Publications (6)
PCARNN-DCBF: Minimal-Intervention Geofence Enforcement for Ground Vehicles
Yinan Yu, Samuel Scheidegger
Runtime geofencing for ground vehicles is rapidly emerging as a critical technology for enforcing Operational Design Domains (ODDs). However, existing solutions struggle to reconci…
Deep Learning-based Scalable Image-to-3D Facade Parser for Generating Thermal 3D Building Models
Yinan Yu, Alex Gonzalez-Caceres, Samuel Scheidegger +2
Renovating existing buildings is essential for climate impact. Early-phase renovation planning requires simulations based on thermal 3D models at Level of Detail (LoD) 3, which inc…
Mono-Camera 3D Multi-Object Tracking Using Deep Learning Detections and PMBM Filtering
Samuel Scheidegger, Joachim Benjaminsson, Emil Rosenberg +2
Monocular cameras are one of the most commonly used sensors in the automotive industry for autonomous vehicles. One major drawback using a monocular camera is that it only makes ob…
A Pre-study on Data Processing Pipelines for Roadside Object Detection Systems Towards Safer Road Infrastructure
Yinan Yu, Samuel Scheidegger, John-Fredrik Grönvall +4
Single-vehicle accidents are the most common type of fatal accidents in Sweden, where a car drives off the road and runs into hazardous roadside objects. Proper installation and ma…
Building Efficient CNNs Using Depthwise Convolutional Eigen-Filters (DeCEF)
Yinan Yu, Samuel Scheidegger, Tomas McKelvey
Deep Convolutional Neural Networks (CNNs) have been widely used in various domains due to their impressive capabilities. These models are typically composed of a large number of 2D…
Fast LIDAR-based Road Detection Using Fully Convolutional Neural Networks
Luca Caltagirone, Samuel Scheidegger, Lennart Svensson +1
In this work, a deep learning approach has been developed to carry out road detection using only LIDAR data. Starting from an unstructured point cloud, top-view images encoding sev…