Innovations in Forestry Research
Welcome to SSMART Forestry Research Group. Our mission is to pioneer and advance the field of forestry through cutting-edge research and technology. Our team of experts is dedicated to discovering innovative ways to sustainably manage forests for generations to come.
A Deformable Shape Model for Automatic and Real-Time Dendrometry
By Lucas A. Wells and Woodam Chung
We present a stereo image-based algorithm for tree stem diameter measurement and form analysis. The algorithm uses planar parametric curves to represent two-dimensional projections of tree stems in stereo images. The curves evolve according to an energy formulation based on the gradients of the images and inductive priors related to biomechanics and morphology of tree stems. After energy minimization, the curves are reconstructed to three dimensions, allowing for diameter measurements at any point along the height of the stem. We describe the algorithm and report the validation test results comparing predicted diameter measurements to external observations. Our findings demonstrate that the algorithm can automatically estimate diameters for trees within 20 m of the camera with an error of 5.52%. We highlight how this method can aid product value optimization through taper analysis and sweep or crook detection. A run-time analysis shows that the algorithm can estimate dendrometric variables for ten trees simultaneously at 15 frames per second on a consumer-grade computer. Furthermore, we discuss the opportunity to produce training data for machine learning algorithms that generalize across domains and eliminate the need to manually tune parameters.
Real-Time Computer Vision for Tree Stem Detection and Tracking
By Lucas A. Wells and Woodam Chung
Object detection and tracking are tasks that humans can perform effortlessly in most environments. Humans can readily recognize individual trees in forests and maintain unique identifiers during occlusion. For computers, on the other hand, this is a complex problem that decades of research have been dedicated to solving. This paper presents a computer vision approach to object detection and tracking tasks in forested environments. We use a state-of-the-art neural network-based detection algorithm to fit bounding boxes around individual tree stems and a simple, efficient, and deterministic multiple object tracking algorithm to maintain unique identities for stems through video frames. We trained the neural network object detector on approximately 3000 ground truth bounding boxes of ponderosa pine trees. We show that tree stem detection can achieve an average precision of 87% using a Jaccard overlap index of 0.5. We also demonstrate the robustness of the tracking algorithm in occlusion and enter–exit–re-enter scenarios. The presented algorithms can perform object detection and tracking at 49 frames per second on a consumer-grade graphics processing unit.
Vision-Aided Localization and Mapping in Forested Environments Using Stereo Images
By Lucas A. Wells and Woodam Chung
: Forests are traditionally characterized by stand-level descriptors, such as basal area, mean diameter, and stem density. In recent years, there has been a growing interest in enhancing the resolution of forest inventory to examine the spatial structure and patterns of trees across landscapes. The spatial arrangement of individual trees is closely linked to various non-monetary forest aspects, including water quality, wildlife habitat, and aesthetics. Additionally, associating individual tree positions with dendrometric variables like diameter, taper, and species can provide data for highly optimized, site-specific silvicultural prescriptions designed to achieve diverse management objectives. Aerial photogrammetry has proven effective for mapping individual trees; however, its utility is limited due to the inability to directly estimate many dendrometric variables. In contrast, terrestrial mapping methods can directly observe essential individual tree characteristics, such as diameter, but their mapping accuracy is governed by the accuracy of the global satellite navigation system (GNSS) receiver and the density of the canopy obstructions between the receiver and the satellite constellation. In this paper, we introduce an integrated approach that combines a camera-based motion and tree detection system with GNSS positioning, yielding a stem map with twice the accuracy of using a consumer-grade GNSS receiver alone. We demonstrate that large-scale stem maps can be generated in real time, achieving a root mean squared position error of 2.16 m. We offer an in-depth explanation of a visual egomotion estimation algorithm designed to enhance the local consistency of GNSS-based positioning. Additionally, we present a least squares minimization technique for concurrently optimizing the pose track and the positions of individual tree stem.
Forestry professionals’ perspectives on exoskeletons (wearable assistive technology) to improve worker safety and health
By Jeong Ho Kim and Woodam Chung
Exoskeletons have been recognized as an effective ergonomic control to reduce physical risk factors, including forceful exertions and awkward postures that are common in manual timber felling. However, no evidence exists to date that offers industry perspectives, important facilitators, and potential barriers for adopting exoskeletons in the forest industry. Therefore, this study aimed to quantify biomechanical stress of timber fellers and assess forestry professionals’ awareness and acceptance of exoskeletons. We measured working postures using wearable sensors during manual timber felling [N = 10] to suggest appropriate and beneficial exoskeleton types for timber fellers. We examined forestry professionals’ awareness and acceptance of exoskeletons and identified perceived barriers and risks using a questionnaire [N = 22]. This study revealed that the forestry professionals expressed considerable interest and acceptance level in exoskeleton use. The important factors influencing the adoption of exoskeletons identified in this study were weight, comfort, simplicity/portability, practicality (usable and easy to use), and easy maintenance. The results also identified timber felling, cutting/sawing, and mechanic work as potential forestry tasks that may benefit most from the exoskeleton use. The wearable sensor data showed that manual timber felling posed substantial torso bending and upper-arm elevation. Given the awkward posture and high prevalence of musculoskeletal pain in the back and upper-arms, this study suggests that back-support and upper-limb support exoskeletons may be suitable to the forest industry. This study provides important insights for future studies investigating the feasibility, readiness, and effectiveness of exoskeletons to be applied to the forest industry.