Forest Sciences Commons^™

Object-Detection From Multi-View Remote Sensing Images: A Case Study Of Fruit And Flower Detection And Counting On A Central Florida Strawberry Farm, Caiwang Zheng, Tao Liu, Amr Abd-Elrahman, Vance M. Whitaker, Benjamin Wilkinson

Michigan Tech Publications, Part 2

Object detection in remote sensing images is one of the most critical computer vision tasks for various earth observation applications. Previous studies applied object detection models to orthomosaic images generated from the SfM (Structure-from-Motion) analysis to perform object detection and counting. However, some small objects that are occluded from the vertical view but observable in raw images from the oblique views cannot be detected in the orthomosaic image, leading to an occlusion issue that cannot be resolved with the traditional orthophoto-based approach. Taking strawberry detection as a case study, the objective of this study is to detect small objects directly …

Grafting Jig For Small-Diameter American Beech: Proof Of Concept And First Print File, Andrea L. Myers, Tara Bal

Michigan Tech 3D Designs

This tool may be useful for grafting other small diameter woody plant species. This jig can be used by non-experts to simplify and standardize the initial cuts necessary for side grafting small-diameter American beech. The initial file which is suitable for 3D printing is available here, whereas we have the intention of undergoing iterative revisions to refine the tool, considering different sizes and modifications. Future versions will be added through the same avenue as advancements are made.

Fire History And Long-Term Carbon Accumulation In Hemi-Boreal Peatlands Companion Dataset, Dominic Uhelski, Evan Kane, Katherine Heckman, Rodney Chimner

Michigan Tech Research Data

This dataset contains peat property data including location, depth, bulk density, organic matter content, and carbon content, infrared spectra, and radiocarbon dates. Peat cores were collected between 2011 and 2019. Analyses were performed between 2018 and 2021. Samples were collected from peatlands in Michigan, Wisconsin, and Minnesota for the purposes of reconstruction of fire history. The data is associated with a yet-to-be-published manuscript to be submitted to Ecosystems.

A README file is included describing the contents of the dataset and all major spreadsheet files contain a Meta worksheet which describes each column of
data.

Earthworm And Soil Data For Ottawa National Forest, Blair Orr

Michigan Tech Research Data

Two types of analysis were run.

I. Probability of finding L. terrestris in habitat types of the Ottawa National Forests.

Abstract: Parts of the Ottawa National Forest (ONF) provide suitable habitat for invasive earthworms. Extensive earthworm invasion is a relatively recent event on the ONF and this study captures the current state of the earthworm invasion through a four-stage invasive species distribution model (iSDM). The random distribution of earthworms indicates early colonization by earthworms which is moderated by habitat (forest type, soil group, and drainage class). CART modeling was used to determine probability of earthworm invasion. The CART model had …