Image Gradient-based Joint Direct Visual Odometry for Stereo Camera

Authors: Jianke Zhu

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We have conducted the experimental evaluation on the challenging KITTI odometry benchmark, whose promising results show that the proposed algorithm is very effective for stereo visual odometry.In this section, we give details of our experimental implementation and discuss the results of visual odometry.To examine the empirical efficacy of the proposed stereo visual odometry approach, we conduct the experiments for comprehensive performance evaluations on KITTI odometry benchmark [Geiger et al., 2012].
Researcher Affiliation Collaboration Jianke Zhu1,2 1College of Computer Science, Zhejiang University, Hangzhou, China 2Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies jkzhu@zju.edu.cn
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described in this paper.
Open Datasets Yes To examine the empirical efficacy of the proposed stereo visual odometry approach, we conduct the experiments for comprehensive performance evaluations on KITTI odometry benchmark [Geiger et al., 2012].
Dataset Splits No There are 11 sequences (00-10) with ground truth poses for training, and 11 sequences (11-21) for testing.
Hardware Specification Yes All of our experiments were carried out on a PC with Intel Core i7-3770 3.8GHz processor and 8GB RAM using single thread.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers.
Experiment Setup Yes To facilitate the multi-scale optimization, we build a 4-level image pyramid.Moreover, the disparity map is calculated by 5 5 block matching with SAD.For the proposed joint direct stereo visual odometry approach, we retain a circular queue of the previous 12 frames.Process noise is set to 10 8 for velocity and one for acceleration.The convergence criteria is either |θ| < 0.001 or the maximum number of iterations (25 (l+1)) is reached.To deal with the large outliers, we choose the Tukey s biweight [Black and Rangarajan, 1996] loss function ρ(t) : where κ is a tuning constant that is set to 4.6851 corresponding to the 95% asymptotic efficiency on the standard normal distribution.