图像扭曲
视觉里程计
计算机视觉
人工智能
动态时间归整
卷积神经网络
运动(物理)
帧(网络)
计算机科学
运动估计
一致性(知识库)
匹配(统计)
人工神经网络
深度学习
模式识别(心理学)
数学
机器人
统计
电信
作者
J. K. K. Tang,John Folkesson,Patric Jensfelt
出处
期刊:IEEE robotics and automation letters
日期:2018-04-01
卷期号:3 (2): 1010-1017
被引量:52
标识
DOI:10.1109/lra.2018.2794624
摘要
In this paper, we propose a new learning scheme for generating geometric correspondences to be used for visual odometry. A convolutional neural network (CNN) combined with a recurrent neural network (RNN) are trained together to detect the location of keypoints as well as to generate corresponding descriptors in one unified structure. The network is optimized by warping points from source frame to reference frame, with a rigid body transform. Essentially, learning from warping. The overall training is focused on movements of the camera rather than movements within the image, which leads to better consistency in the matching and ultimately better motion estimation. Experimental results show that the proposed method achieves better results than both related deep learning and hand crafted methods. Furthermore, as a demonstration of the promise of our method we use a naive SLAM implementation based on these keypoints and get a performance on par with ORB-SLAM.
科研通智能强力驱动
Strongly Powered by AbleSci AI