Monocular 3D Object Detection for Autonomous Driving

Citations Over TimeTop 1% of 2016 papers

Abstract

The goal of this paper is to perform 3D object detection from a single monocular image in the domain of autonomous driving. Our method first aims to generate a set of candidate class-specific object proposals, which are then run through a standard CNN pipeline to obtain high-quality object detections. The focus of this paper is on proposal generation. In particular, we propose an energy minimization approach that places object candidates in 3D using the fact that objects should be on the ground-plane. We then score each candidate box projected to the image plane via several intuitive potentials encoding semantic segmentation, contextual information, size and location priors and typical object shape. Our experimental evaluation demonstrates that our object proposal generation approach significantly outperforms all monocular approaches, and achieves the best detection performance on the challenging KITTI benchmark, among published monocular competitors.

Related Papers

• → Object Detection Algorithms for Video Surveillance Applications(2018)174 cited
• → A Survey on Object Detection Methods in Deep Learning(2021)17 cited
• → Object Detection using Deep Learning(2021)8 cited
• → MULTIPLE OBJECT DETECTION IN IMAGES USING YOLO(2022)
• → Object detection techniques for real-time applications(2022)