In robotic bin-picking applications, the perception of texture-less, highly reflective parts is a valuable but challenging task. The high glossiness can introduce fake edges in RGB images and inaccurate depth measurements especially in heavily cluttered bin scenario. In this paper, we present the ROBI (Reflective Objects in BIns) dataset, a public dataset for 6D object pose estimation and multi-view depth fusion in robotic bin-picking scenarios. The ROBI dataset includes a total of 63 bin-picking scenes captured with two active stereo camera: a high-cost Ensenso sensor and a low-cost RealSense sensor. For each scene, the monochrome/RGB images and depth maps are captured from sampled view spheres around the scene, and are annotated with accurate 6D poses of visible objects and an associated visibility score. For evaluating the performance of depth fusion, we captured the ground truth depth maps by high-cost Ensenso camera with objects coated in anti-reflective scanning spray. To show the utility of the dataset, we evaluated the representative algorithms of 6D object pose estimation and multi-view depth fusion on the full dataset. Evaluation results demonstrate the difficulty of highly reflective objects, especially in difficult cases due to the degradation of depth data quality, severe occlusions and cluttered scene. The ROBI dataset is available online at https://www.trailab.utias.utoronto.ca/robi.
翻译:在机器人浏览器中,对无纹理、高反射部件的感知是一项宝贵但具有挑战性的任务。高光度可能会在 RGB 图像中引入假边缘和不准确的深度测量,特别是在严重杂乱的 bin 情景中。在本文中,我们展示了 ROBI (BIns 中的实时对象) 数据集, 6D 对象的公开数据集在机器人浏览器中包含估计和多视图深度混集。 ROBI 数据集包含总共63 个以两种活跃的立体相机拍摄的垃圾抓取场景: 高成本 Ensenso 传感器和 低成本 RealSense 传感器。 对于每个场景, 单色/ RGB 图像和深度测量都来自现场的抽样查看范围, 并附有准确的 6D 可见对象配置和相关可见度评分。 为了评估深度的深度, 我们通过高成本的 Esenso 摄像头拍摄了地面真相深度地图, 涂有反反光谱扫描喷雾器的物体。 为了展示数据集的效用, 我们评估了6-D 深度 深度 深度数据 的深度 的深度分析, 的深度分析 的深度数据, 的深度分析 的深度分析 的深度分析 的深度, 的深度分析