Self-supervised 3D Object Detection from Monocular Pseudo-LiDAR
This addresses the challenge of accurate 3D object detection for autonomous driving systems without relying on expensive LiDAR sensors, though it is incremental as it builds on existing depth prediction and detection methods.
The paper tackles the problem of low accuracy in 3D object detection using only monocular image sequences by proposing an end-to-end learning method that predicts absolute depth and detects objects, achieving state-of-the-art performance on the KITTI 3D dataset.
There have been attempts to detect 3D objects by fusion of stereo camera images and LiDAR sensor data or using LiDAR for pre-training and only monocular images for testing, but there have been less attempts to use only monocular image sequences due to low accuracy. In addition, when depth prediction using only monocular images, only scale-inconsistent depth can be predicted, which is the reason why researchers are reluctant to use monocular images alone. Therefore, we propose a method for predicting absolute depth and detecting 3D objects using only monocular image sequences by enabling end-to-end learning of detection networks and depth prediction networks. As a result, the proposed method surpasses other existing methods in performance on the KITTI 3D dataset. Even when monocular image and 3D LiDAR are used together during training in an attempt to improve performance, ours exhibit is the best performance compared to other methods using the same input. In addition, end-to-end learning not only improves depth prediction performance, but also enables absolute depth prediction, because our network utilizes the fact that the size of a 3D object such as a car is determined by the approximate size.