ExoNet Database: Wearable Camera Images of Human Locomotion Environments

Abstract: Recent advances in computer vision and artificial intelligence have allowed researchers to develop environment recognition systems for robotic lower-limb exoskeletons and prostheses. However, small-scale and private training datasets have impeded the widespread development and dissemination of image classification algorithms for human locomotion environment recognition. To address these shortcomings, we developed “ExoNet” - the first open-source, large-scale hierarchical database of high-resolution wearable camera images of human locomotion environments. Unparalleled in both scale and diversity, ExoNet comprises over 5.6 million images of different indoor and outdoor real-world walking environments, which were collected using a lightweight wearable smartphone camera system during the summer, fall, and winter seasons. Approximately 940,000 images in ExoNet were human-annotated using a 12-class hierarchical labelling architecture. Available publicly through IEEE DataPort, ExoNet offers an unprecedented community-based platform to train, develop, and compare next-generation image classification algorithms for human locomotion environment recognition. Beyond the control of lower-limb exoskeletons and prostheses, applications of ExoNet extend to humanoid and autonomous legged robotics.Reference: Laschowski B, McNally W, Wong A, and McPhee J. (2020). ExoNet Database: Wearable Camera Images of Human Locomotion Environments. In Preparation.

摘要：近年来计算机视觉与人工智能领域的进展，推动了机器人下肢外骨骼及假肢的环境识别系统研发。然而，小规模且私有性质的训练数据集，阻碍了面向人类运动环境识别的图像分类算法的广泛开发与推广应用。为解决上述局限，我们构建了“ExoNet”——首个开源、大规模的高分辨率可穿戴相机拍摄的人类运动环境图像分层数据库。该数据库在规模与多样性上均无与伦比，包含超过560万张涵盖不同室内外真实步行环境的图像，采集工作于夏、秋、冬三季通过轻量化可穿戴智能手机相机系统完成。其中约94万张图像采用12类分层标注架构完成人工标注。ExoNet通过IEEE数据港（IEEE DataPort）对外公开，为面向人类运动环境识别的下一代图像分类算法的训练、开发与对比提供了前所未有的社区化平台。除用于下肢外骨骼与假肢的控制外，ExoNet的应用场景还可拓展至人形机器人与自主足式机器人领域。参考文献：Laschowski B, McNally W, Wong A, 及 McPhee J. (2020). ExoNet 数据库：人类运动环境可穿戴相机图像. 待刊.