期刊文献+

WeBox:locating small objects from weak edges 被引量:2

原文传递
导出
摘要 In the object detection task,how to better deal with small objects is a great challenge.The detection accuracy of small objects greatly affects the final detection performance.Our propose a detection framework We Box based on weak edges for small object detection in dense scenes,and proposes to train the richer convolutional features(RCF)edges detection network in a weakly supervised way to generate multi-instance proposals.Then through the region proposal network(RPN)network to locate each object in the multi-instance proposals,in order to ensure the effectiveness of the multi-instance proposals,we correspondingly proposed a multi-instance proposals evaluation criterion.Finally,we use faster region-based convolutional neural network(R-CNN)to process We Box single-instance proposals and fine-tune the final results at the pixel level.The experiments have been carried out on BDCI and TT100 K proves that our method maintains high computational efficiency while effectively improving the accuracy of small objects detection.
作者 CHAN Sixian LIU Peng ZHANG Zhuo 产思贤;刘鹏;张卓(College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 31000,China)
出处 《Optoelectronics Letters》 EI 2021年第6期349-353,共5页 光电子快报(英文版)
基金 supported by the National Natural Science Foundation of China(No.61906168)。
  • 相关文献

同被引文献1

引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部