Anchor Distance for 3D Multi-Object Distance Estimation from 2D Single Shot

by   Hyeonwoo Yu, et al.

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, have been developed for specific tasks such as object segmentation or 2D BBox regression. These methods introduce the concept of anchor BBox for elaborate 2D BBox estimation, and predictors are specialized and trained for specific 2D BBoxes. In order to estimate the distances to the 3D objects from a single 2D image, we introduce the notion of anchor distance based on an object's location and propose a method that applies the anchor distance to the multi-object detector structure. We let the predictors catch the distance prior using anchor distance and train the network based on the distance. The predictors can be characterized to the objects located in a specific distance range. By propagating the distance prior using a distance anchor to the predictors, it is feasible to perform the precise distance estimation and real-time execution simultaneously. The proposed method achieves about 30 FPS speed, and shows the lowest RMSE compared to the existing methods.


page 1

page 7


CenterNet3D:An Anchor free Object Detector for Autonomous Driving

Accurate and fast 3D object detection from point clouds is a key task in...

Learning Object-specific Distance from a Monocular Image

Environment perception, including object detection and distance estimati...

MetaAnchor: Learning to Detect Objects with Customized Anchors

We propose a novel and flexible anchor mechanism named MetaAnchor for ob...

R4D: Utilizing Reference Objects for Long-Range Distance Estimation

Estimating the distance of objects is a safety-critical task for autonom...

Analysis of voxel-based 3D object detection methods efficiency for real-time embedded systems

Real-time detection of objects in the 3D scene is one of the tasks an au...

CornerNet: Detecting Objects as Paired Keypoints

We propose CornerNet, a new approach to object detection where we detect...

Anchor Transform: Learning Sparse Representations of Discrete Objects

Learning continuous representations of discrete objects such as text, us...

Please sign up or login with your details

Forgot password? Click here to reset