南京大学学报（自然科学版）2019，Vol.55Issue(1)：73-84,12.DOI:10.13232/j.cnkij.nju.2019.01.007
结合目标检测的小目标语义分割算法
A small obj ect semantic segmentation algorithm combined with obj ect detection
摘要
Abstract
Convolutional Neural Networks (CNN)can provide classifiers which are more powerful than traditional classification methods and can automatically learn deep features,which significantly improve the accuracy of image semantic segmentation.However,these semantic segmentation methods based on CNNs still have some challenges, such as the difficulty in segmenting the small objects in the complex scenes.In this paper,we proposed a semantic segmentation algorithm for small objects combined with obj ect detection,aiming to solve the segmentation challenges of small objects.This work does not directly use a single neural network to segment both small-sized and large-sized obj ects simultaneously.Instead,it separates the small object segmentation task from the complete image segmenta-tion task and trains an object detection model to obtain small obj ect image blocks.A small object segmentation network is designed to get the small object segmentation results,and the results are used to modify the overall image segmentation results.The modified segmentation maps have a better segmentation performance on small objects.关键词
图像语义分割/小目标分割/卷积神经网络/目标检测Key words
image semantic segmentation/small objects segmentation/convolutional neural networks/obj ect detection分类
信息技术与安全科学引用本文复制引用
胡太,杨明..结合目标检测的小目标语义分割算法[J].南京大学学报（自然科学版）,2019,55(1):73-84,12.基金项目
国家自然科学基金重点项目(61432008),国家自然科学基金(61876087,61272222),赛尔网络下一代互联网技术创新项目(NGII20170524) （61432008）
