Skip to content

Latest commit

 

History

History

README.md

Experimental Design

This repository contains the experimental design of my master's thesis, broken down into these sections:

Data Sets

I used the KITTI and AVX data sets for performance evaluation, with the 'Train' subsets for model training, and the 'Test' subsets for validation and evaluation. For more details, see the readme.

Network Settings

I used the PointPillars Network for 3D object detection, with the OpenPCDet tool. The model targets 'Car', 'Pedestrian', and 'Cyclist' classes. Training parameters and techniques are also discussed. For more details, see the readme.

Evaluation Metrics

The KITTI Evaluation Metrics are used for network assessment, which includes the 3D Intersection over Union (IoU), Precision-Recall (PR) curve, Average Precision (AP), and Average Orientation Similarity (AOS) metric. For more details, see the readme.

Adapting KITTI Difficulty Levels

I examined the applicability of KITTI difficulty levels to synthetic data sets in object detection context. For more details, see the readme.

Experiments

A collection of experiments are included, which focus on neural network performance when trained on both real and synthetic data sets. For more details, see the readme.