کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
5006339 | 1461473 | 2018 | 23 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Novel and powerful mosaic constructor for territorial analysis using mobile robots via Binary Robust Invariant Scalable Keypoints
ترجمه فارسی عنوان
سازنده موزاییک رمان و قدرتمند برای تجزیه و تحلیل محدوده با استفاده از روبات های موبایل از طریق دیتا بیسیم
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
موضوعات مرتبط
مهندسی و علوم پایه
سایر رشته های مهندسی
کنترل و سیستم های مهندسی
چکیده انگلیسی
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.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Measurement - Volume 114, January 2018, Pages 448-470
Journal: Measurement - Volume 114, January 2018, Pages 448-470
نویسندگان
Pedro Pedrosa Rebouças Filho, Francisco Diego Lima Moreira, Leandro Bezerra Marinho, Jefferson Silva Almeida,