of ROI is being saved in ..train/1/example.jpg For the train dataset, we save 701 images for each number to be detected, and for the test dataset, we do the same and create 40 images for each number. Now on the created data set we train a CNN. First, we load the data using ImageDataGenerator of keras through which we can use the flow_from_directory function to load the train and test set data, and each of the names of the number folders will be the class names for the imgs loaded.

Create a computer vision program with python and OpenCV.

The code of this project can be found here. For those of you that have found this post before part 1 or that want to refresh what we have done up to this point, here you can catch up with the current state of the project so far. For the rest, we'll keep going from where we left it. I've been really busy lately, so sorry if this second part is not as detailed as the first one. We left the project in a state where we were able to estimate the homography between our reference surface and a frame that contained that same surface in an arbitrary position.