Abstract

One of the most fundamental problems in mobile robotics is to build an environment map. Digital image processing techniques can be applied to extract the most important information from the environment to solve such tasks. In this work, we proposed a new approach to build mosaics using the Binary Robust Invariant Scalable Keypoints (BRISK) method from images captured by a mobile robot and an Unmanned Aerial Vehicle (UAV). Furthermore, we compared our approach with the Scale Invariant Feature Transform (SIFT) and Speed Up Robust Features (SURF) techniques to find the points of interest. The Random Sample Consensus (RANSAC) and the Least Median Square methods were used to find the homography matrix, while the Cubic and Linear Interpolation methods were applied to build the mosaic. According to the results, BRISK with RANSAC and Linear Interpolations were the fastest methods taking 15.671±4.665 s, while, SIFT and SURF took 78.074±5.66 and 19.494±2.32 s, respectively. BRISK achieved the same values as SIFT and SURF for the metrics Mean Squared Error, Peak Signal-to-Noise Ratio and Mean Structural Similarity Index. The results were satisfactory for territorial analysis using both the robot with wheels and the UAV.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.