MonStereo: When Monocular and Stereo Meet at the Tail of 3D Human Localization
This work addresses 3D human localization for self-driving cars or social robots, presenting an incremental improvement by integrating existing vision methods.
The authors tackled 3D human localization by proposing a unified framework that combines monocular and stereo cues to address occlusions, distant cases, and monocular ambiguity, resulting in improved performance on challenging instances like occluded and far-away pedestrians, with specific metrics and error analysis.
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.