Jo, HyungGi Lee, Woosub Kim, Euntai 2024-01-19T16:00:16Z 2024-01-19T16:00:16Z 2021-09-02 2021-01 1551-3203 https://pubs.kist.re.kr/handle/201004/117642 Global localization using a monocular camera is one of the most challenging problems in computer vision and intelligent robotics. In this article, a new deep neural network named Mixture Density (MD)-PoseNet is proposed to address this problem. Unlike existing learning-based global localization methods that return a single guess for the camera pose, MD-PoseNet returns multiple guesses represented in the form of a Gaussian mixture (GM). The key idea of MD-PoseNet is that the network returns the distribution of all probable camera poses instead of the most probable camera pose, and the distribution represents the multiple guesses for the camera pose. The multiple guesses returned by MD-PoseNet are, consequently, exploited in the probabilistic framework of particle filters. Finally, the proposed method is applied to four different environments, and its validity is demonstrated via experiments. English IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC Mixture Density-PoseNet and its Application to Monocular Camera-Based Global Localization Article 10.1109/TII.2020.2986086 1 IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, v.17, no.1, pp.388 - 397 IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 17 1 388 397 scie scopus 000587719200036 2-s2.0-85096035455 Automation & Control Systems Computer Science, Interdisciplinary Applications Engineering, Industrial Automation & Control Systems Computer Science Engineering Article Cameras Robot vision systems Informatics Training Three-dimensional displays Image recognition CNN distribution Gaussian mixture mixture density particle filter