Wood logs picking is a challenging task to automate. Indeed, logs usually come in cluttered configurations, randomly orientated and overlapping. Recent work on log picking automation usually assume that the logs' pose is known, with little consideration given to the actual perception problem. In this paper, we squarely address the latter, using a data-driven approach. First, we introduce a novel dataset, named TimberSeg 1.0, that is densely annotated, i.e., that includes both bounding boxes and pixel-level mask annotations for logs. This dataset comprises 220 images with 2500 individually segmented logs. Using our dataset, we then compare three neural network architectures on the task of individual logs detection and segmentation; two region-based methods and one attention-based method. Unsurprisingly, our results show that axis-aligned proposals, failing to take into account the directional nature of logs, underperform with 19.03 mAP. A rotation-aware proposal method significantly improve results to 31.83 mAP. More interestingly, a Transformer-based approach, without any inductive bias on rotations, outperformed the two others, achieving a mAP of 57.53 on our dataset. Our use case demonstrates the limitations of region-based approaches for cluttered, elongated objects. It also highlights the potential of attention-based methods on this specific task, as they work directly at the pixel-level. These encouraging results indicate that such a perception system could be used to assist the operators on the short-term, or to fully automate log picking operations in the future.
翻译:木材日志的采集是自动化的艰巨任务。 事实上, 日志通常以杂乱的配置形式出现, 随机调整和重叠。 最近关于记录采集自动化的工作通常假设日志的外形已经为人所知, 很少考虑到实际的感知问题 。 在本文中, 我们用数据驱动的方法直截了当地处理后一种问题。 首先, 我们引入了一个新的数据集, 名为 TimberSeg 1.0, 这个数据集, 既包括捆绑框, 也包括对日志的像素级遮罩说明。 这个数据集由220 个图像组成, 配有 2500 个单项的日志 。 更有趣的是, 我们用我们的数据集来比较三个神经网络结构结构结构结构结构结构结构, 而不是直接显示我们系统对具体日志的偏差。 我们的结果显示, 轴校正一致的建议, 无法考虑到日志的定向性质, 这些基于19.03 mAP 。 旋转认知建议的方法可以大大改进结果到 31. 83 mperAP 。 更有意思的是, 以 转换为基于 eal- e- eal- bal- leglegleglegal 方法, 在单个操作上, 在不直接使用任何方向上, 方向上, 在任何特定的操作中, 在任何方向上, 方向上, 方向上, 方向上, 方向上, 在任何方向偏差偏差的操作中, 方向上, 方向上, 显示我们对等操作 显示我们 方向 方向选择 方向方向 方向 方向 方向 方向 方向 方向 方向 方向 方向 方向 方向 方向 方向 。