Delving into Localization Errors for Monocular 3D Object Detection
This work addresses a critical challenge for autonomous driving systems by improving monocular 3D detection, though it is incremental as it builds on existing methods to refine localization.
The paper tackles the problem of inaccurate 3D object detection from monocular images in autonomous driving by identifying localization errors as a key bottleneck, and proposes strategies including removing distant training samples and a new loss function, achieving real-time detection and outperforming previous methods on the KITTI dataset.
Estimating 3D bounding boxes from monocular images is an essential component in autonomous driving, while accurate 3D object detection from this kind of data is very challenging. In this work, by intensive diagnosis experiments, we quantify the impact introduced by each sub-task and found the `localization error' is the vital factor in restricting monocular 3D detection. Besides, we also investigate the underlying reasons behind localization errors, analyze the issues they might bring, and propose three strategies. First, we revisit the misalignment between the center of the 2D bounding box and the projected center of the 3D object, which is a vital factor leading to low localization accuracy. Second, we observe that accurately localizing distant objects with existing technologies is almost impossible, while those samples will mislead the learned network. To this end, we propose to remove such samples from the training set for improving the overall performance of the detector. Lastly, we also propose a novel 3D IoU oriented loss for the size estimation of the object, which is not affected by `localization error'. We conduct extensive experiments on the KITTI dataset, where the proposed method achieves real-time detection and outperforms previous methods by a large margin. The code will be made available at: https://github.com/xinzhuma/monodle.