# Udacity-Projects

**Repository Path**: dalaska/Udacity-Projects

## Basic Information

- **Project Name**: Udacity-Projects
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-05-15
- **Last Updated**: 2020-12-18

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Udacity Nano Degree Projects
## Overview

- AV-11-Lane-Finding

    Detect traffic lane using computer vision.

    ![lane-finding](/img/find-lane.gif)

- AV-12-Traffic-Signs

    Classify traffic signs using deep convolutional neural networks.

    ![traffic-sign](/img/traffic-sign.png)
    
- AV-13-Behavior-Cloning

    Train a car to drive itself in a simulation environment, with the images-steering-angle-pair data using a deep neural network. 

- AV-14-Advance-Lane
    * Compute the camera calibration matrix and distortion coefficients given a set of chessboard images.
    * Apply the distortion correction to the raw image.  
    * 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 lane boundary.
    * Determine 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.

    ![car-detection](/img/detection.gif)

- AV-15-Detection-Tracking

    * Define Features: define features for the vehicle classification including color space feature, color histogram features, and HOG features.
    * Define Classifier: train and fine tune a random forests classifier  to detect vehicle.
    * Vehicle Detection: implement a sliding-window technique and use the classifier to determine whether the image contains vehicles
    * Duplicates Removal: create a heatmap to removal duplicates  (multiple detections  of the same car) and outliers.
    * Vehicle Tracking: tracking and estimate a bounding box for vehicles detected.
    * Video Pipeline: run the pipeline on a video stream and detect vehicles frame by frame

    ![advance-lane](/img/rad.gif)

- AV-21-EKF

    Estimate a pedestrian's 2d location and speed by combining the Radar and Laser measurement using Extended Kalman Filter.

    ![ekf](/img/pipline.png)

- DS-Data-Wrangling

    Clean an area on OpenStreetMap and analysis the statistic of the area using MongoDB.

    ![data-wrangle](/img/data-wrangle.png)

- DS-Red-Wine-Analysis

    Exploring the red wine dataset by using a variety of plots.

    ![wine](/img/wine.png)

- DS-Titanic-Visual

    Show how the chance of survival varies across different passenger class and between children women and men. 

- ML-Customer-Segment

    Create customer segmentation using Unsupervised Learning 

    ![cluster.png](/img/cluster.png)

- ML-Enron-Fraud

    Build a classifier using the email and financial data to identify the person of interest in the Enron fraud.

- ML-Predict-House-Price

    Build a regression model for the housing price in the Boston Area.

    ![house.png](/img/house.png)

- ML-Student-Intervention

    Identify students who might need early intervention using Supervise Learning.

- ML-Taxi-Reinforcement

    Implement driving agents to learn the traffic rules at intersection using Reinforcement Learning

## Certificates
*Machine Learning Engineer*

![ml-degree](/img/ml.png)

*Data Analyst*

![data-degree](/img/da.png)