SimVeRi, a synthetic vehicle re-identification dataset with spatiotemporal metadata and multi-camera views

Overview SimVeRi is a synthetic vehicle re-identification (ReID) dataset generated through CARLA--SUMO co-simulation, designed for multi-camera and air-ground observation settings. The dataset provides structured per-image spatiotemporal metadata that are rarely available in existing vehicle ReID benchmarks, including world coordinates, vehicle headings, speeds, timestamps, and occlusion estimates aligned to every captured image. The dataset is built on CARLA Town05 with a network of 30 cameras: - 19 ground-level roadside cameras- 5 elevated fixed cameras- 6 UAV (unmanned aerial vehicle) cameras SimVeRi is intended as a controllable benchmark resource for reproducible evaluation and structured analysis of vehicle re-identification, spatiotemporal reasoning, and cross-view association. Dataset Components 1. Core Ground-Ground Benchmark - 33,942 images of 650 vehicle identities- Captured by 24 fixed roadside cameras (19 ground + 5 elevated)- Identity-disjoint train / gallery / query split (454 train IDs, 196 eval IDs; 28,379 train, 4,738 gallery, 825 query images)- One query image per camera per vehicle; query excluded from gallery 2. Twins Supplement - 14,032 images of 125 vehicles in 25 visually identical groups (5 vehicles per group)- All vehicles within each group share the same CARLA blueprint and colour- Supports controlled evaluation under severe appearance ambiguity at both vehicle-level and group-level 3. Air-Ground Extension - Tracklet-level cross-view protocols for aerial-ground vehicle association- Test scope: 316 air tracklets / 825 ground tracklets (79 vehicles with both layers)- Full scope: 984 air tracklets / 1,077 ground tracklets (246 vehicles with both layers)- Positive pairs defined by same vehicle identity and temporal overlap- Air and ground tracklet images additionally include per-image spatiotemporal metadata (ag_spatiotemporal.json: timestamp, world coordinates, heading, speed, occlusion). Per-Image Metadata Each image record is associated with structured metadata including: - Vehicle identity (mapped ID) and camera identity- Simulation timestamp- World coordinates (x, y, z) in CARLA coordinate system- Vehicle heading (degrees) and speed (km/h)- Occlusion ratio and occlusion level- Bounding box dimensions and camera-to-vehicle distance Dataset-Level Metadata - camera_network.json --- 30-camera deployment with 3D positions, rotations, FOV, layer classification, and route-based inter-camera distance matrix- trajectory_info.csv --- within-camera tracklet summaries (2,731 tracklets)- camera_transitions.csv --- inter-camera transition statistics (route distance, mean travel time, sample counts)- splits.json --- identity-disjoint train/test partition (seed 42, ratio 0.70)- vehicle_attributes.json --- vehicle type and colour definitions- twins_groups.json --- group membership for identical-appearance vehicles Intended Use SimVeRi supports research in: - Vehicle re-identification and multi-camera retrieval- Spatiotemporal reasoning and trajectory-aware association- Cross-view and air-ground vehicle matching- Controlled evaluation under appearance ambiguity (Twins)- Synthetic data for intelligent transportation systems- Camera network analysis and deployment optimization Generation SimVeRi was generated using CARLA 0.9.13 and SUMO 1.15.0 in synchronized co-simulation mode. Vehicle appearance was sampled from 25 native CARLA blueprints with 17 colour variants. The simulator weather was fixed to ClearNoon. The companion generation and validation code is available at: https://github.com/Zengzhi-Zhang/SimVeRi