Kinect V2 vs Intel RealSense D435: A Comparative Study on 3D Mapping
Resumo
The generation of accurate 3D maps is essential for an efficient autonomous navigation. With precise mapping, robots can plan optimal paths, avoiding obstacles and efficiently reaching their destinations. For this purpose, the use of RGB-D cameras, which capture color images and depth information of the environment, is common. This paper presents a comparative study of 3D maps generated by the Kinect V2 and RealSense D435 sensors, which were properly configured in a manipulator robot for controlled data acquisition, considering different environments and capture conditions. The RTAB-Map algorithm was used to process the data acquired by the sensors and generate the 3D maps. This analysis allows identifying which sensors are more suitable for each type of environment, as well as their limitations and advantages. Thus, this comparison helps select the best camera for each application and provides valuable insights for the development of more accurate and efficient applications.
Referências
G. Brahmanage and H. Leung, “Outdoor rgb-d mapping using intelrealsense,” in 2019 IEEE SENSORS, 2019, pp. 1–4.
R. Fernandes, T. L. Rocha, H. Azpúrua, G. Pessin, A. A. Neto, and G. Freitas, “Investigation of visual reconstruction techniques using mobile robots in confined environments,” in 2020 Latin American Robotics Symposium (LARS), 2020 Brazilian Symposium on Robotics (SBR) and 2020 Workshop on Robotics in Education (WRE), 2020, pp. 1–6.
J. G. da Silva Neto, P. J. da Lima Silva, F. Figueredo, J. M. X. N. Teixeira, and V. Teichrieb, “Comparison of rgb-d sensors for 3d reconstruction,” in 2020 22nd Symposium on Virtual and Augmented Reality (SVR), 2020, pp. 252–261.
N. Altuntas¸, E. Uslu, F. Çakmak, M. F. Amasyalı, and S. Yavuz, “Comparison of 3-dimensional slam systems: Rtab-map vs. kintinuous,” in 2017 Int. Conf. on Comp. Science and Eng., 2017, pp. 99–103.
K. J. de Jesus, H. J. Kobs, A. R. Cukla, M. A. de Souza Leite Cuadros, and D. F. T. Gamarra, “Comparison of visual slam algorithms orb-slam2, rtab-map and sptam in internal and external environments with ros,” in 2021 Latin American Robotics Symposium (LARS), 2021 Brazilian Symposium on Robotics (SBR), and 2021 Workshop on Robotics in Education (WRE), 2021, pp. 216–221.
M. Filipenko and I. Afanasyev, “Comparison of various slam systems for mobile robot in an indoor environment,” in 2018 International Conference on Intelligent Systems (IS), 2018, pp. 400–407.
K. Wang, G. Zhang, and H. Bao, “Robust 3d reconstruction with an rgb-d camera,” IEEE Trans. on Image Processing, 2014.
A. Tupper and R. Green, “Pedestrian proximity detection using rgb-d data,” in 2019 International Conference on Image and Vision Computing New Zealand (IVCNZ), 2019, pp. 1–6.
J. D. Mejia-Trujillo, Y. J. Casta˜no-Pino, A. Navarro, J. D. Arango-Paredes, D. Rincón, J. Valderrama, B. Muñoz, and J. L. Orozco, “Kinect™ and intel realsense™ d435 comparison: a preliminary study for motion analysis,” in 2019 IEEE Int. Conf. on E-health Networking, Application Services (HealthCom), 2019.
R. Zou, X. Ge, and G. Wang, “Applications of rgb-d data for 3d reconstruction in the indoor environment,” in 2016 IEEE Chinese Guidance, Navigation and Control Conference (CGNCC), 2016, pp. 375–378.
