From f29a42d145fb4e7a54b42c949ce36a462f5c7af2 Mon Sep 17 00:00:00 2001 From: Zager-Zhang <348338663@qq.com> Date: Tue, 19 Mar 2024 15:44:57 +0800 Subject: [PATCH] update --- index.html | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/index.html b/index.html index 4cd6976..6732185 100644 --- a/index.html +++ b/index.html @@ -33,7 +33,9 @@
Zengzhi Li1,4, Guiyong Zheng1, Yiming Luo1, +
Zhu Wang4, + Jinni Zhou5, Shaojie Shen2, Boyu Zhou1,†
@@ -43,7 +45,8 @@
2 The Hong Kong University of Science and Technology.    3 Northwestern Polytechnical University.   
- 4 North China Electric Power University, Hebei.    + 4 North China Electric Power University.    + 5 The Hong Kong University of Science and Technology.   
*Equal Contribution    @@ -85,6 +88,7 @@

Abstract

+ Unmanned Aerial Vehicles (UAVs) have gained significant popularity in scene reconstruction. In this paper, we introduce FC-Hetero, a LiDAR-Visual heterogeneous multi-UAV system designed specifically for fast aerial reconstruction in complex scenes. Our system comprises an explorer equipped with a LiDAR sensor boasting a large field-of-view (FoV), alongside photographers equipped with cameras. To ensure rapid acquisition of the scene's surface geometry, we employ a surface frontier-based exploration strategy for the explorer. As the surface is progressively explored, we identify the uncovered areas and generate viewpoints incrementally. These viewpoints are then assigned to photographers using a Consistent Multiple Depot Multiple Traveling Salesman Problem (Consistent-MDMTSP) approach, which optimizes scanning efficiency and guarantees task consistency. Finally, photographers utilize the assigned viewpoints to determine optimal coverage paths for acquiring images. We present extensive benchmarks in the realistic simulator, which validates the performance of FC-Hetero compared with classical and state-of-the-art methods.

TODO