Project:1 SELF DRIVING CAR USING NEURAL NETWORKS
Advancements in technology have changed how we move from one place to another; cars today
include semi-autonomous features like self-braking systems, obstacle detections, and assisted
parking systems. Artificial Intelligence has already started to replace humans in many areas. This
project is to develop a fully autonomous vehicle prototype which uses neural networks to sense
the complete environment around it and take actions according to the inputs from the dynamic
environment. The car can perform lane detection, traffic sign recognition, and traffic lights
recognition. The car has 2 rear wheels and one casor wheel in the front.
A picamera was attached on the car for capturing live frames. The ultrasonic sensor is attached at the front of the car to detect the obstacles when passing through the obstacles. A 2 lane track is built to test the car and some obstacles are placed on the track. The car will navigate by itself and overtake all the obstacles on the track. The Raspberry pi communicates with single board computer through Wi-Fi. The single board computer is hosted by a TCP server. When picamera captures a frame which is sent through Raspberry to server for further processing and making prediction with the help of neural network model and helps the car to navigate itself.
Project:2 FACE RECOGNITION USING LIVE VIDEO FEEDS
The main idea is to collect and build datasets of different faces and train a model that can recognize faces from the live video with high accuracy using regular learning. This Project is implemented in Python using numpy, Opencv and AI concepts on Jupyter notebook. OpenCV includes a comprehensive set of both classic and state-of-the-art computer vision and machine learning algorithms. This project incorporate different algorithms:
- Faces Detection
- Faces Recognition
- Objects Identification
- Classify human actions in videos
- Track camera movement
- Track moving objects
- Extract 3D models of objects
- Find similar images from an image database
- Remove red eyes from images taken using flash
- Follow eye movements
OpenCV is a great tool to have in hand when dealing with data problems related to media. In the case you want to create your own tuned algorithm, due to its simplicity it lets you use the majority of your resources on developing the algorithm itself and not on the manipulation of the data, which can be a pain in the.
Project:3 DROWSINESS DETECTION WITH OPENCV
In this project we used computer vision system that can automatically detect driver drowsiness in a real-time video stream and then play an alarm if the driver appears to be drowsy.