A Robust Optical Flow Tracking Method Based On Prediction Model for Visual-Inertial Odometry

Zhu, Shengnan; Yang, Shuming; Hu, Pengyu; Qu, Xiaoyan

doi:10.1109/lra.2021.3079806

Cited by 9 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using optical flow tracking does not need to calculate descriptors, it avoids the calculation process of calculating and matching descriptors, and reduces the calculation time. The same pixel moves between image frames and extracts feature points for the first image and uses the LK [9,10] optical flow method provided by OpenCV to track the movement process of feature points.…”

Section: Visual-inertial Odometrymentioning

confidence: 99%

Multi-Sensor Fusion SLAM Method for Underground Power Pipe Gallery

Que

Zheng

Zou

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The satellite signal in the underground power pipe gallery is missing and the light is dim, so simultaneous localization and mapping (SLAM) is facing many challenges. Aiming at this special scene, a new SLAM method based on multi-sensor fusion is proposed by using a new type of area array laser radar and a monocular camera to build a 3D scanner. The geometric structure of the global map is obtained by fusing the pre-integrated IMU data and the lidar data. The texture and color information of the global map are supplemented by visual information rendering. A data connection bridge is built between the equipment and the local server in the form of remote networking to achieve data synchronization. The experimental results of an underground power pipe gallery in Zhejiang Province show that the method significantly improves the accuracy of 3D reconstruction in complex environments, and provides a useful reference for the development of localization and mapping of underground inspection robots.

show abstract

Section: Visual-inertial Odometrymentioning

confidence: 99%

Multi-Sensor Fusion SLAM Method for Underground Power Pipe Gallery

Que

Zheng

Zou

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…There is an urgent need to explore a method to ingeniously fuse multisensor information and maximize the overall confidence of VINS. The second challenge is the problem of image feature matching or tracking failure in illumination-changing scenes [11], [12]. Drastic illumination change may cause VINS to collapse due to insufficient geometric constraints to participate in the optimization.…”

Section: Introductionmentioning

confidence: 99%

“…Many existing works focus on the second challenge. By combining the extrinsic transformation matrix and the reprojection model, Zhu et al [11] propose an initial optical flow prediction algorithm based on IMU pre-integration, which greatly improves the success rate of feature point tracking in environments with drastic illumination change. The work in [16] designs a deep convolutional neural network (CNN) model to adaptively change the camera exposure time and gain, which increases the number of high-quality features.…”

Section: Introductionmentioning

confidence: 99%

IR-VIO: Illumination-Robust Visual-Inertial Odometry Based on Adaptive Weighting Algorithm With Two-Layer Confidence Maximization

Song¹,

Zhang²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

<p>Illumination change, image blur, and fast motion dramatically decrease the performance of visual-inertial navigation systems (VINS). This paper presents a new illumination-robust visual-inertial odometry (IR-VIO) based on adaptive weighting algorithm with two-layer confidence maximization. First, to prevent the VIO performance degradation caused by poor image quality in complex scenes and ignoring the confidence differences of feature points, we develop a novel adaptive weighting algorithm on the multi-sensor layer and visual feature layer to better fuse multi-sensor information and maximize the overall confidence of VIO. Second, to solve the problems of image feature tracking difficulty and excessive image noise in illumination-changing scenes, an image enhancement algorithm is introduced to enhance consecutive images to the same brightness level, while a block noise removal algorithm with constraint protection mechanism is proposed to dynamically remove feature points in noise areas. Finally, experimental results on the public dataset and real-world environments demonstrate that IR-VIO has superior performance in terms of accuracy and robustness compared with the state-of-the-art methods. Supplementary video is available at https://youtu.be/163Sk7twEMY.</p>

show abstract

Robust Initialization for Stereo Visual-Inertial SLAM with Polar-Based Gravity Estimation

Liu

Rao

et al. 2022

2022 4th International Conference on Data Intelligence and Security (ICDIS)

View full text Add to dashboard Cite

A Robust Optical Flow Tracking Method Based On Prediction Model for Visual-Inertial Odometry

Cited by 9 publications

References 31 publications

Multi-Sensor Fusion SLAM Method for Underground Power Pipe Gallery

Multi-Sensor Fusion SLAM Method for Underground Power Pipe Gallery

IR-VIO: Illumination-Robust Visual-Inertial Odometry Based on Adaptive Weighting Algorithm With Two-Layer Confidence Maximization

Robust Initialization for Stereo Visual-Inertial SLAM with Polar-Based Gravity Estimation

Contact Info

Product

Resources

About