Individual tree segmentation and tree-counting using supervised clustering

doi:10.1016/j.compag.2023.107629

Return

Individual tree segmentation and tree-counting using supervised clustering

2023-02-01

PRE

DOI：10.1016/j.compag.2023.107629

Original

Original request for help

Save

Abstract

En 中文

Individual tree segmentation (ITS), or tree counting, is a fundamental work in precision forestry and agriculture processes. Rather than the time-consuming and labor-intensive manual inspection, computer vision has shown substantial prospects in unmanned aerial vehicle (UAV)-based applications; one such application includes the automatic tree-counting problem in the forest resource inventory. However, it is difficult to obtain individual trees owing to the particularity of tree canopy crowns, such as color graduality, shape uncertainty, and overlapping. In this study, we propose a learning framework based on supervised data clustering. Here, both ITS and tree counting can be obtained accurately and simultaneously from a two-dimensional (2D) top-view tree canopy crowns whether they are isolated, overlapped, or both. A pixel-precision classifier is used to recognize tree pixels or superpixels (a set of meaningful pixels), rather than using complex image preprocessing or feature construction techniques. The obtained tree superpixels are then grouped into individual trees by the proposed supervised clustering method. To obtain accurate ITS and tree counts, the similarity used for the clustering is learned from the user-supplied supervisions, rather than pre-specified or grid-search as in the existing state-of-the-art methods. This study also includes an extensive experimental comparison of homogenous and heterogeneous high-resolution images. The results demonstrate that our method is superior to the state-of-the-art methods in both visualized ITS and numeric tree-counting results, even comparable to human vision. It achieves a counting accuracy of 99.16 % in terms of the R-2 value and 2.2923 in terms of the pixel mean absolute error (MAE). These are 22.04 % higher and 8.727 lower, respectively, than those of the second-best method.

Keywords:

Superpixel

Tree-counting

Individual tree segmentation

Similarity

Supervised clustering