UDACITY SELF-DRIVING CAR ENGINEER NANODEGREE

Semantic Segmentation Project (Advanced Deep Learning)

Introduction

The goal of this project is to construct a fully convolutional neural network based on the VGG-16 image classifier architecture for performing semantic segmentation to identify drivable road area from an car dashcam image (trained and tested on the KITTI data set).

Approach

Architecture

A pre-trained VGG-16 network was converted to a fully convolutional network by converting the final fully connected layer to a 1x1 convolution and setting the depth equal to the number of desired classes (in this case, two: road and not-road). Performance is improved through the use of skip connections, performing 1x1 convolutions on previous VGG layers (in this case, layers 3 and 4) and adding them element-wise to upsampled (through transposed convolution) lower-level layers (i.e. the 1x1-convolved layer 7 is upsampled before being added to the 1x1-convolved layer 4). Each convolution and transpose convolution layer includes a kernel initializer and regularizer

Optimizer

The loss function for the network is cross-entropy, and an Adam optimizer is used.

Training

The hyperparameters used for training are:

• keep_prob: 0.5
• learning_rate: 0.0009
• epochs: 50
• batch_size: 5

Results

Loss per batch tends to average below 0.200 after two epochs and below 0.100 after ten epochs. Average loss per batch at epoch 20: 0.054, at epoch 30: 0.072, at epoch 40: 0.037, and at epoch 50: 0.031.

Samples

Below are a few sample images from the output of the fully convolutional network, with the segmentation class overlaid upon the original image in green.

Performance is very good, but not perfect with only spots of road identified in a handful of images.

The following is from the original Udacity repository README

Introduction

In this project, you'll label the pixels of a road in images using a Fully Convolutional Network (FCN).

Setup

Frameworks and Packages

Make sure you have the following is installed:

• Python 3
• TensorFlow
• NumPy
• SciPy

Dataset

Download the Kitti Road dataset from here. Extract the dataset in the data folder. This will create the folder data_road with all the training a test images.

Start

Implement

Implement the code in the main.py module indicated by the "TODO" comments. The comments indicated with "OPTIONAL" tag are not required to complete.

Run

Run the following command to run the project:

python main.py

Note If running this in Jupyter Notebook system messages, such as those regarding test status, may appear in the terminal rather than the notebook.

Submission

1. Ensure you've passed all the unit tests.
2. Ensure you pass all points on the rubric.
3. Submit the following in a zip file.

• helper.py
• main.py
• project_tests.py
• Newest inference images from runs folder

How to write a README

A well written README file can enhance your project and portfolio. Develop your abilities to create professional README files by completing this free course.