上下文信息在目标检测算法中的应用
黄龙飞
摘要(Abstract):
<正>随着人工智能的发展,计算机视觉在其中扮演着一个重要的角色。尤其在自动驾驶、医疗图像、VR等技术领域当中,对图像识别、目标检测等任务的标准有了更高的要求。本文针对上下文信息在目标检测任务中发挥的作用,分别基于传统机器学习的目标检测任务和基于深度学习的目标检测任务,通过上下文建模方法的分析和模型的对比,概述了上下文信息在当中的应用和发展。
关键词(KeyWords):
基金项目(Foundation):
作者(Author): 黄龙飞
DOI: 10.19353/j.cnki.dzsj.2020.02.014
参考文献(References):
- Lin,Tsung-Yi,et al."Feature pyramid networks for object detection."Proceedings of the IEEE conference on computer vision and pattern recognition.2017;
- Gidaris,Spyros,and Nikos Komodakis."Object detection via a multi-region and semantic segmentation-aware cnn model."Proceedings of the IEEE international conference on computer vision.2015;
- Bae SH.Object Detection based on Region Decomposition and Assembly[J].ar Xiv preprint ar Xiv:1901.08225,2019;
- Hu,Han,et al."Relation networks for object detection."Computer Vision and Pattern Recognition(CVPR).Vol.2.No.3.2018;
- Liu,Yong,et al."Structure inference net:Object detection using scene-level context and instance-level relationships."Proceedings of the IEEE conference on computer vision and pattern recognition.2018。