ALVIO: Adaptive Line and Point Feature-based Visual Inertial Odometry for Robust Localization in Indoor Environments

Jung, Kwangyik; Kim, Yeeun; Lim, Hyunjun; Myung, Hyun

doi:10.48550/arxiv.2012.15008

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table III shows all algorithms compared in this paper. [16] VINS-Fusion [20] VINS-Fusion-gpu [21] ALVIO [18] ORB-SLAM2 [19] VINS-Fusion-imu [20] ROVIO [17] Stereo-MSCKF [22] Kimera [23] C. Evaluation All Jetson boards are set to the maximum CPU clock mode, consuming maximum power to thoroughly compare the potential performance of each algorithm. The performance evaluation is performed based on the resource usage and Absolute Trajectory Error (ATE) for each algorithm and platform.…”

Section: B Compared Algorithmsmentioning

confidence: 99%

“…This study aims to comprehensively analyze the feasibility and evaluate the performance of VIO algorithms, which are open source, and widely applied and used on various NVIDIA hardware configurations. We test three mono-VIO (VINS-Mono [16], ROVIO [17], and ALVIO [18]), two stereo-VO (ORB-SLAM2 stereo [19] and VINS-Fusion w/o IMU [20]), and four stereo-VIO (VINS-Fusion w/ IMU [20], VINS-Fusion w/ GPU [21], Stereo-MSCKF [22], and Kimera [23]) algorithms and benchmark them on NVIDIA Jetson TX2, Xavier NX, and AGX Xavier boards, respectively. Furthermore, we conduct benchmark tests on the proposed dataset.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Run Your Visual-Inertial Odometry on NVIDIA Jetson: Benchmark Tests on a Micro Aerial Vehicle

Jeon

Jung

Lee

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

This paper presents benchmark tests of various visual(-inertial) odometry algorithms on NVIDIA Jetson platforms. The compared algorithms include mono and stereo, covering Visual Odometry (VO) and Visual-Inertial Odometry (VIO): VINS-Mono, VINS-Fusion, Kimera, ALVIO, Stereo-MSCKF, ORB-SLAM2 stereo, and ROVIO. As these methods are mainly used for unmanned aerial vehicles (UAVs), they must perform well in situations where the size of the processing board and weight is limited. Jetson boards released by NVIDIA satisfy these constraints as they have a sufficiently powerful central processing unit (CPU) and graphics processing unit (GPU) for image processing. However, in existing studies, the performance of Jetson boards as a processing platform for executing VO/VIO has not been compared extensively in terms of the usage of computing resources and accuracy. Therefore, this study compares representative VO/VIO algorithms on several NVIDIA Jetson platforms, namely NVIDIA Jetson TX2, Xavier NX, and AGX Xavier, and introduces a novel dataset 'KAIST VIO dataset' for UAVs. Including pure rotations, the dataset has several geometric trajectories that are harsh to visual(inertial) state estimation. The evaluation is performed in terms of the accuracy of estimated odometry, CPU usage, and memory usage on various Jetson boards, algorithms, and trajectories. We present the results of the comprehensive benchmark test and release the dataset for the computer vision and robotics applications.

show abstract