Abstract
Object detection is an essential technology for surveillance systems, particularly in areas with a high risk of accidents such as railway level crossings. To prevent future collisions, the system must detect and track any object that passes through the monitored area with high accuracy, and this process must be performed fulfilling real-time specifications. In this work, an edge IoT HW platform implementation capable of detecting and tracking objects in a railway level crossing scenario is proposed. The response of the system has to be calculated and sent from the proposed IoT platform to the train, so as to trigger a warning action to avoid a possible collision. The system uses a low-resolution 3D 16-channel LIDAR as a sensor that provides an accurate point cloud map with a large amount of data. The element used to process the information is a custom embedded edge platform with low computing resources and low-power consumption. This processing element is located as close as possible to the sensor, where data is generated to improve latency, privacy, and avoid bandwidth limitations, compared to performing processing in the cloud. Additionally, lightweight object detection and tracking algorithm is proposed in this work to process a large amount of information provided by the LIDAR, allowing to reach real-time specifications. The proposed method is validated quantitatively by carrying out implementation on a car road, emulating a railway level crossing.
Highlights
The current situation regarding the high number of accidents at railway level crossings in Europe is one of the main motivations for this work
Wisultschew et al.: 3D-Light Detection And Ranging (LIDAR) Based Object Detection and Tracking on the Edge of Internet of Things (IoT) for Railway Level Crossing detect the targets with the highest accuracy, reliability, and robustness to reduce the risk of an accident
If two objects are overlapped, the one which is furthest away from the LIDAR will not be detected nor tracked. This fact is a limitation for LIDAR-based systems, which could be addressed by deploying sensors based on other working principles
Summary
The current situation regarding the high number of accidents at railway level crossings in Europe is one of the main motivations for this work. C. Wisultschew et al.: 3D-LIDAR Based Object Detection and Tracking on the Edge of IoT for Railway Level Crossing detect the targets with the highest accuracy, reliability, and robustness to reduce the risk of an accident. Wisultschew et al.: 3D-LIDAR Based Object Detection and Tracking on the Edge of IoT for Railway Level Crossing detect the targets with the highest accuracy, reliability, and robustness to reduce the risk of an accident It will involve using complex sensors, combined or alone, which should be able to work under any weather condition and day or night [7]. The limitation in energy and computing capacity implies that it could be interesting to reduce the number of sensors considered, due to further processing for data fusion In this regard, this work opts for considering a single sensor, which stands out for its high reliability and robustness, outperforming image-based systems.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
