MHMichael L. Hilton

Michael L. Hilton

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Michael L. Hilton has a total of 9 co-authors. Here are the top co-authors by number of shared publications:

  • Craig Guyer

    BAuburn University, 331 Funchess Hall, Auburn, AL 36849, USA

    1 shared publication
  • Ericha Shelton-Nix

    CAlabama Department of Conservation and Natural Resources, Division of Wildlife and Freshwater Fisheries, 64 North Union Street, Montgomery, AL 36130, USA

    1 shared publication
  • Jane M. Downer

    Natural Sciences Collegium, Eckerd College 4200 54th Avenue S St. Petersburg FL 33711 USA

    1 shared publication
  • Jay P. Giblin

    Physical Sciences, Inc. (United States)

    1 shared publication
  • Jeffrey M. Goessling

    Natural Sciences Collegium, Eckerd College 4200 54th Avenue S St. Petersburg FL 33711 USA

    1 shared publication
  • Jeffrey M. Goessling

    AEckerd College, 4200 54th Avenue South, St Petersburg, FL 33711, USA

    1 shared publication

Latest Publications

  • Open Access

    Population consolidation and head-starting as demographic rescue of a low-density gopher tortoise population

    by Jeffrey M. Goessling, Craig Guyer, Michael L. Hilton, Ericha Shelton-Nix

    Context: Gopher tortoises, Gopherus polyphemus, are a keystone species of south-eastern North America due to their historically high density, grazing habits, and the burrows that they maintain across upland landscapes. Many gopher tortoise populations are demographically non-viable due to low population density and/or population size. Management for this species frequently utilize measures such as translocation and head-starting. Aims: Between 2020 and 2024, we used short-distance translocation to consolidate a low-density resident population of gopher tortoises and monitored spatial biology and apparent survival in the translocated animals immediately following translocation. We also conducted head-starting of tortoises collected as eggs from the same site and manipulated head-start release conditions to test whether soft- versus hard-release affected apparent survival. Methods: We tracked both wild and head-started tortoises via radiotelemetry for 1 year during and 1 year after penning; we determined apparent survival by direct observation of individuals remaining alive and within the site approximately 1.5 years after all enclosure pens had been removed. Key results: Home ranges of free-ranging tortoises were approximately the same in the enclosure pen as they were after the enclosure pen was removed, but apparent survival of free-ranging tortoises at the study site was only 56% after the enclosure was removed. Male adult tortoises had higher apparent survival in the site than did females, and translocation distance was a negative predictor of apparent survival. Release condition did not affect head-started tortoise apparent survival, and overall apparent survival of head-started tortoises was 70% 2 years after release. Conclusions: Head-starting and direct hard release of juveniles are likely to be successful tools for gopher tortoise conservation, whereas population consolidation may cause poor adult survival and/or site fidelity. Implications: Short-distance translocations of wildlife populations should be further studied before this tool is more broadly applied in conservation projects.

  • Probing chemical surface contaminants with a deep ultraviolet spatial heterodyne Raman system

    by Rusha Chatterjee, Katharine Lunny, Michael Hilton, Jay P. Giblin

    Physical Sciences Inc. has developed a standoff deep ultraviolet (DUV) Raman sensor for the detection of explosive residues. The sensor is based on a solid-state DUV excitation source coupled with a Spatial Heterodyne Spectrometer receiver. The sensor measures Raman signals across a ~830–2680 cm-1 spectral range from a 2.6 cm2 interrogation area from a 1 m standoff in a single snapshot with a 17 cm-1 spectral resolution. Acquired spectra are processed through an on-board deep learning spectral correlation algorithm that provides real-time target identification. Developmental testing of the sensor has been conducted in a laboratory environment against explosive simulants including potassium chlorate, ammonium nitrate, and urea in bulk form as well as residues deposited on various substrates including plastic, glass, and metals. These measurements have demonstrated the system’s ability to measure Raman spectra and identify targets in 1 to 120 seconds.


  • Open Access

    Utility of machine learning for segmenting camera trap time‐lapse recordings

    by Michael L. Hilton, Jeffrey M. Goessling, Leah M. Knezevich, Jane M. Downer

    Camera trap time‐lapse recordings can collect vast amounts of data on wildlife in their natural settings. Transforming these data into information useful to ecologists is a major challenge. Machine learning techniques show promise for becoming important tools in the cost‐effective analysis of camera trap data, but only if they become readily available to researchers without requiring advanced computing skills and resources. We present a new suite of software tools that reduce the amount of human effort needed to segment time‐lapse, camera trap recordings in preparation for analysis. The tools incorporate a convolutional neural network trained to detect a focal species and to generate a draft video segmentation indicating the ranges of time when the focal species is present. We evaluated the utility of our neural network by comparing manual and automatic segmentations of 64 time‐lapse recordings of gopher tortoise ( Gopherus polyphemus ) burrows, recorded in Pinellas County, Florida, USA between 25 November 2020 and 30 November 2020. The neural network correctly found 130 of the 145 segments containing tortoises (89.7%), whereas student graders found 135 segments (93.1%). A year of experience using the new software suite in an ongoing study of gopher tortoises deploying 12 camera traps indicates one person, assisted by machine learning algorithms, can segment a week's worth of time‐lapse recordings—11.5 hours of standard‐speed video—in under 3 hours. We concluded that the use of machine learning algorithms is practical and allows researchers to process large volumes of time‐lapse data with minimal human effort.