ATFVO: An Attentive Tensor-compressed LSTM Model with Optical Flow Features for Monocular Visual Odometry

Hongwei Ren; Chenghao Li; Xinyi Zhang; Chenchen Ding; Changhai Man; Hao Yu

10.1109/WRCSARA53879.2021.9612673

2021-11-19

2021 WRC Symposium on Advanced Robotics and Automation (WRC SARA)

978-1-6654-1824-9

2021 WRC Symposium on Advanced Robotics and Automation (WRC SARA)

79-85

2021-09-11

Beijing

This paper proposes a new framework called ATFVO which can be deployed on the edge device to resolve monocular visual odometry problem. The vast majority of visual odometry algorithms using deep learning are equivalent to or beyond the traditional visual odometry algorithms in performance, however they do not consider the computing capability of edge equipment. In this paper, convolution neural network (CNN) and attentive tensor-compressed compression LSTM (A-T-LSTM) are used, with optical flow feature as input and a 6-DoF absolute-scale pose as output. The framework is fused with the spatio-temporal feature and deal with the overfitting problem of over-parameterized LSTM with high-dimensional inputs, and utilizes attention mechanism to get poses from the sequence output of T-LSTM. The poses are estimated from the original RGB images sequence without depending on any prior knowledge. The experimental outcomes at the KITTI dataset display that, in compared with the performance of the most advanced methods, the single T-LSTM model is 141× smaller than the original LSTM model, and the entire model is nearly one-seventh of DeepVO with a speed 23× faster than Flowdometry. The proposed VO is deployed to the robot based on raspberry pi, which can achieve real-time inference and navigate a cruise.

Performance evaluation Deep learning Navigation Convolution Neural networks Real-time systems Image sequences

第一 ; 通讯

EI

20220411524111

Computer vision ; Optical flows ; Tensors ; Vision

Computer Applications:723.5 ; Light/Optics:741.1 ; Vision:741.2 ; Algebra:921.1

人工提交

Southern University of Science and Technology

Hongwei Ren,Chenghao Li,Xinyi Zhang,et al. ATFVO: An Attentive Tensor-compressed LSTM Model with Optical Flow Features for Monocular Visual Odometry[C],2021:79-85.