SmartForest4.0

🌟 We are proud to announce that our team — Stefano Puliti, Rasmus Astrup, and Johannes Rahlf — received the Special Contribution Award of the ISPRS International Contest on Individual Tree Crown (ITC) Segmentation! 🌳 This recognition, awarded at the Joint SELPER & ISPRS TC III Symposium in Belém, Brazil, highlights the advancements in tree crown segmentation using high-resolution images. We extend our gratitude to Xinlian Liang for organizing this competition and supporting innovation in remote sensing and ISPRS for organizing such an impactful event. 📸 Joerg Brauchle | ISPRS - International Society for Photogrammetry and Remote Sensing | #RemoteSensing | #TreeCrownSegmentation | #ForestryResearch | #Award | SELPER - Brasil | NIBIO Norwegian Institute of Bioeconomy Research |

🌳 NEW PAPER ALLERT from SmartForest4.0 featuring SegmentAnyTree: A sensor platform and agnostic deep learning model for tree segmentation using laser scanning data. Congratulations to the authors Maciej Wielgosz, Stefano Puliti, binbin xiang, Konrad Schindler and Rasmus Astrup on their work! In this latest #RSE study the team worked more on individual tree segmentation from point clouds, powered by an end-to-end deep learning model! And here’s the game-changer: this model is data-agnostic! 🎉 It seamlessly segments both ground based LiDAR data (TLS, MLS) and airborne data (ULS and ALS).   In addition, they have benchmarked it across multiple datasets for robustness. And as a final highlight, they’re thrilled to release a new #opendata repository featuring NIBIO's labeled MLS data to support further research in the field.   Check it out and give it a spin: Code: 👉 https://lnkd.in/dF22sJDn Paper: 👉https://lnkd.in/dFgMr_Rc Datasets: 👉 FOR-instance dataset: https://lnkd.in/dDkiQDuC 👉 NIBIO_MLS dataset: is available at: https://lnkd.in/dewqsDas Demo: 👉 https://forestsens.com/ Run it on your data and let us know your thoughts! 🌲✨ More on SmartForest? Have a look at our webpage 👉 https://smartforest.no/    | NIBIO Norwegian Institute of Bioeconomy Research | ETH Zürich | #TreeSegmentation | #DeepLearning | #InstanceSegmentation | #PanopticSegmentation | #RemoteSensing | #forestmanagement | Contribute to SmartForest-no/SegmentAnyTree development by creating an account on GitHub. Follow SingleTree for future developments in forest 3D scene AI! 

📢 OPEN POSTDOC POSITION within SmartForest4.0 at NMBU - Norwegian University of Life Sciences on the use of remote sensing to evaluate the suitability for continous cover forestry. 📆 Application deadline November 5, 2024 Find more information and apply here 👉 https://lnkd.in/dVAgtwCn The main tasks are: ◾ The detailed analyses of the correlation between data from various types of remote sensing and forestry characteristics that are relevant for assessing the suitability for continous cover forestry. ◾ Development of practical methods for classifying the suitability for continous cover forestry that can be implemented in today's forest management plans. More information on SmartForest is available on our webpage 👉 https://smartforest.no/ | #forestmanagement | #CCF | #remotesensing | NIBIO Norwegian Institute of Bioeconomy Research | #forestry |

💡 🌲 This week we had the chance to meet the consortium of our Centre for Research-based Innovation during our 2 day annual meeting, the SmartForest days! It was a pleasure to see so many from industry and research gathered, exchanging news and catching up! On the first day of the event, we had an engaging conference filled with insightful sessions on sharing of environmental data, with valuable input from our industry partners at Norges Skogeierforbund, Viken Skog SA, and Glommen Mjøsen Skog SA. We also had a session focussing on Innovation with Ard Innovation and Erik Willén from Stora Enso. We used the opportunity to inform about some highlights from the work of the centre like ForestSens, our AI-driven cloud platform (www.forestsens.com), wood quality estimation (Moelven), and developments of operational systems for damage evaluation after storms (Skogbrand Forsikringsselskap). Some of the PhD candidates in SmartForest4.0 also presented their work on ◾ Mapping of natural forests with deep learning (Julius Wold) ◾ Stand segmentation with AI (Håkon Næss Sandum) ◾ Tracking of logs from the forest to the sawmill using tracking codes and object detection models (Yohann Jacob Sandvik) ◾ Assessing the importance of accurate forest data in forest planning and decision-making processes (Olha Nahorna) ◾ Automated classification of roads and maintenance needs for better planning (Helle Ross Gobakken) On the second day, we had an excursion to a research forest in Våler, with a high number of permanent inventory plots. Here, SmartForest presented some of its work in four stations on ◾ Forest Roads ◾ Site index and tree species identification ◾ Retention trees ◾ Mission planning for collection of airborne laser scanning data explained by Field and segmentation of single trees It was a great setting to discuss our research findings and innovations in a more practical setting.   | NIBIO Norwegian Institute of Bioeconomy Research | NMBU - Norwegian University of Life Sciences | Norges forskningsråd | NORSKOG | Field | Landbruksdirektoratet | Skogdata | AT Skog SA | Statskog SF | Norsk Virkesmåling | Maskinentreprenørenes Forbund (MEF) | Komatsu Forest | Geodata AS | University of Oslo | Biodrone | RIF Institut für Forschung und Transfer e.V. | FPInnovations | Mistra Digital Forest | #forestry | #remotesensing | #forestinventory | #AI | #deeplearning | #drones | #forestmanagement | #enabelingtechnologies |

🇳🇿 🌳🌲🛰️ Wrapping up an inspiring few days at ForestSAT 2024 in Rotorua, New Zealand! The team from the Norwegian National Forest Inventory (Zsófia Koma and I) had an exciting time sharing ideas and reconnecting with both new and old friends and colleagues. I had the honor of presenting our latest research on AI—also on behalf of Stefano Puliti and SmartForest4.0—and chairing sessions on forest monitoring. Tomorrow, we’re looking forward to the field trip! I’m eager to bring the new ideas and insights back to NIBIO Norwegian Institute of Bioeconomy Research. A big thank you to Scion for hosting such a fantastic conference. #forestsat2024 #remotesensing #biodiversity #forestry #AI #deeplearning

💡 🌲 SmartForest4.0 is happy to share the latest work from the Centre on 3D scene panoptic segmentation of high density LiDAR point clouds of forests! This work is a collaboration between ETH Zürich and SmartForest4.0 NIBIO Norwegian Institute of Bioeconomy Research. Congratulations to the authors binbin xiang, Maciej Wielgosz, Theodora Kontogianni, Torben Peters,Stefano Puliti, Konrad Schindler and Rasmus Astrup! | #deeplearning | #forestmanagement | #FORinstance | #AI |

If you are interested in lidar data and tree species classification, check out this one....

📢 🎯 A new article was just published on Predicting tree species composition using airborne laser scanning and multispectral data in boreal forests! Congratulations to the authors Jaime Candelas Bielza, Lennart Noordermeer, Erik Næsset, Terje Gobakken, Johannes Breidenbach and Hans Ole Ørka! https://lnkd.in/dWRsJE7C Tree species composition is essential information for forest management and remotely sensed (RS) data have proven to be useful for its prediction. In forest management inventories, tree species are commonly interpreted manually from aerial images for each stand, which is time and resource consuming and entails substantial uncertainty. The objective of this study was to evaluate a range of RS data sources comprising airborne laser scanning (ALS) and airborne and satellite-borne multispectral data for model-based prediction of tree species composition. Total volume was predicted using non-linear regression and volume proportions of species were predicted using parametric Dirichlet models. Predicted dominant species was defined as the species with the greatest predicted volume proportion and predicted species-specific volumes were calculated as the product of predicted total volume multiplied by predicted volume proportions. Ground reference data obtained from 1184 sample plots of 250 m2 in eight districts in Norway were used. Combinations of ALS and two multispectral data sources, i.e. aerial images and Sentinel-2 satellite images from different seasons, were compared. The most accurate predictions of tree species composition were obtained by combining ALS and multi-season Sentinel-2 imagery, specifically from summer and fall. This study highlights the utility of remotely sensed data for prediction of tree species composition in operational forest inventories, particularly indicating the utility of ALS and multi-season Sentinel-2 imagery. read the full article here 👉 https://lnkd.in/dWRsJE7C | NMBU - Norwegian University of Life Sciences | NIBIO Norwegian Institute of Bioeconomy Research | Elsevier | #aerialimages | #airborne #laserscanning | #dirichlet_regression | #sentinel2 | #treespecies | #forestinventory | #forestmanagement | #multispectraldata | #forests |

📢 Open Postdoc position within SmartForest4.0 at NIBIO Norwegian Institute of Bioeconomy Research in Ås, Norway! 📆 Do not forget to apply by August 11th! This is an exciting opportunity to work on ◾ Developing AI approaches and methods for analyzing image, lidar data and x-ray data for individual logs capture at the saw mill in support of traceability and wood quality measurement and prediction ◾ Developing AI approaches and methods for analyzing image, lidar data, and photogrammetric data of standing trees in the forest in support of traceability and wood quality measurement and prediction read more about the position and apply here 👉 https://lnkd.in/dZEZvRUz | #postdoc | #openposition | #lidar | #phyton | #AI | #photogrammetry | #image | #forestry | #Norway | #computervision | #treaceability |

A new SmartForest4.0 article, “A Comparative Literature Review of Machine Learning and Image Processing Techniques Used for Scaling and Grading of Wood Logs” was just published in Forests MDPI. Congratulations to the authors  Yohann Jacob Sandvik, Cecilia Futsaether, Kristian Hovde Liland and Oliver Tomic! This literature review assesses the efficacy of image-processing techniques and machine-learning models in computer vision for wood log grading and scaling. Four searches were conducted in four scientific databases, yielding a total of 1288 results, which were narrowed down to 33 relevant studies. The studies were categorized according to their goals, including log end grading, log side grading, individual log scaling, log pile scaling, and log segmentation. The studies were compared based on the input used, choice of model, model performance, and level of autonomy. This review found a preference for images over point cloud representations for logs and an increase in camera use over laser scanners. It identified three primary model types: classical image-processing algorithms, deep learning models, and other machine learning models. However, comparing performance across studies proved challenging due to varying goals and metrics. Deep learning models showed better performance in the log pile scaling and log segmentation goal categories. Cameras were found to have become more popular over time compared to laser scanners, possibly due to stereovision cameras taking over for laser scanners for sampling point cloud datasets. Classical image-processing algorithms were consistently used, deep learning models gained prominence in 2018, and other machine learning models were used in studies published between 2010 and 2018. Read the full article here 👉 https://lnkd.in/daSsjXz7 For more information on SmartForest, read here 👉 https://smartforest.no/ | NMBU - Norwegian University of Life Sciences | Norges forskningsråd | #logscaling | #loggrading | #woodscience | #timber | #computervision | #artificialintelligence | #deeplearning | #machinelearning | #imageprocssing |