WSEAS Transactions on Systems
Print ISSN: 1109-2777, E-ISSN: 2224-2678
Volume 24, 2025
Monocular Image-Based 3D Object Detection for Industrial Pick-and-Place Tasks
Authors: , ,
Search Articles
Abstract: This paper proposes a new pipeline that estimates depth information from a single RGB image
and utilizes it for object detection. By fusing the pseudo depth map generated through the MiDaS-based
Monocular Depth Estimation with the RGB image, the performance of the existing RGB-based detection model is
improved. The proposed method is practical because spatial structure information can be utilized without an actual
depth sensor, and shows robust performance, especially in occlusion between objects and complex background
environments. As a result of experiments on the KITTI and SUN RGB-D datasets, the proposed method achieved
performance improvement of 4.2% and 3.8% on mAP compared to the existing RGB-based method, respectively.
Keywords:
Monocular Depth Estimation, RGB-D Fusion, Object Detection, Computer Vision, Deep Learning
Pages: 779-786
DOI: 10.37394/23202.2025.24.65