Inicio  /  Agriculture  /  Vol: 12 Par: 9 (2022)  /  Artículo
ARTÍCULO
TITULO

Influence of Selected Modeling Parameters on Plant Segmentation Quality Using Decision Tree Classifiers

Florian Kitzler    
Helmut Wagentristl    
Reinhard W. Neugschwandtner    
Andreas Gronauer and Viktoria Motsch    

Resumen

Modern precision agriculture applications increasingly rely on stable computer vision outputs. An important computer vision task is to discriminate between soil and plant pixels, which is called plant segmentation. For this task, supervised learning techniques, such as decision tree classifiers (DTC), support vector machines (SVM), or artificial neural networks (ANN) are increasing in popularity. The selection of training data is of utmost importance in these approaches as it influences the quality of the resulting models. We investigated the influence of three modeling parameters, namely proportion of plant pixels (plant cover), criteria on what pixel to choose (pixel selection), and number/type of features (input features) on the segmentation quality using DTCs. Our findings show that plant cover and, to a minor degree, input features have a significant impact on segmentation quality. We can state that the overperformance of multi-feature input decision tree classifiers over threshold-based color index methods can be explained to a high degree by the more balanced training data. Single-feature input decision tree classifiers can compete with state-of-the-art models when the same training data are provided. This study is the first step in a systematic analysis of influence parameters of such plant segmentation models.

 Artículos similares

       
 
Siyi Li, Zhen Tao, Yuan Liu, Shengshu Li, Rakhwe Kama, Chao Hu, Xiangyang Fan and Zhongyang Li    
Treated livestock wastewater reuse for irrigation and straw return in arid regions have become common practices worldwide. However, many uncertainties still exist regarding the effects of the returning straw sizes on heavy metal accumulation in soil and ... ver más
Revista: Agriculture

 
Lidija Begovic, Nikola Juri?ic, Martina ?rajer Gajdo?ik, Alma Miku?ka and Selma Mlinaric    
Soybean (Glycine max (L.) Merr.) is one of the most economically important crops in the world due to its nutritional value. To optimize soybean growth and yield, a wide range of commercial herbicides intended for weed control in crops are used. Although ... ver más
Revista: Agriculture

 
Lukasz S. Jarosz, Ewa Tomaszewska, Agnieszka Marek, Marcin Hejdysz, Artur Burmanczuk, Artur Ciszewski, Sebastian Nowaczewski, Zbigniew Gradzki, Maciej Batorski, Malgorzata Swiatkiewicz and Anna Rysiak    
The use of feed additives containing glutamine can influence the growth and development of piglets during the weaning period. The aim of this study was to determine the effect of feed supplementation with 0.5% L-glutamine on selected parameters of the no... ver más
Revista: Agriculture

 
Lei Wang and Yiwen Zhao    
The supply level of irrigation and water conservancy is related to the utilization efficiency of water resources, the production level of farmers, and the supply quality of agricultural products, especially relating to national food security and stabilit... ver más
Revista: Agriculture

 
Krystyna Zarzynska, Cezary Trawczynski and Milena Pietraszko    
This paper presents the results of the authors? own research and literature research on the impact of selected environmental and agronomical factors on the yield of potato grown under the organic system and the possibility of increasing the yield. The re... ver más
Revista: Agriculture