| Title |
Development of Real-time Object Coordinate Creation Algorithm using Depth Camera and GPS |
| Authors |
이재욱(Jaewook Lee) ; 김태현(Taehyun Kim) ; 류재규(Jaekyu Ryu) ; 문희창(Heechang Moon) |
| DOI |
https://doi.org/10.5573/ieie.2023.60.3.88 |
| Keywords |
CMOS RC oscilllator; PVT compensation; digitally trimmable |
| Abstract |
Various studies using depth cameras are developing a lot. In line with the trend, this paper conducted a study to find GPS UTM coordinates of real-time objects using a camera with a depth camera and an RGB camera at the same time. After first performing resolution matching of two cameras with different resolutions, we find out object recognition using RGB cameras and central pixel coordinates of the bounding box of the recognized object. After that, the distance from the camera to the object was measured using a depth camera that matched the resolution with the same pixel. X and Y distances away from the camera to the object were calculated through the focus of the camera pixel, the center pixel coordinates of the bounding box of the object, and the distance obtained by the depth camera. Then, the calculated value was calculated by the UTM coordinate value of GPS in the same position as the camera, the heading direction extracted through the previous coordinates of GPS, and the X and Y distances away from the object obtained by the camera. For the accuracy of the experimental results, the distance and UTM coordinates of a particular point were obtained in advance through GPS, and then a real person stood at the location and recognized the object, and then the accuracy was determined. As a result of the experiment, a result with high accuracy was obtained within 10m. |