Object Detection for Sweeping Robots in Home Scenes (ODSR-IHS): A Novel Benchmark Dataset

Object detection plays an important role in computer vision. It has a variety of applications, including security detection, vehicle recognition, and service robots. With the continuous improvement public databases development deep learning, object witnessed significant breakthroughs. However, sweeping robots during operations should consider various factors, camera angle, indoor scenery, identification category. To best our knowledge, no corresponding database on these conditions been developed. In this study, we review based learning Then, propose large-scale publicly available benchmark dataset called for home scenes (ODSR-IHS). The 6,000 images 16,409 instances 14 categories. Finally, evaluate several state-of-the-art methods ODSR-IHS transplant them to hardware establish recognition research