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

• Main Authors: Anderson Aparecido dos Santos, José Marcato Junior, Márcio Santos Araújo, David Robledo Di Martini, Everton Castelão Tetila, Henrique Lopes Siqueira, Camila Aoki, Anette Eltner, Edson Takashi Matsubara, Hemerson Pistori, Raul Queiroz Feitosa, Veraldo Liesenberg, Wesley Nunes Gonçalves
• Format: Article
• Language: English
• Published: MDPI AG 2019-08-01
• Series: Sensors
• Subjects: object-detection; deep learning; remote sensing
• Online Access: https://www.mdpi.com/1424-8220/19/16/3595

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 <i>Dipteryx alata</i> Vogel (Fabaceae). The experimental analysis delivered average precision around 92% with an associated processing times below 30 miliseconds.