当前位置: X-MOL 学术Symmetry › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Novel Joint Object Detection Algorithm Using Cascading Parallel Detectors
Symmetry ( IF 2.940 ) Pub Date : 2021-01-15 , DOI: 10.3390/sym13010137
Zihan Zhou , Qinghan Lai , Shuai Ding , Song Liu

Object detection is an essential computer vision task that aims to detect target objects from an image. The traditional models are insufficient to generate a high-quality anchor box. To solve the problem, we propose a novel joint model called guided anchoring Region proposal networks and Cascading Grid Region Convolutional Neural Networks (RCGrid R-CNN), enhancing the ability of object detection. Our proposed model design is a joint object detection algorithm containing an anchor-based and an anchor-free branch in parallel and symmetry. In the anchor-based, we use nine-point spatial information fusion to obtain better anchor box location and introduce the shape prediction method of Guided Anchoring Region Proposal Networks (GA-RPN) to enhance the accuracy of the predicted anchor box. In the anchor-free branch, we introduce the Feature Selective Anchor-Free module (FSAF) to reduce the overlapping anchor boxes to obtain a more accurate anchor box. Furthermore, inspired by cascading theory, we cascade the new-designed detectors to improve the ability of object detection by setting a gradually increasing Intersection over Union (IoU) threshold. Compared with typical baseline models, we comprehensively evaluated our model by conducting experiments on two open datasets: Pascal VOC2007 and COCO2017. The experimental results demonstrate the effectiveness of RCGrid R-CNN in producing a high-quality anchor box.

中文翻译:

级联并行检测器的新型联合目标检测算法

对象检测是一项基本的计算机视觉任务,旨在从图像中检测目标对象。传统模型不足以生成高质量的锚框。为了解决该问题,我们提出了一种新颖的联合模型,称为引导锚定区域提议网络和级联网格区域卷积神经网络(RCGrid R-CNN),以增强对象检测的能力。我们提出的模型设计是一种联合对象检测算法,该算法包含平行且对称的基于锚点和无锚点的分支。在基于锚点的情况下,我们使用九点空间信息融合来获得更好的锚点框位置,并引入了导向锚定区域提议网络(GA-RPN)的形状预测方法,以提高预测的锚点框的准确性。在免锚分支中,我们引入了特征选择性无锚模块(FSAF),以减少重叠的锚框,从而获得更准确的锚框。此外,受级联理论的启发,我们将新设计的检测器进行级联,以通过设置逐渐增加的“相交交叉”(IoU)阈值来提高物体检测的能力。与典型的基线模型相比,我们通过在两个开放数据集上进行实验对Pascal VOC2007和COCO2017进行了全面评估。实验结果证明了RCGrid R-CNN在生产高质量锚盒中的有效性。我们通过设置逐渐增加的“相交交叉点”(IoU)阈值来级联新设计的检测器,以提高物体检测的能力。与典型的基线模型相比,我们通过在两个开放数据集上进行实验对Pascal VOC2007和COCO2017进行了全面评估。实验结果证明了RCGrid R-CNN在生产高质量锚盒中的有效性。我们通过设置逐渐增加的“相交超过”(IoU)阈值来级联新设计的检测器,以提高物体检测的能力。与典型的基准模型相比,我们通过在两个开放数据集上进行实验来全面评估模型:Pascal VOC2007和COCO2017。实验结果证明了RCGrid R-CNN在生产高质量锚盒中的有效性。
更新日期:2021-01-15
down
wechat
bug