Assessment of CNN-Based Methods for Individual Tree Detection on Images Captured by RGB Cameras Attached to UAVs

Abstract

Detection and classification of tree species from remote sensing data were performed using mainly multispectral and hyperspectral images and Light Detection And Ranging (LiDAR) data. Despite the comparatively lower cost and higher spatial resolution, few studies focused on images captured by Red-Green-Blue (RGB) sensors. Besides, the recent years have witnessed an impressive progress of deep learning methods for object detection. Motivated by this scenario, we proposed and evaluated the usage of Convolutional Neural Network (CNN)-based methods combined with Unmanned Aerial Vehicle (UAV) high spatial resolution RGB imagery for the detection of law protected tree species. Three state-of-the-art object detection methods were evaluated: Faster Region-based Convolutional Neural Network (Faster R-CNN), YOLOv3 and RetinaNet. A dataset was built to assess the selected methods, comprising 392 RBG images captured from August 2018 to February 2019, over a forested urban area in midwest Brazil. The target object is an important tree species threatened by extinction known as Dipteryx alata Vogel (Fabaceae). The experimental analysis delivered average precision around 92% with an associated processing times below 30 miliseconds.

Applying Fully Convolutional Architectures for Semantic Segmentation of a Single Tree Species in Urban Environment on High Resolution UAV Optical Imagery

“…The dataset used in this work contained UAV images of Campo Grande municipality, in the state of Mato Grosso do Sul, Brazil (Figure 1). This dataset was a subset of the one presented in [21] and comprised 225 UAV images acquired from 13 August 2018 to 22 September 2018 using a Phantom 4 advanced quadcopter (DJI Innovation Company Inc., Shenzhen, China) in three study areas, depicted in Figure 1. The UAV had an RGB camera with 20 megapixels, a CMOS sensor, a nominal focal length of 8.8 mm, and a field of view of 84 • .…”

“…On the other hand, computer vision has evolved substantially in the last decade, mainly due to the introduction of deep learning methods. In this context, convolutional neural networks (CNNs) have become the most common approach for different image analysis tasks such as automatic classification, object detection, and semantic segmentation [3,5,6,[21][22][23][24][25]. Recently, CNNs have been widely applied for remote sensing problems achieving the state-of-the-art in many applications [26].…”

“…Overall accuracy up to 89% was reported in this study. In [21], Santos et al proposed different deep learning methods for detecting law protected tree species using high resolution RGB imagery. These methods delivered a bounding box that enclosed each object instance, but did not delineate the shape or contour of the target.…”

Detection of Maize Tassels from UAV RGB Imagery with Faster R-CNN

“…Therefore, improving the throughput of phenotyping measurements is a significant challenge in this kind of research. Recent developments in the application of the unmanned aerial vehicle (UAV) mounted with high definition cameras have increased the sample size tremendously [8][9][10]. Researchers have implemented many applications in plant height estimation [11][12][13], seedling counting [14][15][16], and crop growth estimation [17,18] using UAV images.…”

CNN-Based Feature-Level Fusion of Very High Resolution Aerial Imagery and Lidar Data

“…DenseNet were compared against two popular machine learning classifiers including Random Forest (RF) and SVM, and the results proved the superiority of the DenseNet over the other two methods. Also, Santos et al (2019) proposed and evaluated a CNN-based approach for detecting tree species from highresolution images captured by RGB cameras in a UAV platform. In that study, three state-of-the-art CNN-based methods for object detection were tested: Faster R-CNN, YOLOv3, and RetinaNet.…”