On Improving the Accuracy of Object Detection for High Resolution Images Based on SSD
On Improving the Accuracy of Object Detection for High Resolution Images Based on SSD
复制标题
基于SSD提高高分辨率图像目标检测精度的研究
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
K. Nishikawa
中科院分区：
文献类型：
--
作者：
Kei Irie;Yicheng Qiu;K. Nishikawa
在本文中，我们考虑使用SSD（单镜头多盒检测器）提高目标检测的准确性。SSD是众所周知的，它可以执行搜索的区域候选和分类的对象在一个单一的过程。SSD的一个问题是，如果物体不大于一定的尺寸，精度就会下降。为了解决这个问题，我们提出了一种方法来提高目标检测的准确性，通过扩展传统的方法。虽然所提出的方法应用的SSD后的图像的分割，如在传统的一个，不同的是，SSD执行仅使用来自网络的部分信息。这使我们能够检测使用标准SSD无法检测到的小物体。然后，使用未分割图像的检测结果和分割图像后的结果来校正区域度量。计算机仿真结果表明了该方法的有效性。
In this paper, we consider improving the accuracy of object detection using SSD (Single Shot multibox Detector). SSD is well known that it can execute the searching of region candidate and classifying the objects in a single process. One of the problems of the SSD is that if the object is not larger than a certain size, the accuracy will decrease. To solve this problem, we propose a method to improve the accuracy of the object detection by extending a conventional method. Although the proposed method applies the SSD after the segmentation of the image as in the conventional one, the difference is that SSD is performed using only partial information from the network. This allows us to detect small objects that could not be detected using the standard SSD. Then, region metrics are corrected using the result of detection without image segmentation and the result after image segmentation. The effectiveness of the proposed method is shown through the computer simulations.