MT-DSSD: multi-task deconvolutional single shot detector for object detection, segmentation, and grasping detection
MT-DSSD: multi-task deconvolutional single shot detector for object detection, segmentation, and grasping detection
复制标题
DOI：
10.1080/01691864.2022.2043183
复制
发表时间：
2022-03
影响因子：
2
通讯作者：
Ryosuke Araki;Tsubasa Hirakawa;Takayoshi Yamashita;H. Fujiyoshi
中科院分区：
文献类型：
--
作者：
Ryosuke Araki;Tsubasa Hirakawa;Takayoshi Yamashita;H. Fujiyoshi
在物流仓库中挑选和放置各种物品的机器人必须从图像中检测和识别物品，然后决定抓住哪些点。我们的多任务去卷积单枪检测器(MT-DSSD)同时执行这种操作所需的三个任务：目标检测、语义分割和抓取检测。MT-DSSD是一种基于DSSD的多任务学习(MTL)方法，与单独的模型执行每个任务相比，它减少了计算量，并获得了较高的速度。使用Amazon Robotics Challenges数据集进行的评估表明，我们的模型比同类方法具有更好的目标检测和分割性能，而消融研究表明MTL可以提高每项任务的准确性。此外，机器人抓取实验表明，该模型可以检测到合适的抓取点。图形摘要
A robot that picks and places the wide variety of items in a logistics warehouse must detect and recognize items from images and then decide which points to grasp. Our Multi-task Deconvolutional Single Shot Detector (MT-DSSD) simultaneously performs the three tasks necessary for this manipulation: object detection, semantic segmentation, and grasping detection. MT-DSSD is a multi-task learning (MTL) method based on DSSD that reduces the amount of computation and achieves high speed compared to when separate models perform each task. Evaluations using the Amazon Robotics Challenge dataset showed that our model has a better object detection and segmentation performance than comparable methods, and an ablation study showed that MTL could improve the accuracy of each task. Further, robotic experiments for grasping demonstrated that our model could detect the appropriate grasping point. GRAPHICAL ABSTRACT