NYC-Event-VPR
收藏资源简介:
NYC-Event-VPR数据集是由纽约大学创建的一个大规模高分辨率事件相机视觉位置识别数据集,主要用于城市环境中自动驾驶机器人的视觉位置识别任务。该数据集包含超过13.5小时的视频数据,覆盖了纽约市260公里的范围,涵盖了多种天气和光照条件。数据集的创建过程包括使用Prophesee IMX636 HD事件传感器和RGB相机进行数据采集,并通过数据处理管道确保数据与现有框架的兼容性。该数据集的应用领域主要是机器人视觉位置识别,旨在解决在复杂城市环境中准确识别位置的问题。
NYC-Event-VPR dataset is a large-scale high-resolution event camera visual place recognition (VPR) dataset developed by New York University, primarily used for visual place recognition tasks of autonomous robots in urban environments. This dataset contains over 13.5 hours of video data, covering an area of 260 kilometers across New York City and encompassing diverse weather and lighting conditions. The dataset was created using the Prophesee IMX636 HD event sensor and RGB camera for data collection, with a dedicated data processing pipeline implemented to ensure compatibility with existing frameworks. Its main application domain is robotic visual place recognition, aiming to address the challenge of accurate place recognition in complex urban environments.

- 1NYC-Event-VPR: A Large-Scale High-Resolution Event-Based Visual Place Recognition Dataset in Dense Urban Environments纽约大学 · 2024年



