Data Fusion-Based Lane Departure Warning Framework Using Fuzzy Logic
Collisions arising from lane departures have contributed to traffic accidents causing millions of injuries and tens of thousands of casualties per year worldwide. Many related studies had shown that single vehicle lane departure crashes accounted largely in road traffic deaths that results from drifti...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
2019
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Collisions arising from lane departures have contributed to traffic accidents causing millions of injuries and tens of thousands of casualties per year worldwide. Many related studies had shown that single vehicle lane departure crashes accounted largely in road traffic deaths that results from drifting out of the roadway. Hence, automotive safety has becoming a concern for the road users as most of the road casualties occurred due to driver’s fallacious judgement of vehicle path. However, lane detection challenges from environmental conditions such as low illumination, worn lane markings, occluded lane markings, shadows, and other road markings that affecting the performance of identifying the accurate lanes. This thesis proposes a novel data fusion-based Lane Departure Warning (LDW) framework for improving the lane departure detection rate under both daytime and night-time driving environments. Data fusion-based LDW is composed of visionbased LDW framework and model-based vehicle dynamics framework. Vision-based LDW is essentially consisting of vision-based lane detection framework and followed by the computation of lateral offset ratio. Model-based vehicle dynamics is mainly consists of a mathematical representation of 9-Degree-of-freedom (DOF) system. The lateral offset ratio from vision-based LDW and yaw acceleration from model-based vehicle dynamics are fused into a multi-input single-output fuzzy logic controller. The output of fuzzy logic controller is used for determining the LDW based on six predefined fuzzy rules. |
|---|