Design and Implementation of an Object Detection System Using Faster R-CNN

被引：9

作者：

Wang Cheng ^{[1
]}

Peng Zhihao ^{[2
]}

机构：

[1] Dalian Neusoft Univ Informat, Shool Digital Arts & Design, Dalian 116626, Peoples R China

[2] Dalian Neusoft Univ Informat, Shool Comp & Software, Dalian 116626, Peoples R China

来源：

2019 INTERNATIONAL CONFERENCE ON ROBOTS & INTELLIGENT SYSTEM (ICRIS 2019) | 2019年

关键词：

Regional proposal approach; Object detection; Convolutional Neural Network;

D O I：

10.1109/ICRIS.2019.00060

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Recent development in object detection are greatly driven by the success of region proposal approaches and region-based convolutional neural networks (R-CNNs). In this paper, we designed and implemented an object detection system using a faster-CNN method that shares full-image convolutional features with a detection network, so as to enable nearly cost-free region proposals. Development of this system is based on the previous work on Faster R-CNN. Results shows that with this method, we could achieve high accuracy while detecting objects.

引用

页码：204 / 206

页数：3