A Multi-Modal IoT and Deep Learning Platform for Real-Time Bus Safety Monitoring and Passenger Intelligence
Abstract
Sri Lanka’s public bus network carries millions of daily commuters yet operates with negligible real-time visibility into driver safety, road compliance, or service quality [1], [2]. Drivers go unmonitored, violations go unrecorded, and passengers lack reliable arrival or occupancy information [1]. This paper presents an integrated, low-cost IoT platform addressing these deficiencies within a single system. A cab-mounted camera continuously monitors the driver, detecting drowsiness, phone use, and seat belt non-compliance with a mean average precision (mAP50) of 98.5%. A forward-facing module fuses object detection, lane segmentation, and monocular depth estimation to identify traffic violations at 10–25 FPS (Raspberry Pi 5; Table III). Calibrated load cells feed a LightGBM regressor generating load-aware speed recommendations (R2 = 0.887, MAE = 1.94 km/h). An LSTM trained on SLTB ticketing data predicts arrival times to within 103 s MAE; a BiLSTM multi-task model estimates boarding and alighting counts with MAEs of 2.29 and 2.18 passengers, respectively. The complete hardware bill-of-materials is under USD 100 per bus, comprising a Raspberry Pi 4/5, ESP32, load cells, and off-the-shelf sensors. Together these modules form a proof-of-concept that meaningfully advances transit safety and passenger intelligence without infrastructure-level investment.