LiDAR点群から3D物体検出と道路理解を同時に行う簡潔で効率的なマルチタスクネットワーク
A Simple and Efficient Multi-task Network for 3D Object Detection and Road Understanding
生のLiDAR点群を入力とし、3D物体検出と走行可能領域・地面高さ推定など6つの知覚タスクを単一のエンコーダ・デコーダ型ネットワークで同時に予測する手法を提案し、オンライン自己位置推定にも応用した。
著者: Di Feng, Yiyang Zhou, Chenfeng Xu, Masayoshi Tomizuka, Wei Zhan
分類: cs.CV, cs.RO
原文アブストラクト
Detecting dynamic objects and predicting static road information such as drivable areas and ground heights are crucial for safe autonomous driving. Previous works studied each perception task separately, and lacked a collective quantitative analysis. In this work, we show that it is possible to perform all perception tasks via a simple and efficient multi-task network. Our proposed network, LidarMTL, takes raw LiDAR point cloud as inputs, and predicts six perception outputs for 3D object detection and road understanding. The network is based on an encoder-decoder architecture with 3D sparse convolution and deconvolution operations. Extensive experiments verify the proposed method with competitive accuracies compared to state-of-the-art object detectors and other task-specific networks. LidarMTL is also leveraged for online localization. Code and pre-trained model have been made available at https://github.com/frankfengdi/LidarMTL.
