Deep vision pipeline for self-driving cars based on machine learning methods

Abstract

The purpose of this thesis project is to design and implement a vision pipeline useful for self-driving cars, based on computer vision methods and deep learning frameworks. This pipeline is useful for identifying the lane, other cars in the view, as well as traffic signs. A final vision pipeline design is proposed that explores a network that can control steering based on vision input. Firstly, the working model of computer vision techniques used are presented. The mathematical models used are explored, and implementation in source code developed. These models comprise the vision side of the pipeline. Secondly, this report explores the deep learning models implemented as part of the pipeline. The mathematical approach is presented as well as the source code implementation. The models are industry and academia proven and their implementation is developed in detail. The final part provides details on full pipeline architecture, and required hardware. A comprehensive discussion is made on the pipeline, the lessons learned, and future work.