A new method which is applied to estimate the area of region by using least square technology is proposed in this paper. The original image is captured by an unmanned aerial vehicle (UAV) and then applying image processing technology to do the preliminary image procedure. Based on the number pixels of the measurement region, the system can estimate its area. However, the height of UAV is hard to control in different place, therefore, the size of captured images will have a little different. It will cause some errors of the total pixels of image. In this paper, the second order least square regression technology is applied to modify this problem. Before the estimation procedure, an UAV is used to get many images of region area for training this algorithm. It captures a group of images for the same area from different height by every ten meters. In image processing process, edge detection and morphology are used to find the range of the interest region, and then count the number of pixels of it. Based on the experimental results, the proposed algorithm can estimate one unknown area accurately.
|頁（從 - 到）||118-126|
|期刊||Journal of Information Hiding and Multimedia Signal Processing|
|出版狀態||Published - 2019 一月|
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition