Individual Tree Crown Delineation for the Species Classification and Assessment of Vital Status of Forest Stands from UAV Images

Abstract

Monitoring the structure parameters and damage to trees plays an important role in forest management. Remote-sensing data collected by an unmanned aerial vehicle (UAV) provides valuable resources to improve the efficiency of decision making. In this work, we propose an approach to enhance algorithms for species classification and assessment of the vital status of forest stands by using automated individual tree crowns delineation (ITCD). The approach can be potentially used for inventory and identifying the health status of trees in regional-scale forest areas. The proposed ITCD algorithm goes through three stages: preprocessing (contrast enhancement), crown segmentation based on wavelet transformation and morphological operations, and boundaries detection. The performance of the ITCD algorithm was demonstrated for different test plots containing homogeneous and complex structured forest stands. For typical scenes, the crown contouring accuracy is about 95%. The pixel-by-pixel classification is based on the ensemble supervised classification method error correcting output codes with the Gaussian kernel support vector machine chosen as a binary learner. We demonstrated that pixel-by-pixel species classification of multi-spectral images can be performed with a total error of about 1%, which is significantly less than by processing RGB images. The advantage of the proposed approach lies in the combined processing of multispectral and RGB photo images.

Estimación de variables dasométricas en rodales bajo manejo forestal con vehículos aéreos no tripulados

“…La medición de variables dasométricos en las especies forestales siempre existe un porcentaje de error al momento de la captura, levantamiento de datos (Safonova et al, 2021) o por la geografía del lugar, de esta forma el resultado de este estudio fue similar a los datos arrojado de forma manual y la capturada fotografía del dron, porque ya que se contaba con la ubicación de cada árbol los cuales fueron seleccionados del área en donde se tomaron las fotografía (Figura 1) pese al terreno irregular de los rodales, aun así, no presentaba variabilidad en los resultados obtenidos manualmente con lecturas de dron. Sin embargo, Sperlich et al (2014), en un estudio realizado en Alemania con esta tecnología, reportan que el porcentaje de detección para el bosque de coníferas es de 87.68% en el radio de búsqueda 1 m y 90.41% en el radio de búsqueda 2m.…”

Remote Sensing Assessment of the Expansion of Ips typographus Attacks in the Chuprene Reserve, Western Balkan Range

“…For this reason, the mapping of bark beetle spots based on NDVI data can be quite inaccurate and, therefore, should be used in combination with RGB images. A combined processing of multispectral and RGB photo images was applied for species classification and assessment of the vital status of forest stands in the Chuprene Reserve [19].…”

Detection of Norway Spruce Trees (Picea Abies) Infested by Bark Beetle in UAV Images Using YOLOs Architectures

“…For typical scenes, the crown contouring accuracy is about 95%. The advantage of the proposed approach lies in the combined processing of multispectral and RGB photo images from DJI quadcopters [23].…”

“…This experiment is complementary to our latest research [23]. In this paper, we analyze the detection of four infestation classes of Norway spruce trees attacked by the European bark beetle (green-, yellow-, red-, and gray-attack (see Section III.A)) on UAV images using YOLO architectures.…”

“…The study area is the territory of the West Balkan Mountains (up to 1300-1500 m altitude), the south of the administrative center of Chuprene, Vidin Province, Bulgaria (Figure 1). We considered study area located in protected place of Chuprene Biosphere Reserve, included in the list of UNESCO [23]. The reserve has been created with the aim of preserving the environment of the unique natural complex.…”