Real-time object detection using a remotely accessible Wi-fi camera Motivation:- When it comes to identifying images, we humans can clearly recognize and distinguish different features of objects.
This is because our brains have been trained unconsciously with the same set of images that has resulted in the development of capabilities to differentiate between things effortlessly.
Contrary to human brains, computer views visuals as an array of numerical values and looks for patterns in the digital image, be it a still, video, graphic, or even live, to recognize and distinguish key features of the image.
Training computers to detect objects is helpful in various areas including security, as well as in automation. This project is a demonstration of such a model.
Overview:- The complete code is written in python language and uses various python libraries including OpenCV. It also makes the use of TensorFlow API. The whole code is distributed in two Jupyter notebooks :
- The first Jupyter notebook (image_collection.ipynb) contains the code for collection of images.
- The second notebook (training_and_detection.ipynb) contains the code for training our model, as well as to detect objects through our v380 Wi-Fi camera.
For this project, I have created a separate virtual environment in the system (‘spro’) to install all the packages and libraries that we need, and then import all the header files according to their need.