An evaluation of real-time RGB-D visual odometry algorithms on mobile devices

被引：9

作者：

Angladon, Vincent ^{[1
,2
]}

Gasparini, Simone ^{[1
]}

Charvillat, Vincent ^{[1
]}

Pribanic, Tomislav ^{[3
]}

Petkovic, Tomislav ^{[3
]}

Donlic, Matea ^{[3
]}

Ahsan, Benjamin ^{[2
]}

Bruel, Frederic ^{[2
]}

机构：

[1] Univ Toulouse, IRIT, INPT, 118 Route Narbonne, F-31062 Toulouse, France

[2] Telequid, Toulouse, France

[3] Univ Zagreb, Fac Elect Engn & Comp, Unska 3, Zagreb 10000, Croatia

来源：

JOURNAL OF REAL-TIME IMAGE PROCESSING | 2019年 / 16卷 / 05期

关键词：

RGB-D Camera; Visual odometry; Benchmark; Mobile device; REGISTRATION;

D O I：

10.1007/s11554-017-0670-y

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present an evaluation and a comparison of different visual odometry algorithms selected to be tested on a mobile device equipped with a RGB-D camera. The most promising algorithms from the literature are tested on different mobile devices, some equipped with the Structure Sensor. We evaluate the accuracy of each selected algorithm as well as the memory and CPU consumption, and we show that even without specific optimization, some of them can provide a reliable measure of the device motion in real time.

引用

页码：1643 / 1660

页数：18