Monocular 3D Object Detection Based on Pseudo Multimodal Information Extraction and Keypoint Estimation

Abstract

Three-dimensional object detection is an essential and fundamental task in the field of computer vision which can be widely used in various scenarios such as autonomous driving and visual navigation. In view of the current insufficient utilization of image information in current monocular camera-based 3D object detection algorithms, we propose a monocular 3D object detection algorithm based on pseudo-multimodal information extraction and keypoint estimation. We utilize the original image to generate pseudo-lidar and a bird’s-eye view, and then feed the fused data of the original image and pseudo-lidar to the keypoint-based network for an initial 3D box estimation, finally using the bird’s-eye view to refine the initial 3D box. The experimental performance of our method exceeds state-of-the-art algorithms under the evaluation criteria of 3D object detection and localization on the KITTI dataset, achieving the best experimental performance so far.