Scribd
Upload
2 views1 page

1 - Introduction

The project focuses on creating a convolutional neural network for object detection in urban environments using a dataset from Waymo, which includes annotated images of cyclists, pedestrians, and vehicles. It involves extensive data analysis, model training with TensorFlow Object Detection API, and experimentation with hyperparameters to enhance performance. Additionally, the project includes monitoring training with TensorBoard and generating predictions on images.

Uploaded by

Anthony P
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
2 views1 page

1 - Introduction

The project focuses on creating a convolutional neural network for object detection in urban environments using a dataset from Waymo, which includes annotated images of cyclists, pedestrians, and vehicles. It involves extensive data analysis, model training with TensorFlow Object Detection API, and experimentation with hyperparameters to enhance performance. Additionally, the project includes monitoring training with TensorBoard and generating predictions on images.

Uploaded by

Anthony P
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

8/10/22, 7:26 PM Object Detection in an Urban Environment

Project Introduction
In this project, you will apply the skills you have gained in this course to create a convolutional
neural network to detect and classify objects using data from Waymo. You will be provided with a
dataset of images of urban environments containing annotated cyclists, pedestrians and
vehicles.

First, you will perform an extensive data analysis including the computation of label distributions,
display of sample images, and checking for object occlusions.

An example night image from the Waymo dataset, with annotations for vehicles and pedestrians.

You will use this analysis to decide what augmentations are meaningful for this project. Then, you
will train a neural network to detect and classify objects.

You will monitor the training with TensorBoard and decide when to end it. Finally, you will
experiment with different hyperparameters to improve your model's performance.

This project will include use of the TensorFlow Object Detection API, where you can deploy you
model to get predictions on images sent to the API. You will also be provided with code to create
a short video of their model predictions.

[Link] 1/1

You might also like