arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.13339cs.CV
收藏

通过具有特定训练方法的单一多模型卷积神经网络进行目标定位

Object Localization Through a Single Multiple-Model Convolutional Neural Network with a Specific Training Approach

K. N. Toosi University of Technology(K.N.图斯工业大学)

Faraz Lotfi, Farnoosh Faraji, Hamid D. Taghirad

AI总结:

本文提出一种针对轻量级CNN的特殊训练方法及多输入尺寸结构,通过减少锚框数量确定ROI,有效提升了不同尺寸目标的定位性能并在跟踪应用中得到验证。

摘要:

目标定位在任何目标检测器中都起着至关重要的作用,因此一直受到许多研究者的关注。本文提出了一种针对轻量级卷积神经网络(CNN)的特殊训练方法,用于确定图像中的感兴趣区域(ROI),同时有效减少可能锚框的数量。几乎所有基于CNN的检测器都使用固定输入尺寸的图像,这在处理各种目标尺寸时可能导致性能不佳。本文提出了一种不同的CNN结构,采用三种不同的输入尺寸来提升性能。为了证明所提方法的有效性,使用了两个常见数据集进行训练,同时考虑了通过定位应用进行跟踪以展示其最终性能。充满希望的结果表明,所提出的结构和训练方法在实际中具有适用性。

英文摘要:

Object localization has a vital role in any object detector, and therefore, has been the focus of attention by many researchers. In this article, a special training approach is proposed for a light convolutional neural network (CNN) to determine the region of interest (ROI) in an image while effectively reducing the number of probable anchor boxes. Almost all CNN-based detectors utilize a fixed input size image, which may yield poor performance when dealing with various object sizes. In this paper, a different CNN structure is proposed taking three different input sizes, to enhance the performance. In order to demonstrate the effectiveness of the proposed method, two common data set are used for training while tracking by localization application is considered to demonstrate its final performance. The promising results indicate the applicability of the presented structure and the training method in practice.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑