L-AVATeD: the LiDAR And Visual wAlking Terrain Dataset
收藏资源简介：
An understanding of local walking context plays an important role in the analysis of gait in humans. Laboratory analysis on its own can constrain the ability of researchers to properly assess clinical gait in patients and therefore study in diverse walking environments is warranted. While gait characteristics themselves are measured using a variety of sensors (e.g. Inertial Measurement Units), a ground-truth understanding of the walking terrain (necessary for the interpretation of IMU data) is traditionally identified from simple visual data. Deep Neural Networks, and in particular Convolutional Neural Networks are ideal for this classification task, but require extensive training data. Modern mobile devices include a suite of sensors capable of gathering not only images of walking terrain, but also depth data using built-in LiDAR sensors, and classifiers incorporating this multimodal data can outperform simple visual classification. We therefore present L-AVATeD: the Lidar And Visible wAlking Terrain Dataset, consisting of ~8,000 pairs of visual (RGB) and Depth (LiDAR) data. The data are divided into 9 classes of walking terrain typical of the built environments inside and surrounding North American academic and health-related institutions.
对人类步行局部场景的理解，在人体步态分析中具有重要作用。仅依靠实验室分析，会限制研究人员对患者临床步态进行准确评估的能力，因此有必要在多样化的步行环境中开展相关研究。尽管步态特征本身可通过多种传感器（如惯性测量单元（Inertial Measurement Units））进行采集，但传统上仅通过简单视觉数据来获取步行地形的地面真值（这是解读惯性测量单元数据的必要前提）。深度神经网络（Deep Neural Networks，尤其是卷积神经网络（Convolutional Neural Networks））非常适合该分类任务，但需要大量训练数据。现代移动设备配备了一套传感器，不仅可采集步行地形的图像，还可通过内置激光雷达（LiDAR）获取深度数据；融合此类多模态数据的分类器，性能优于单纯的视觉分类模型。为此我们推出了L-AVATeD数据集：即激光雷达与可见光步行地形数据集（Lidar And Visible wAlking Terrain Dataset），该数据集包含约8000组可见光（RGB）与深度（LiDAR）数据对。该数据集的步行地形共分为9类，均为北美学术机构及医疗相关机构内部及周边常见的人工建造环境地形。
