Abstract:
A Perfectly Accurate, Synthetic dataset featuring a virtual railway EnVironment for Multi-View Stereopsis (RailEnV- PASMVS) is presented, consisting of 40 scenes and 79,800 renderings together with ground truth depth maps, extrinsic and intrinsic camera parameters, pseudo-geolocation meta- data and binary segmentation masks of all the track com- ponents. Every scene is rendered from a set of 3 cameras, each positioned relative to the track for optimal 3D recon- struction of the rail profile. The set of cameras is trans- lated across the 100 m length of tangent (straight) track to yield a total of 1995 camera views. Photorealistic lighting of each of the 40 scenes is achieved with the implementation of high-definition, high dynamic range (HDR) environmen- tal textures. Additional variation is introduced in the form of camera focal lengths, camera location and rotation pa- rameters and shader modifications for materials. Represen- tative track geometry provides random and unique vertical alignment data for the rail profile for every scene. This pri- mary, synthetic dataset is augmented by a smaller photo-graph collection consisting of 320 annotated photographs for improved semantic segmentation performance. The combina- tion of diffuse and specular properties increases the ambigu- ity and complexity of the data distribution. RailEnV-PASMVS represents an application specific dataset for railway engi- neering, against the backdrop of existing datasets available in the field of computer vision, providing the precision required for novel research applications in the field of transportation engineering. The novelty of the RailEnV-PASMVS dataset is demonstrated with two use cases, resolving shortcomings of the existing PASMVS dataset.
