Segmentation of Overlapping Tree Images in the Digital Photographs of Forest Areas

Journal Title: Lesnoy Zhurnal (Russian Forestry Journal) - Year 2024, Vol 1, Issue 1

Abstract

The use of decision support systems based on computer vision and artificial intelligence significantly improves the working conditions for the operators of technological machines in the timber sector, whose work implies high intensity and psycho-emotional overload. By means of computer vision and artificial intelligence the operator can quickly and easily obtain the data on the state of the cutting area and adopt the optimal solution for holding the working operation. This facilitates his work and reduces the time spent searching and analyzing the data on the cutting area. Meanwhile, one of the key elements of such a system is a subsystem for automatic segmentation of objects in the photograph. We have explored the possibility of segmenting overlapping objects in the photographs of forest areas using a convolutional neural network based on the Mask R-CNN architecture. Unlike in most works on similar topics, the objects of this study are color photographs taken by an RGB camera rather than a lidar. This creates the prospect for reducing the cost of hardware and software systems used to support decision-making by the operators of logging machines. The images of the stems and crowns of coniferous and deciduous trees overlapping each other are the segmented objects under consideration. Using the GIMP graphic editor, we have manually marked the color photographs depicting a total of 134 trees of 4 different species: spruce, aspen, birch and pine. Utilizing the developed database, we have carried out an experiment to further train the Mask R-CNN convolutional neural network for segmentation of overlapping parts of the trees in the digital photographs of forest areas. The neural network has been pre-trained using the Microsoft COCO dataset containing more than 200,000 images of 80 different classes of objects such as people, cars, animals and various items. While training the neural network, the images supplied to its input were subjected to a series of various linear and nonlinear geometric transformations, which made it possible to increase the volume of training data by 11 times. As a result, the accuracy of segmentation of the images of the stems and crowns of coniferous and deciduous trees overlapping each other has reached 79 %, which allows the use of neural networks based on a similar architecture in decision support systems for logging machine operators.

Authors and Affiliations

Igor V. Petukhov, Konstantin O. Ivanov, Dmitry M. Vorozhtsov, Alexey A. Rozhentsov, Nataliya I. Rozhentsova, Ludmila A. Steshina,

Keywords

Related Articles

The Study of the Destruction Process of Frozen and Thawing Soils Exposed to the Skidding System

Wood logging in the forests of the cryolithozone is growing more urgent for the Russian Federation due to the depletion of available reserves of mature commercial forests in southern and Central Siberia, the Republic of...

Growth Features of Siberian Elm on Brown Soils of the Astrakhan Semi-Desert

The article presents the current state assessment and suggests the methods for additional moisture supply of soils under stable tree plantations of Siberian elm (Ulmus pumila L.) on brown soils of semi-desert. The resear...

The Condition of Arboriflora of the Gvardejskij Park of Krasnoyarsk

An inventory of green spaces in the Gvardejskij Park of the Sovetskij District of Krasnoyarsk has been carried out. The aim of the work has been to assess the species composition and vital condition of woody and shrubby...

The Use of Spatial Analysis Methods in Assessing the Degree of Fire Frequency in Forests of the Khabarovsk Territory

Forest fires are the dominant factor in the transformation of natural landscapes in the boreal zone. The area of the Khabarovsk Territory, 93.6 % of which belongs to the forest fund lands, currently has a forest cover of...

Radial Growth of Scots Pine in the Northern Taiga

The research aims at assessing the influence of daytime and nighttime meteorological parameters (air temperature, dew point, relative air humidity, wind velocity and amount of precipitation) on the pine radial growth in...

Download PDF file
  • EP ID EP731653
  • DOI 10.37482/0536-1036-2024-1-126-140
  • Views 72
  • Downloads 0

How To Cite

Igor V. Petukhov, Konstantin O. Ivanov, Dmitry M. Vorozhtsov, Alexey A. Rozhentsov, Nataliya I. Rozhentsova, Ludmila A. Steshina, (2024). Segmentation of Overlapping Tree Images in the Digital Photographs of Forest Areas. Lesnoy Zhurnal (Russian Forestry Journal), 1(1), -. https://europub.co.uk/articles/-A-731653