AnoVox_Static_Legacy

<p>This is the legacy version of AnoVox; a preliminary release prior to the full release of the remaining dataset within this Zenodo Community. We advise against using it.</p> <p>---------------</p> <p>The presented&nbsp;<strong>AnoVox&nbsp;</strong>dataset is a dataset of abnormal scenarios with unknown objects. The benchmark relies on the CARLA 0.9.14 simulator. This dataset includes a collection of road scenarios that feature abnormal objects. These scenarios were developed using the CARLA Simulator.&nbsp;</p> <p>The <strong>"Anovox"</strong> directory comprises ten distinct scenario folders, each assigned a unique identifier. These folders encapsulate a comprehensive array of data components crucial for characterizing and comprehending abnormal traffic situations. Each scenario presents a specific traffic context and covers a time span of 18.5 seconds, equivalent to 185 ticks.</p> <p>Within each individual scenario folder, the following subfolders and files are present:</p> <p>1.&nbsp;<strong>"ACTION"</strong>: This folder contains the action state values attributed to the ego vehicle for every tick throughout the scenario.</p> <p>2.&nbsp;<strong>"ANOMALY"</strong>: This repository houses anomalous objects or occurrences that take place within the scenario. Additionally, this folder has the potential to incorporate irregular driver and pedestrian actions in future iterations.</p> <p>3.&nbsp;<strong>"DEPTH_IMG"</strong>: This section comprises depth images that encode the spatial depth of each pixel through the utilization of RGB channels (for more information, refer to the CARLA docs: https://carla.readthedocs.io/en/latest/ref_sensors/#depth-camera).</p> <p>4.&nbsp;<strong>"PCD"</strong>: This section encompasses point cloud data derived from lidar scans, effectively representing the semantic segmentation of the simulated environment.</p> <p>5.&nbsp;<strong>"RGB_IMG"</strong>: This section hosts RGB images corresponding to each frame of the scenario.</p> <p>6.&nbsp;<strong>"SEMANTIC_IMG"</strong>: Here, you will find images that offer ground truth information via semantic segmentation.</p> <p>7.&nbsp;<strong>"SEMANTIC_PCD"</strong>: This section contains point cloud representations with embedded semantic segmentation details, further enriching the ground truth information.</p> <p>8.&nbsp;<strong>"VOXEL_GRID"</strong>: This section provides ground truth via a voxel representation of the surroundings.</p> <p>Additionally, the dataset is augmented by a separate directory titled&nbsp;<strong>"Scenario_Configuration_Files."</strong>&nbsp;This directory comprises eight JSON files tailored for different urban environments, distinguished by their names ("Town01," "Town02," "Town03," "Town04," "Town05," "Town06," "Town07," "Town10HD"). These JSON files play a crucial role in ensuring the reproducibility of scenarios. They encompass critical details, such as the spawn points of anomalies and the ego vehicle, alongside weather presets.</p> <p>The color palette used to represent the semantic segmentation is based on the Cityscapes color palette. A detailed description of this color palette can be found in the document&nbsp;<strong>"color_palette.txt"</strong>.</p>