| 基于级联卷积神经网络的高效目标检测方法 |
| |
| 引用本文： | 宋云博,陈冬艳,郝赟,付先平. 基于级联卷积神经网络的高效目标检测方法[J]. 计算机工程与应用, 2021, 57(5): 139-145. DOI: 10.3778/j.issn.1002-8331.1911-0215 |
| |
| 作者姓名： | 宋云博 陈冬艳 郝赟 付先平 |
| |
| 作者单位： | 大连海事大学 信息科学技术学院，辽宁 大连 116026 |
| |
| 基金项目： | 中国博士后基金;交通运输部基础研究基金;国家自然科学基金;中央高校基本科研业务费专项资金 |
| |
| 摘 要： | 目标检测作为计算机视觉的重要研究方向,在智慧城市、无人驾驶等领域的作用越来越重要.传统目标检测算法中,根据交并比(Intersection over Union,IOU)的大小判断正负样本,但较低的IOU会引入噪声,降低检测器的精度;较高的IOU会保留少数高质量样本,造成过拟合;并且推荐区域和检测器的IOU阈值相差过大...
|
| 关 键 词： | 卷积神经网络 深度学习 级联网络 高精度目标检测 |
Efficient Object Detection Method Based on Cascaded Convolutional Neural Network |
| |
| SONG Yunbo,CHEN Dongyan,HAO Yun,FU Xianping. Efficient Object Detection Method Based on Cascaded Convolutional Neural Network[J]. Computer Engineering and Applications, 2021, 57(5): 139-145. DOI: 10.3778/j.issn.1002-8331.1911-0215 |
| |
| Authors: | SONG Yunbo CHEN Dongyan HAO Yun FU Xianping |
| |
| Affiliation: | College of Information Science and Technology, Dalian Maritime University, Dalian, Liaoning 116026, China |
| |
| Abstract: | As an important research direction of computer vision, object detection plays an increasingly important role in smart cities and unmanned driving. In traditional object detection algorithms, it judges positive and negative samples according to the threshold value of the Intersection over Union（IOU）. Some lower IOU will introduce noise and reduce the accuracy of the detector, and higher IOU will retain some high-quality samples, resulting in over-fitting. The difference between the IOU threshold of the recommended area and the detector will cause quality mismatch. In response to these problems, this paper proposes a parallel cascaded detection network based on cascaded network, which is composed of various of detectors connected in series and in parallel. Every of each detector sets an incremental IOU threshold, thus at each stage a higher quality distribution is obtained to train the next detector and gradually resample to reduce overfitting. The experimental results show that the proposed parallel cascaded detection network is better than the traditional object detection algorithm in detection precision. The average Accuracy Precision（AP） of the object detection dataset Microsoft COCO is increased by about 1.5 percentage points using the proposed parallel detection network. |
| |
| Keywords: | convolutional neural network deep learning cascaded network high-precision object detection |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载免费的PDF全文 |
|
