Reliability-grasping detection of an object in a complex scene is a challenging task and is a critical problem that needs to be solved urgently in practical application. At present, the grasp position is obtained through the feature analysis of the whole input image. However, the clutter background information in the image impairs the accuracy of grasping detection. In this paper, a robotic grasp detection algorithm named MASK-GD (grasp detection based on mask region) is proposed, which provides a feasible solution to this problem. MASK is a segmented image that only contains the pixels of the target object. MASK-GD for grasp detection only uses the features of the MASK area rather than the features of the entire image in the scene. It has two stages: the first stage is to provide the MASK area of the target object, and the second stage is a grasp detector based on the features of the MASK area. Experimental results demonstrate that the performance of MASK-GD is comparable with state-of-the-art grasp detection algorithms on Cornell Grasp Dataset and Jacquard Dataset. In the meantime, MASK-GD performs much better in complex scenes.

复杂场景中物体的可靠性抓取检测是一项具有挑战性的任务，是实际应用中急需解决的关键问题。目前，抓握位置是通过对整个输入图像的特征分析得到的。然而，图像中杂乱的背景信息损害了抓取检测的准确性。本文提出了一种机器人抓取检测算法MASK-GD（基于掩模区域的抓取检测），为该问题提供了可行的解决方案。MASK 是仅包含目标对象像素的分割图像。用于抓取检测的 MASK-GD 仅使用 MASK 区域的特征，而不是场景中整个图像的特征。它有两个阶段：第一阶段是提供目标物体的MASK区域，第二阶段是基于 MASK 区域特征的抓取检测器。实验结果表明，MASK-GD 的性能可与 Cornell Grasp 数据集和 Jacquard 数据集上的最新抓取检测算法相媲美。同时，MASK-GD 在复杂场景中的表现要好得多。