[2008.05416] DXSLAM: A Robust and Efficient Visual SLAM System with Deep Featuresopen searchopen navigation menucontact arXivsubscribe to arXiv mailings

A robust and efficient Simultaneous Localization and Mapping (SLAM) system is essential for robot autonomy. For visual SLAM algorithms, though the theoretical framework has been well established for most aspects, feature extraction and association is still empirically designed in most cases, and can be vulnerable in complex environments. This paper shows that feature extraction with deep convolutional neural networks (CNNs) can be seamlessly incorporated into a modern SLAM framework. The proposed SLAM system utilizes a state-of-the-art CNN to detect keypoints in each image frame, and to give not only keypoint descriptors, but also a global descriptor of the whole image. These local and global features are then used by different SLAM modules, resulting in much more robustness against environmental changes and viewpoint changes compared with using hand-crafted features. We also train a visual vocabulary of local features with a Bag of Words (BoW) method. Based on the local features, glob

1 mentions: @ddetone
Date: 2020/08/20 02:21

Referring Tweets

@ddetone DXSLAM: A Robust and Efficient Visual SLAM System with Deep Features t.co/soxBCx8R32 tldr; Improved SLAM robustness when you combine the efficient HF-Net (distilled SuperPoint+NetVLAD) with an ORB-SLAM2 framework. Open-source code available t.co/YZS2XuSVuc

Bookmark Comments

Related Entries

Read more Ray — Ray 0.9.0.dev0 documentation
3 users, 0 mentions 2020/01/15 17:21
Read more GitHub - sikang/mpl_ros: A ROS wrapper for trajectory planning based on motion primitives
1 users, 0 mentions 2020/05/26 09:51
Read more Rapid Iron-On User Interfaces: Hands-on Fabrication of Interactive Textile Prototypes | Interactive ...
1 users, 0 mentions 2020/06/23 05:21
Read more "Recent Progress on Atlas, the World’s Most Dynamic Humanoid Robot" - Scott Kuindersma - YouTube
1 users, 0 mentions 2020/10/13 13:01
Read more GitHub - MichaelBeechan/VO-SLAM-Review: SLAM is mainly divided into two parts: the front end and the...
1 users, 0 mentions 2020/10/19 02:21