A STUDY OF USING FULLY CONVOLUTIONAL NETWORK FOR TREETOP DETECTION ON REMOTE SENSING DATA

Abstract. Individual tree detection and counting are critical for the forest inventory management. In almost all of these methods that based on remote sensing data, the treetop detection is the most important and essential part. However, due to the diversities of the tree attributes, such as crown size and branch distribution, it is hard to find a universal treetop detector and most of the current detectors need to be carefully designed based on the heuristic or prior knowledge. Hence, to find an efficient and versatile detector, we apply deep neural network to extract and learn the high-level semantic treetop features. In contrast to using manually labelled training data, we innovatively train the network with the pseudo ones that come from the result of the conventional non-supervised treetop detectors which may be not robust in different scenarios. In this study, we use multi-view high-resolution satellite imagery derived DSM (Digital Surface Model) and multispectral orthophoto as data and apply the top-hat by reconstruction (THR) operation to find treetops as the pseudo labels. The FCN (fully convolutional network) is adopted as a pixel-level classification network to segment the input image into treetops and non-treetops pixels. Our experiments show that the FCN based treetop detector is able to achieve a detection accuracy of 99.7 % at the prairie area and 66.3 % at the complicated town area which shows better performance than THR in the various scenarios. This study demonstrates that without manual labels, the FCN treetop detector can be trained by the pseudo labels that generated using the non-supervised detector and achieve better and robust results in different scenarios.

[1]  Jiaojiao Tian,et al.  3 D change detection – approaches and applications , 2016 .

[2]  Bogdan M. Strimbu,et al.  A graph-based segmentation algorithm for tree crown extraction using airborne LiDAR data , 2015 .

[3]  Juha Hyyppä,et al.  UAV-BASED PHOTOGRAMMETRIC POINT CLOUDS AND HYPERSPECTRAL IMAGING FOR MAPPING BIODIVERSITY INDICATORS IN BOREAL FORESTS , 2017 .

[4]  Conghe Song,et al.  Estimating average tree crown size using spatial information from Ikonos and QuickBird images: Across-sensor and across-site comparisons , 2010 .

[5]  Russell Turner,et al.  Development of an automated individual tree detection model using point cloud LiDAR data for accurate tree counts in a Pinus radiata plantation , 2016 .

[6]  B. Koch,et al.  Detection of individual tree crowns in airborne lidar data , 2006 .

[7]  Darius S. Culvenor,et al.  TIDA: an algorithm for the delineation of tree crowns in high spatial resolution remotely sensed imagery , 2002 .

[8]  D. King,et al.  Approaches for optimal automated individual tree crown detection in regenerating coniferous forests , 2005 .

[9]  P. Gong,et al.  Isolating individual trees in a savanna woodland using small footprint lidar data , 2006 .

[10]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[11]  K. O. Niemann,et al.  Local Maximum Filtering for the Extraction of Tree Locations and Basal Area from High Spatial Resolution Imagery , 2000 .

[12]  Sassan Saatchi,et al.  Lidar detection of individual tree size in tropical forests , 2016 .

[13]  Yinghai Ke,et al.  A review of methods for automatic individual tree-crown detection and delineation from passive remote sensing , 2011 .

[14]  S. Malyshev,et al.  Scaling from individual trees to forests in an Earth system modeling framework using a mathematically tractable model of height-structured competition , 2015 .

[15]  Arko Lucieer,et al.  An Automated Technique for Generating Georectified Mosaics from Ultra-High Resolution Unmanned Aerial Vehicle (UAV) Imagery, Based on Structure from Motion (SfM) Point Clouds , 2012, Remote. Sens..

[16]  Cem Ünsalan,et al.  Tree crown detection and delineation in satellite images using probabilistic voting , 2017 .

[17]  Wenkai Li,et al.  Delineating Individual Trees from Lidar Data: A Comparison of Vector- and Raster-based Segmentation Approaches , 2013, Remote. Sens..

[18]  Luc Vincent,et al.  Morphological grayscale reconstruction in image analysis: applications and efficient algorithms , 1993, IEEE Trans. Image Process..

[19]  Jamie Sherrah,et al.  Fully Convolutional Networks for Dense Semantic Labelling of High-Resolution Aerial Imagery , 2016, ArXiv.

[20]  Nikos Koutsias,et al.  Object-based classification using Quickbird imagery for delineating forest vegetation polygons in a Mediterranean test site , 2008 .

[21]  Nate G. McDowell,et al.  Automated tree crown detection and size estimation using multi-scale analysis of high-resolution satellite imagery , 2013 .

[22]  Randolph H. Wynne,et al.  Estimating plot-level tree heights with lidar : local filtering with a canopy-height based variable window size , 2002 .

[23]  C. Silva,et al.  Individual tree detection from Unmanned Aerial Vehicle (UAV) derived canopy height model in an open canopy mixed conifer forest , 2017 .

[24]  P. Gong,et al.  Individual Tree-Crown Delineation and Treetop Detection in High-Spatial-Resolution Aerial Imagery , 2004 .

[25]  Eufemia Tarantino,et al.  A tree counting algorithm for precision agriculture tasks , 2013, Int. J. Digit. Earth.

[26]  D. Passoni,et al.  Use of Unmanned Aerial Systems for multispectral survey and tree classification: a test in a park area of northern Italy , 2014 .

[27]  Zhanyi Hu,et al.  Semantic labeling of high-resolution aerial images using an ensemble of fully convolutional networks , 2017 .

[28]  Tomas Brandtberg.  Detection and analysis of individual leaf-off tree crowns in small footprint, high sampling density lidar data from the eastern deciduous forest in North America , 2003 .

[29]  Marco Heurich,et al.  Individual-tree- and stand-based development following natural disturbance in a heterogeneously structured forest: A LiDAR-based approach , 2017, Ecol. Informatics.

[30]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Jiaojiao Tian,et al.  3D change detection – Approaches and applications , 2016 .

[32]  M. J. Tarp-Johansen,et al.  Automatic Stem Mapping in Three Dimensions by Template Matching from Aerial Photographs , 2002 .

[33]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[34]  Iasonas Kokkinos,et al.  Semantic Part Segmentation with Deep Learning , 2015, ArXiv.

[35]  Marco Heurich,et al.  Forest inventories by LiDAR data: A comparison of single tree segmentation and metric-based methods for inventories of a heterogeneous temperate forest , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[36]  Myron Brown,et al.  METRIC EVALUATION PIPELINE FOR 3D MODELING OF URBAN SCENES , 2017 .

[37]  Marc Bosch,et al.  A multiple view stereo benchmark for satellite imagery , 2016, 2016 IEEE Applied Imagery Pattern Recognition Workshop (AIPR).