Indoor object detection is a very demanding and important task for robot applications. Object knowledge, such as two-dimensional (2D) shape and depth information, may be helpful for detection. In this article, we focus on region-based convolutional neural network (CNN) detector and propose a geometric property-based Faster R-CNN method (GP-Faster) for indoor object detection. GP-Faster incorporates geometric property in Faster R-CNN to improve the detection performance. In detail, we first use mesh grids that are the intersections of direct and inverse proportion functions to generate appropriate anchors for indoor objects. After the anchors are regressed to the regions of interest produced by a region proposal network (RPN-RoIs), we then use 2D geometric constraints to refine the RPN-RoIs, in which the 2D constraint of every classification is a convex hull region enclosing the width and height coordinates of the ground-truth boxes on the training set. Comparison experiments are implemented on two indoor datasets SUN2012 and NYUv2. Since the depth information is available in NYUv2, we involve depth constraints in GP-Faster and propose 3D geometric property-based Faster R-CNN (DGP-Faster) on NYUv2. The experimental results show that both GP-Faster and DGP-Faster increase the performance of the mean average precision.

对于机器人应用而言，室内物体检测是一项非常艰巨且重要的任务。诸如二维（2D）形状和深度信息之类的对象知识可能有助于检测。在本文中，我们重点研究基于区域的卷积神经网络（CNN）检测器，并提出了一种基于几何属性的Faster R-CNN方法（GP-Faster）用于室内物体检测。GP-Faster在Faster R-CNN中合并了几何属性，以提高检测性能。详细地说，我们首先使用作为正比例函数和反比例函数的交集的网格，以生成适合室内对象的锚点。在将锚点回归到区域提案网络（RPN-RoIs）生成的感兴趣区域后，然后我们使用2D几何约束来细化RPN-RoI，其中每个分类的2D约束是一个凸包区域，其中包含训练集上地面实线框的宽度和高度坐标。在两个室内数据集SUN2012和NYUv2上进行了比较实验。由于可以在NYUv2中获得深度信息，因此我们在GP-Faster中涉及深度约束，并在NYUv2上提出基于3D几何属性的Faster R-CNN（DGP-Faster）。实验结果表明，GP-Faster和DGP-Faster均可提高平均平均精度的性能。我们在GP-Faster中涉及深度约束，并在NYUv2上提出了基于3D几何属性的Faster R-CNN（DGP-Faster）。实验结果表明，GP-Faster和DGP-Faster均可提高平均平均精度的性能。我们在GP-Faster中涉及深度约束，并在NYUv2上提出了基于3D几何属性的Faster R-CNN（DGP-Faster）。实验结果表明，GP-Faster和DGP-Faster均可提高平均平均精度的性能。