Deep learning has made significant breakthroughs in the tasks of image classification, detection, segmentation, etc. However, the application of deep learning in robotics is still scarce. SLAM is a fundamental problem in robotics and loop closure detection is an important part of SLAM. This paper attempts to use supervised learning methods to solve the loop closure detection problem in vision SLAM. We proposed Siamese-ResNet network, which combines Siamese network with ResNet to detect loop closure. To show the effectiveness of Siamese-ResNet, we evaluate Siamese-ResNet and FabMap2.0 on several open published datasets, like TUM SLAM dataset and FabMap SLAM dataset. Compared with FabMap2.0, Siamese-ResNet shows higher accuracy, better robustness and shorter time-consuming.
Siamese-ResNet: Implementing Loop Closure Detection based on Siamese Network
2018-06-01
7181026 byte
Conference paper
Electronic Resource
English
SIAMESE-RESNET: IMPLEMENTING LOOP CLOSURE DETECTION BASED ON SIAMESE NETWORK
British Library Conference Proceedings | 2018
|Engineering Index Backfile | 1907
Engineering Index Backfile | 1904
MPSiam: A Fast Multiplexing Siamese Tracking Network
TIBKAT | 2022
|MPSiam: A Fast Multiplexing Siamese Tracking Network
Springer Verlag | 2021
|