VIODE

Dynamic environments such as urban areas are still challenging for popular visual-inertial odometry (VIO) algo- rithms. Existing datasets typically fail to capture the dynamic nature of these environments, therefore making it difficult to quantitatively evaluate the robustness of existing VIO methods. To address this issue, we propose three contributions: firstly, we provide the VIODE benchmark, a novel dataset recorded from a simulated UAV that navigates in challenging dynamic environments. The unique feature of the VIODE dataset is the systematic introduction of moving objects into the scenes. It includes three environments, each of which is available in four dynamic levels that progressively add moving objects. The dataset contains synchronized stereo images and IMU data, as well as ground-truth trajectories and instance segmentation masks. Secondly, we compare state-of-the-art VIO algorithms on the VIODE dataset and show that they display substantial performance degradation in highly dynamic scenes. Thirdly, we propose a simple extension for visual localization algorithms that relies on semantic information. Our results show that scene semantics are an effective way to mitigate the adverse effects of dynamic objects on VIO algorithms. Finally, we make the VIODE dataset publicly available at https://github.com/kminoda/VIODE.诸如城市区域等动态环境，对于主流的视觉惯性里程计（Visual-Inertial Odometry, VIO）算法而言仍是极具挑战性的应用场景。现有数据集通常无法准确捕捉这类环境的动态特性，因此难以对现有VIO算法的鲁棒性开展定量评估。为解决这一问题，本文提出三项核心贡献：其一，我们发布VIODE基准数据集——该数据集由在高难度动态环境中航行的仿真无人机（Unmanned Aerial Vehicle, UAV）采集得到。VIODE数据集的独特之处在于，其通过系统性设计在场景中引入了移动目标。该数据集包含三类实验环境，每类环境均设有四种动态等级，等级越高则场景内的移动目标数量逐步递增。数据集涵盖同步立体图像与惯性测量单元（Inertial Measurement Unit, IMU）数据，同时还包含真值轨迹与实例分割掩码。其二，我们在VIODE数据集上对当前主流顶尖的VIO算法进行了对比测试，结果显示这些算法在高动态场景中会出现显著的性能退化。其三，我们提出了一种基于语义信息的视觉定位算法简易扩展方案。实验结果表明，场景语义信息可有效缓解动态目标对VIO算法造成的负面影响。最后，我们将VIODE数据集公开共享，其访问地址为https://github.com/kminoda/VIODE。