Traffic3D: Aston University

Stand A023
The Traffic3DAI traffic control system has been shown to continue performing well in real time traffic control tasks, in all kinds of adverse weather conditions (rain, snow), obstructed views (eg a tree growing within the camera’s field of view), rapidly changing traffic conditions and challenging junction configurations.   To achieve resilience in performance, Traffic3DAI has been trained in simulation, using the Traffic3D simulator, in progressively harder conditions (adverse weather, lighting, occlusions, rapidly varying traffic, challenging junction configurations) - the goal being to equip this intelligent signal controller with the ability to operate in any real-life traffic environment. Traffic3D (traffic3D.org) is a new traffic simulation paradigm, built to push forward research in human-like learning (for example, based on photo-realistic visual input). It provides a fast, cheap and scalable proxy for real-world traffic environments. Developed by researchers at Aston University, it provides effective simulation of diverse and dynamic 3D-road traffic scenarios, closely mimicking real-world traffic characteristics such as faithful simulation of individual vehicle behaviour, their precise physics of movement and photo-realism. Traffic3D can facilitate research across multiple domains, including transport engineering , reinforcement learning, object detection and segmentation, unsupervised representation learning and visual question answering.

Categories

  • Modelling
  • Signage
  • Signalling
  • Software
  • Temporary Traffic Lights
  • Traffic Calming
  • Traffic Control & Monitoring
  • Traffic Management, Enforcement & Control
  • Traffic Signalling & Control Devices
  • Traffic Simulation
  • Video Image Processing