Anchor Distance for 3D Multi-Object Distance Estimation from 2D Single Shot
Hyeonwoo Yu, Jean Oh

TL;DR
This paper introduces a real-time method for estimating distances to multiple objects from a single image using anchor distances, improving accuracy and speed in 3D perception for autonomous systems.
Contribution
It proposes the concept of anchor distance for multi-object detection, enabling precise and efficient 3D distance estimation from 2D images in real-time.
Findings
Achieves approximately 30 FPS speed.
Demonstrates the lowest RMSE among compared methods.
Effective in multi-object distance estimation from single images.
Abstract
Visual perception of the objects in a 3D environment is a key to successful performance in autonomous driving and simultaneous localization and mapping (SLAM). In this paper, we present a real time approach for estimating the distances to multiple objects in a scene using only a single-shot image. Given a 2D Bounding Box (BBox) and object parameters, a 3D distance to the object can be calculated directly using 3D reprojection; however, such methods are prone to significant errors because an error from the 2D detection can be amplified in 3D. In addition, it is also challenging to apply such methods to a real-time system due to the computational burden. In the case of the traditional multi-object detection methods, %they mostly pay attention to existing works have been developed for specific tasks such as object segmentation or 2D BBox regression. These methods introduce the concept of…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Optical Sensing Technologies · Robotics and Sensor-Based Localization · Advanced Neural Network Applications
