Representation based regression for object distance estimation

• DOI: 10.1016/j.neunet.2022.11.011
• Publication Date: 2022-11-12T07:22:39Z
• Authors: Mete Ahishali; Mehmet Yamac; Serkan Kiranyaz; Moncef Gabbouj
• Keywords: Representation

In this study, we propose a novel approach to predict the distances of detected objects in an observed scene. The proposed modifies recently Convolutional Support Estimator Networks (CSENs). CSENs are designed compute direct mapping for Estimation (SE) task representation-based classification problem. We further and demonstrate that methods (sparse or collaborative representation) can be used well-designed regression problems especially over scarce data. To best our knowledge, is first method performing by utilizing modified CSENs; hence, name as Representation-based Regression (RbR). initial version has proxy stage (i.e., coarse estimation support set) required input. improve CSEN model proposing Compressive Learning (CL-CSEN) ability jointly optimize so-called along with convolutional layers. experimental evaluations using KITTI 3D Object Detection distance dataset show achieve significantly improved performance all competing methods. Finally, software implementations publicly shared at https://github.com/meteahishali/CSENDistance.