文献类型：期刊文献

英文题名：Optimization of Sassafras tzumu leaves color quantification with UAV RGB imaging and Sassafras-net

作者：Meng, Qingwei[1,2] Yan, Wei Qi[3] Xu, Cong[4] Zhang, Zhaoxu[5] Hao, Xia[5] Chen, Hui[6] Liu, Wei[7] Li, Yanjie[1]

第一作者：Meng, Qingwei

通信作者：Li, YJ[1]

机构：[1]Chinese Acad Forestry, Res Inst Subtrop Forestry, State Key Lab Tree Genet & Breeding, Hangzhou 311400, Zhejiang, Peoples R China;[2]Yangtze Univ, Coll Hort & Gardening, Jingzhou 434025, Hubei, Peoples R China;[3]Auckland Univ Technol, Auckland 1010, New Zealand;[4]Univ Canterbury, Sch Forestry, Private Bag 4800, Christchurch 8140, New Zealand;[5]Shandong Agr Univ, Coll Informat Sci & Engn, Tai An 271018, Shandong, Peoples R China;[6]Forest Pest Control & Quarantine Stn Shaoxing City, Shaoxing 312000, Zhejiang, Peoples R China;[7]Zhejiang A&F Univ, Coll Opt Mech & Elect Engn, Hangzhou 311300, Zhejiang, Peoples R China

年份：2025

卷号：12

期号：3

起止页码：384-397

外文期刊名：INFORMATION PROCESSING IN AGRICULTURE

收录：;EI(收录号：20250717875226);Scopus(收录号：2-s2.0-85217646560);WOS:【SCI-EXPANDED(收录号:WOS:001604438300001)】；

基金：This work was funded by Zhejiang Science and Technology Major Program on Agricultural New Variety Breeding (2021C02070-7-3) and the Fundamental Research Funds of CAF, No. CAFYBB2022QA001

语种：英文

外文关键词：UAV RGB images; Color leaves; YOLOX; CCTrans network; Tree phenotypes

摘要：Quantifying the leaf density and coloration of trees is critical for assessing landscape esthetics and photosynthetic efficiency; however, traditional leaf-counting methods are labor-intensive and potentially harmful to trees, making accurate measurements challenging. To address these issues, we present "Sassafras-net," an advanced model specifically designed to detect and count colored leaves on Sassafras tzumu trees. The methodology consists of two steps. First, we used an improved model termed YOLOX-CBAM to accurately detect and isolate individual trees. This model proved to be more effective than alternatives, such as YOLOX, YOLOv8, YOLOv7, YOLOv5, and Fater-RCNN. Second, the Sassafras-net model, which is based on the CCTrans network, counts the number of colored leaves per tree. Compared with the original CCTrans model of 52.30 and 84.90, the Sassafras-net model achieved significantly lower mean absolute error and mean squared error values of 27.29 and 39.00, respectively. These results confirm the ability of the model to accurately and efficiently quantify colored leaves. To the best of our knowledge, this is the first study to quantify colored leaves in trees. Our method provides forestry researchers with an effective and economical tool for selecting and breeding S. tzumu trees with enhanced color traits. In addition, this study opens new avenues for studying tree traits related to leaf coloration.