AFE-ORB-SLAM: Robust Monocular VSLAM Based on Adaptive FAST Threshold and Image Enhancement for Complex Lighting Environments

نویسندگان

چکیده

Abstract Monocular Visual Simultaneous Localisation and Mapping (VSLAM) systems are widely utilised for intelligent mobile robots to work in unknown environments. However, complex varying illuminations challenge the accuracy robustness of VSLAM significantly. Existing feature-based methods often fail due insufficient feature points that can be extracted those challenging illumination Therefore, this paper proposes an improved ORB-SLAM algorithm based on adaptive FAST threshold image enhancement (AFE-ORB-SLAM), which works environments with lighting conditions. An truncated Adaptive Gamma Correction (AGC) is combined unsharp masking reduce effect caused by different illuminations. What more, ORB extraction method proposed adopted obtain more reliable points. To verify performance AFE-ORB-SLAM, three public datasets (the extended Imperial College London National University Ireland Maynooth (ICL-NUIM) dataset conditions, Onboard Illumination Visual-Inertial Odometry (OIVIO) European Robotics Challenge (EuRoC) dataset) utilised. The results compared other state-of-the-art monocular methods. experimental demonstrate AFE-ORB-SLAM could achieve highest average localisation robust conditions while keeping similar normal scenarios.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Threshold based Adaptive Power-Law Applications in Image Enhancement

This paper presents a spatial domain threshold based adaptive power-law applications (TAPLA) in image enhancement technique in which adaptation is carried out with local thresholds. This is an improved version of Adaptive Power-law Transformations (APLT) [14] in which adaptation is carried out with local means. The computational time of APLT is window-size dependent to find local mean while the...

متن کامل

Image enhancement filters based on threshold patterns

Threshold Boolean lters (TBFs) constitute a large class of non-linear lters that are very e ective in removing impulsive noise. However, the required computational complexity is very high because thresholding has to be done at all levels. In this paper, a new type of lters based on threshold operation is proposed. The proposed lters, called threshold pattern lters (TPFs), try to pick up a sampl...

متن کامل

Batch based Monocular SLAM for Egocentric Videos

Simultaneous Localization and Mapping (SLAM) from a monocular camera has been a well researched area. However, estimating camera pose and 3d geometry reliably for egocentric videos still remain a challenge [25, 40, 42]. Some of the common causes of failures are dominant 3D rotations and low parallax between successive frames, resulting in unreliable pose and 3d estimates. For forward moving cam...

متن کامل

Robust vSLAM for Dynamic Scenes

This paper proposes a robust visual Simultaneous Localization and Mapping(vSLAM) method that consists of two parts: (1)an initialization method for a 3D map and camera poses, and (2)an outlier rejection method for moving objects. We introduce weighted tentative initial values of a camera pose and 3-D map to reduce the user operation load. We also distinguish outliers of feature points between m...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Journal of Intelligent and Robotic Systems

سال: 2022

ISSN: ['1573-0409', '0921-0296']

DOI: https://doi.org/10.1007/s10846-022-01645-w