Automatic Tree Height Measurement Based on Three-Dimensional Reconstruction Using Smartphone

Tree height is a crucial structural parameter in forest inventory as it provides basis for evaluating stock volume and growth status. In recent years, close-range photogrammetry based on smartphone has attracted attention from researchers due to its low cost non-destructive characteristics. However, such methods have specific requirements camera angle distance during shooting, pre-shooting operations calibration placement of boards are necessary, which could be inconvenient operate complex natural environments. We propose tree measurement method three-dimensional (3D) reconstruction. Firstly, an absolute depth map was obtained by combining ARCore MidasNet. Secondly, Attention-UNet improved adding maps network input obtain mask. Thirdly, the color image were fused 3D point cloud scene. Then, extracted using Finally, measured extracting axis-aligned bounding box cloud. built into Android app, demonstrating efficiency automation. Our approach achieves average relative error 3.20% within shooting range 2–17 m, meeting accuracy survey.