期刊
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
卷 -, 期 -, 页码 6325-6333出版社
IEEE
DOI: 10.1109/CVPR.2018.00662
关键词
-
资金
- NSF [IIS-1421435, CHS-1617236]
Local feature detection is a fundamental task in computer vision, and hand-crafted feature detectors such as SIFT have shown success in applications including image-based localization and registration. Recent work has used features detected in texture images for precise global localization, but is limited by the performance of existing feature detectors on textures, as opposed to natural images. We propose an effective and scalable method for learning feature detectors for textures, which combines an existing ranking loss with an efficient fully-convolutional architecture as well as a new training-loss term that maximizes the peakedness of the response map. We demonstrate that our detector is more repeatable than existing methods, leading to improvements in a real-world texture-based localization application.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据