KMS Chongqing Institute of Green and Intelligent Technology, CAS
| Real-Time Object Detection Using Efficient Convolutional Networks | |
| Zhou, Xian1,2; Feng, You-Ji1; Zhou, Xi1 | |
| 2017 | |
| 摘要 | While recent object detection approaches have greatly improved the accuracy and robustness, the detection speed remains a Challenge for the community. In this paper, we propose an efficient fully convolutional network (EFCN) for real time object detection. EFCN employs the lightweight MobileNet [1] as the base network to significantly reduce the computation cost. Meanwhile, it detects objects in feature maps with multiple scales, and deploys a refining module on the top of each of these feature maps to alleviate the accuracy loss brought by the simple base network. We evaluate EFCN on the challenging KITTI [2] dataset and compare it with the state-of-the-art methods. The results show that EFCN keeps a good balance between speed and accuracy, it has 25 × fewer parameters and is up, to 31 × faster than Faster-RCNN [3] while maintaining similar or better accuracy. © 2017, Springer International Publishing AG. |
| 语种 | 英语 |
| DOI | 10.1007/978-3-319-69923-3_68 |
| 会议(录)名称 | 12th Chinese Conference on Biometric Recognition, CCBR 2017
 |
| 页码 | 633-641 |
| 通讯作者 | Zhou, Xian (1849529790@qq.com) |
| 收录类别 | EI |
| 会议地点 | Beijing, China |
| 会议日期 | October 28, 2017 - October 29, 2017 |
