PIXOR: Real-time 3D Object Detection from Point Clouds (2018-06-01T00:00:00.000000Z)

TL;DR

PIXOR is proposed, a proposal-free, single-stage detector that outputs oriented 3D object estimates decoded from pixel-wise neural network predictions that surpasses other state-of-the-art methods notably in terms of Average Precision (AP), while still runs at 10 FPS.

Abstract

We address the problem of real-time 3D object detection from point clouds in the context of autonomous driving. Speed is critical as detection is a necessary component for safety. Existing approaches are, however, expensive in computation due to high dimensionality of point clouds. We utilize the 3D data more efficiently by representing the scene from the Bird's Eye View (BEV), and propose PIXOR, a proposal-free, single-stage detector that outputs oriented 3D object estimates decoded from pixel-wise neural network predictions. The input representation, network architecture, and model optimization are specially designed to balance high accuracy and real-time efficiency. We validate PIXOR on two datasets: the KITTI BEV object detection benchmark, and a large-scale 3D vehicle detection benchmark. In both datasets we show that the proposed detector surpasses other state-of-the-art methods notably in terms of Average Precision (AP), while still runs at 10 FPS.

Authors

Binh Yang

5 papers

R. Urtasun

12 papers

Wenjie Luo

1 papers

TL;DR

Abstract

Authors

References38 items

Focal Loss for Dense Object Detection

EAST: An Efficient and Accurate Scene Text Detector

Feature Pyramid Networks for Object Detection

3D fully convolutional network for vehicle detection in point cloud

Multi-view 3D Object Detection Network for Autonomous Driving

PVANet: Lightweight Deep Neural Networks for Real-time Object Detection

Deconvolution and Checkerboard Artifacts

Vote3Deep: Fast object detection in 3D point clouds using efficient convolutional neural networks

3D Object Proposals Using Stereo Imagery for Accurate Object Class Detection

Monocular 3D Object Detection for Autonomous Driving

Vehicle Detection from 3D Lidar Using Fully Convolutional Network

R-FCN: Object Detection via Region-based Fully Convolutional Networks

Identity Mappings in Deep Residual Networks

Deep Residual Learning for Image Recognition

SSD: Single Shot MultiBox Detector

Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images

DenseBox: Unifying Landmark Localization with End to End Object Detection

Voting for Voting in Online Point Cloud Object Detection

You Only Look Once: Unified, Real-Time Object Detection

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Fast R-CNN

Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation

Learning Spatiotemporal Features with 3D Convolutional Networks

Fully convolutional networks for semantic segmentation

Sliding Shapes for 3D Object Detection in Depth Images

Very Deep Convolutional Networks for Large-Scale Image Recognition

ImageNet Large Scale Visual Recognition Challenge

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

Vision meets robotics: The KITTI dataset

Selective Search for Object Recognition

ImageNet classification with deep convolutional neural networks

Are we ready for autonomous driving? The KITTI vision benchmark suite

ImageNet: A large-scale hierarchical image database

Least Squares Support Vector Machine Classifiers

Single Shot Multibox Detector를 적용한 실시간 선박 검출 및 분류 시스템 개발

International Journal of Computer Vision manuscript No. (will be inserted by the editor) The PASCAL Visual Object Classes (VOC) Challenge

Field of Study

Journal Information

Name

Page