An Integrated Deep Learning-based Lane Departure Warning and Blind Spot Detection System: A Case Study for the Kayoola Buses

Abstract

Deep learning-based driver assistance systems (ADAS) have attracted interest from researchers due to their impact on improving vehicle safety and reducing road traffic accidents. In Uganda, road accidents have continued to soar with an increase of up to 42% in 2021 due to the growing road traffic density. To curb the high rates of road accidents, especially for heavy-duty vehicles, Kiira Motors Corporation a state-owned mobility solutions enterprise needs advanced driver assistance systems for improved safety of their market entry products- the Kayoola buses. This research presents an approach to vehicular safety enhancement through the integration of Lane Departure Warning (LDW) and Blind Spot Detection systems (BSD) using advanced deep learning algorithms. The resultant LDW and BSD system is realized on the Raspberry Pi platform, incorporating diverse sensors. By combining these advanced features, the study not only bridges an essential research void but also offers a practical resolution to pressing road safety concerns in the East African context. The integration of LDW and BSD systems through deep learning techniques marks a pivotal advancement in vehicular safety. The lane detection model was tested on DET and TuSimple datasets. Our model attained a mean F1 Score of 77.59% and a mean IoU of 65.26% on the Dataset for Lane Extraction (DET) and an overall accuracy of 97.96% on the TuSimple dataset. Our work presents an integrated lane departure warning and blind spot detection system that will be able to alert the driver using the graphical user interface, and auditory feedback. The anticipated real-world implementation is poised to substantiate the system’s effectiveness, thereby contributing to safer roads regionally and inspiring innovation in automotive engineering by leveraging artificial intelligence.