MonStereo: when Monocular and Stereo Meet at the Tail of 3D Human Localization
2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021)(2021)
Abstract
Monocular and stereo visions are cost-effective solutions for 3D human localization in the context of self-driving cars or social robots. However, they are usually developed independently and have their respective strengths and limitations. We propose a novel unified learning framework that leverages the strengths of both monocular and stereo cues for 3D human localization. Our method jointly (i) associates humans in left- right images, (ii) deals with occluded and distant cases in stereo settings by relying on the robustness of monocular cues, and (iii) tackles the intrinsic ambiguity of monocular perspective projection by exploiting prior knowledge of the human height distribution. We specifically evaluate outliers as well as challenging instances, such as occluded and far-away pedestrians, by analyzing the entire error distribution and by estimating calibrated confidence intervals. Finally, we critically review the official KITTI 3D metrics and propose a practical 3D localization metric tailored for humans.
MoreTranslated text
Key words
practical 3D localization metric,3D human localization,stereo visions,cost-effective solutions,stereo cues,monocular cues,monocular perspective projection,human height distribution,KITTI 3D metrics,self-driving cars,social robots,left-right images
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined