ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection

03/01/2020
by   Zhenbo Xu, et al.
6

3D object detection is an essential task in autonomous driving and robotics. Though great progress has been made, challenges remain in estimating 3D pose for distant and occluded objects. In this paper, we present a novel framework named ZoomNet for stereo imagery-based 3D detection. The pipeline of ZoomNet begins with an ordinary 2D object detection model which is used to obtain pairs of left-right bounding boxes. To further exploit the abundant texture cues in RGB images for more accurate disparity estimation, we introduce a conceptually straight-forward module – adaptive zooming, which simultaneously resizes 2D instance bounding boxes to a unified resolution and adjusts the camera intrinsic parameters accordingly. In this way, we are able to estimate higher-quality disparity maps from the resized box images then construct dense point clouds for both nearby and distant objects. Moreover, we introduce to learn part locations as complementary features to improve the resistance against occlusion and put forward the 3D fitting score to better estimate the 3D detection quality. Extensive experiments on the popular KITTI 3D detection dataset indicate ZoomNet surpasses all previous state-of-the-art methods by large margins (improved by 9.4 study also demonstrates that our adaptive zooming strategy brings an improvement of over 10 KITTI benchmark lacks fine-grained annotations like pixel-wise part locations, we also present our KFG dataset by augmenting KITTI with detailed instance-wise annotations including pixel-wise part location, pixel-wise disparity, etc.. Both the KFG dataset and our codes will be publicly available at https://github.com/detectRecog/ZoomNet.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 7

research
12/04/2021

Behind the Curtain: Learning Occluded Shapes for 3D Object Detection

Advances in LiDAR sensors provide rich 3D data that supports 3D scene un...
research
07/12/2022

Paint and Distill: Boosting 3D Object Detection with Semantic Passing Network

3D object detection task from lidar or camera sensors is essential for a...
research
12/08/2020

Accurate 3D Object Detection using Energy-Based Models

Accurate 3D object detection (3DOD) is crucial for safe navigation of co...
research
02/26/2019

Stereo R-CNN based 3D Object Detection for Autonomous Driving

We propose a 3D object detection method for autonomous driving by fully ...
research
12/14/2016

Detect, Replace, Refine: Deep Structured Prediction For Pixel Wise Labeling

Pixel wise image labeling is an interesting and challenging problem with...
research
03/10/2023

DAVIS-Ag: A Synthetic Plant Dataset for Developing Domain-Inspired Active Vision in Agricultural Robots

In agricultural environments, viewpoint planning can be a critical funct...
research
03/10/2019

Group-wise Correlation Stereo Network

Stereo matching estimates the disparity between a rectified image pair, ...

Please sign up or login with your details

Forgot password? Click here to reset