An Energy-Efficient Smart Bus Transport Management System with Blind-Spot Collision Detection Ability

TL;DR

This work tackles key inefficiencies and safety risks in public bus systems in developing regions by integrating edge-driven perception (via YOLOv4-Tiny on a Raspberry Pi 4B) for blind-spot and bus-stop detection, RFID-based passenger tracking, a smart bus-door mechanism, and solar-powered bus-stops. A two-web-app data server (React/Node) with Google Maps visualization supports real-time tracking and admin analytics, while a solar-energy subsystem sizes panels andBattery storage to enable continuous operation. The system demonstrates near-ideal blind-spot detection performance (≈$99\%$ accuracy) and provides robust energy savings with an estimated annual benefit of up to $12.71$ kWh, highlighting the practicality of an energy-efficient, safety-enhanced public transit solution. The proposed architecture, along with open-source implementation guidance, offers a scalable path to safer, more reliable, and greener urban transportation by leveraging computer vision, IoT, and renewables.

Abstract

Public bus transport systems in developing countries often suffer from a lack of real-time location updates and for users, making commuting inconvenient and unreliable for passengers. Furthermore, stopping at undesired locations rather than designated bus stops creates safety risks and contributes to roadblocks, often causing traffic congestion. Additionally, issues such as blind spots, along with a lack of following traffic laws, increase the chances of accidents. In this work, we address these challenges by proposing a smart public bus system along with intelligent bus stops that enhance safety, efficiency, and sustainability. Our approach includes a deep learning-based blind-spot warning system to help drivers avoid accidents with automated bus-stop detection to accurately identify bus stops, improving transit efficiency. We also introduce IoT-based solar-powered smart bus stops that show real-time passenger counts, along with an RFID-based card system to track where passengers board and exit. A smart door system ensures safer and more organised boarding, while real-time bus tracking keeps passengers informed. To connect all these features, we use an HTTP-based server for seamless communication between the interconnected network systems. Our proposed system demonstrated approximately 99% efficiency in real-time blind spot detection while stopping precisely at the bus stops. Furthermore, the server showed real-time location updates both to the users and at the bus stops, enhancing commuting efficiency. The proposed energy-efficient bus stop demonstrated 12.71kWh energy saving, promoting sustainable architecture. Full implementation and source code are available at: https://github.com/sadman-adib/MoveMe-IoT

Figures (11)

• Figure 1: Full system architecture. It illustrates a smart bus monitoring and collision detection system divided into three sections: BUS (A), DATA SERVER (B), and BUS STOP (C). In the BUS (A) section, the process starts with a Raspberry Pi 4B, where a webcam detects bus stops, turning on the light and opening the door. Passengers use RFID card punch, and the system calculates the passenger count. The Raspberry Pi continuously measures distance; if a webcam detects an object, collision measurement is triggered, and a sonar sensor measures the distance. If the distance is less than 1 meter, a buzzer sounds as a warning. The DATA SERVER (B) section starts with an ESP32, which transmits data to a database, making it accessible via a web application. In the BUS STOP (C) section, an Arduino receives real-time data via an ESP-01 WiFi module and an RTC module, displaying it on an OLED screen. The system is powered through a USB connection from a solar 20W panel, which charges a 12V battery via a PWM MPPT manager. This architecture integrates real-time bus tracking, collision alerts, and passenger updates for an efficient transportation system.
• Figure 2: Fully detailed implementation architecture. It explains the hardware architecture, showcasing the integration of a Raspberry Pi 4B with camera and sonar sensors for object detection, an LED for bus stop alerts, an RFID system for passenger tracking, and wireless networking for real-time seat count updates to bus-stop displays, all powered by onboard electricity and solar energy.
• Figure 3: Component setup in bus for real-time implementation. It shows the complete setup of a smart bus monitoring system, highlighting the practical placement of cameras for blind-spot and bus-stop detection, SONAR sensors for distance measurement, an RFID reader for logging passenger entry and exit, and the integration of all components with a Raspberry Pi inside the bus. The images illustrate how each device is mounted and connected, ensuring real-time safety monitoring, obstacle detection, and automated passenger tracking within a single, compact system.
• Figure 4: Blind-spot object detection architecture. It shows that the blind-spot detection system uses a YOLOv4-Tiny model on a Raspberry Pi 4b to detect objects around the bus, activates a SONAR sensor for distance measurement, and triggers a buzzer alarm if a collision risk is detected within 1m, enhancing safety.
• Figure 5: Bus-stop detection system with smart bus-door functionality architecture. The system employs a YOLOv4-Tiny model on a Raspberry Pi 4b to detect bus-stops via a camera, activating an LED to alert the driver for increased safety and awareness. Simultaneously, a smart bus-door mechanism cross-checks the detected location with actual bus-stops to ensure doors only open at valid stops, issuing warnings and triggering emergency alerts if opened incorrectly, thus enhancing both safety and operational efficiency.