View Code? Open in Web Editor
NEW
Computer vision and machine learning projects for self-driving car technologies
Jupyter Notebook 5.37%
HTML 3.57%
Python 0.12%
CMake 0.61%
C++ 37.76%
C 2.86%
Shell 3.38%
Cuda 0.33%
Fortran 43.14%
JavaScript 0.02%
CSS 0.01%
M4 0.28%
Batchfile 0.01%
Makefile 1.86%
Java 0.04%
MATLAB 0.06%
R 0.08%
TeX 0.47%
AMPL 0.01%
SourcePawn 0.01%
selfdrivingcar's Introduction
Self-Driving Car Projects
1. Finding lanes in a video stream using OpenCV
- Use openCV, Canny edge detector, Hough transform and region of interest masks to build a simple lane detection pipeline
2. Identifying traffic signs using Tensorflow
- Use Tensor-flow and Convolutional neural-networks (CNNs) to classify different types of traffic signs.
3. Behavioral Cloning using Keras
- Use a car simulator to collect data of good driving behavior
- Build, a convolution neural network in Keras that predicts steering angles from images
- Train and validate the model with a training and validation set
- Test that the model successfully drives around track one without leaving the road
4. Advanced lane detection pipeline
- Compute the camera calibration matrix and distortion coefficients given a set of chessboard images.
- Apply a distortion correction to raw images.
- Use color transforms, gradients, etc., to create a thresholded binary image.
- Apply a perspective transform to rectify binary image ("birds-eye view").
- Detect lane pixels and fit to find the lane boundary.
- Determine the curvature of the lane and vehicle position with respect to center.
- Warp the detected lane boundaries back onto the original image.
- Output visual display of the lane boundaries and numerical estimation of lane curvature and vehicle position.
5. Vehicle Detection pipeline
- Perform a Histogram of Oriented Gradients (HOG) feature extraction on a labeled training set of images and train a classifier Linear SVM classifier
- Also apply a color transform and append binned color features, as well as histograms of color, to your HOG feature vector.
- Note: for those first two steps don't forget to normalize your features and randomize a selection for training and testing.
- Implement a sliding-window technique and use your trained classifier to search for vehicles in images.
- Run the pipeline on a video stream and create a heat map of recurring detections frame by frame to reject outliers and follow detected vehicles.
- Estimate a bounding box for vehicles detected.
6. Extended Kalman filter
- Use an extended Kalman filter to predict the path of a moving object based on LIDAR and RADAR data
7. Unscented Kalman filter
- Use an unscented Kalman filter to predict the path of a moving object nbased on LIDAR and RADAR data
- Use Particle filters to localize an object moving within a known map
- Use a PID controller to control the steering of a vehicle within the lane
10. Model predictive control
- Use a Kinematic model to more accurately control the steering of the vehicle even at high speeds
selfdrivingcar's People
Contributors
Watchers