ExoNet Database: Wearable Camera Images of Human Locomotion Environments

Advances in robotic vision and artificial intelligence have enabled researchers to develop environment recognition systems for lower-limb exoskeletons and prostheses. However, insufficient and private training datasets have impeded the widespread development and dissemination of image classification algorithms. To address these shortcomings, we have developed the ExoNet Database, the first open-source database of high-quality wearable RGB camera images of human locomotion environments. Using a lightweight wearable smartphone camera system, over 5.6 million images of indoor and outdoor real-world walking environments were collected throughout summer, autumn, and winter seasons. Approximately 940,000 images of ExoNet Database were human-annotated using a 12-classs hierarchical image classification architecture. Images were uploaded to IEEE DataPort and are publicly available for download. The ExoNet Database offers an unprecedented shared platform for training, developing, and comparing next-generation image classification algorithms. Beyond the control of lower-limb exoskeletons and prostheses, applications extend to other assistive technologies (e.g., powered wheelchairs) and humanoids and autonomous legged robotics.Reference: Laschowski B, McNally W, Wong A, and McPhee J. (2020). ExoNet Database: Wearable Camera Images of Human Locomotion Environments. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. In Preparation.

机器人视觉与人工智能领域的进展，已助力研究者开发出适用于下肢外骨骼（lower-limb exoskeletons）与假肢（prostheses）的环境识别系统。然而，训练数据集的匮乏与私有化问题，阻碍了图像分类算法的大规模开发与推广。为解决上述缺陷，我们构建了ExoNet数据库（ExoNet Database）——首个开源的、高质量人类行走环境可穿戴RGB相机图像数据库。借助轻量化可穿戴智能手机相机系统，我们在夏季、秋季与冬季三个季节，采集了超过560万张真实室内外行走环境的图像。其中约94万张图像采用12类层级化图像分类架构完成人工标注。该数据集已上传至IEEE数据港（IEEE DataPort），可公开下载获取。ExoNet数据库为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共享平台。除下肢外骨骼与假肢的控制场景外，其应用范围还拓展至其他辅助技术领域（例如电动轮椅）、类人机器人以及自主腿式机器人。参考文献：Laschowski B, McNally W, Wong A, 与 McPhee J. (2020). ExoNet数据库：人类行走环境的可穿戴相机图像. IEEE工程医学与生物学学会年度国际会议. 待刊。