IMF数据集
收藏资源简介:
IMF数据集由北京航空航天大学交通运输科学与工程学院的研究团队创建,旨在支持道路地形感知的多模态融合网络研究。数据集包含两种类型的多模态融合感知系统收集的数据,包括车辆悬挂系统上的加速度计和前挡风玻璃上的双目摄像头收集的视觉数据,以及不同光照条件和车速下的数据。该数据集用于评估多模态融合网络在不同光照条件下的道路地形感知效果,并与其他单模态感知方法进行比较。
The IMF dataset was developed by a research team from the School of Transportation Science and Engineering, Beihang University, Beijing, with the objective of supporting research on multimodal fusion networks for road terrain perception. The dataset encompasses data collected via a multimodal fusion perception setup with two types of sensors: acceleration data from accelerometers mounted on the vehicle suspension system and visual data from a stereo camera installed on the front windshield, alongside data captured under varying lighting conditions and vehicle speeds. This dataset is employed to assess the performance of multimodal fusion networks in road terrain perception under different lighting conditions, and to make comparisons with other unimodal perception methods.




