A Semi-Automated Single Day Image Differencing Technique to Identify Animals in Aerial Imagery

Our research presents a proof-of-concept that explores a new and innovative method to identify large animals in aerial imagery with single day image differencing. We acquired two aerial images of eight fenced pastures and conducted a principal component analysis of each image. We then subtracted the first principal component of the two pasture images followed by heuristic thresholding to generate polygons. The number of polygons represented the number of potential cattle (Bos taurus) and horses (Equus caballus) in the pasture. The process was considered semi-automated because we were not able to automate the identification of spatial or spectral thresholding values. Imagery was acquired concurrently with ground counts of animal numbers. Across the eight pastures, 82% of the animals were correctly identified, mean percent commission was 53%, and mean percent omission was 18%. The high commission error was due to small mis-alignments generated from image-to-image registration, misidentified shadows, and grouping behavior of animals. The high probability of correctly identifying animals suggests short time interval image differencing could provide a new technique to enumerate wild ungulates occupying grassland ecosystems, especially in isolated or difficult to access areas. To our knowledge, this was the first attempt to use standard change detection techniques to identify and enumerate large ungulates.

[1]  W. Perryman,et al.  COUNTING STELLER SEA LION PUPS IN ALASKA: AN EVALUATION OF MEDIUMFORMAT, COLOR AERIAL PHOTOGRAPHY , 2001 .

[2]  P. Chavez,et al.  Extracting spectral contrast in landsat thematic mapper image data using selective principal component analysis , 1989 .

[3]  David S. Gilmer,et al.  Goose counts from aerial photographs using an optical digitizer , 1988 .

[4]  G. White,et al.  How many mule deer are there? Challenges of credibility in Colorado , 2004 .

[5]  Sightability model for California bighorn sheep in canyonlands using forward-looking infrared (FLIR) , 2004 .

[6]  Timothy Evans,et al.  A Review and Assessment of Land-Use Change Models Dynamics of Space, Time, and Human Choice , 2002 .

[7]  B. Brockett.  Accuracy, bias and precision of helicopter-based counts of black rhinoceros in Pilanesberg National Park, South Africa , 2002 .

[8]  W. Linklater,et al.  Escape behaviour of feral horses during a helicopter count , 2002 .

[9]  Francisco José Madrid-Cuevas,et al.  Solving the process of hysteresis without determining the optimal thresholds , 2010, Pattern Recognit..

[10]  J. Tracey,et al.  Some human, aircraft and animal factors affecting aerial surveys: how to enumerate animals from the air , 2008 .

[11]  L. Rivest,et al.  STATISTICAL METHODS FOR ESTIMATING CARIBOU ABUNDANCE USING POSTCALVING AGGREGATIONS DETECTED BY RADIO TELEMETRY , 1998 .

[12]  Gerald L. Kooyman,et al.  An Emperor Penguin Population Estimate: The First Global, Synoptic Survey of a Species from Space , 2012, PloS one.

[13]  H. Jachmann.  Comparison of aerial counts with ground counts for large African herbivores , 2002 .

[14]  Nicolas Coudray,et al.  Robust threshold estimation for images with unimodal histograms , 2010, Pattern Recognit. Lett..

[15]  Henrique G. Momm,et al.  Estimating Speed and Direction of Small Dynamic Targets through Optical Satellite Imaging , 2010, Remote. Sens..

[16]  Mustapha Mouloua,et al.  Automation and Human Performance : Theory and Applications , 1996 .

[17]  Robert Weibel,et al.  Discovering relative motion patterns in groups of moving point objects , 2005, Int. J. Geogr. Inf. Sci..

[18]  J. Aars,et al.  Estimating the Number of Walruses in Svalbard from Aerial Surveys and Behavioural Data from Satellite Telemetry , 2009 .

[19]  Magnus Andersen,et al.  ABUNDANCE OF RINGED SEALS (PUSA HISPIDA) IN THE FJORDS OF SPITSBERGEN, SVALBARD, DURING THE PEAK MOLTING PERIOD , 2006 .

[20]  J. Townshend,et al.  Impact of sensor's point spread function on land cover characterization: Assessment and deconvolution , 2002 .

[21]  Observer variability in estimating numbers: An experiment , 1982 .

[22]  Joseph Revelli,et al.  The Image Processing Handbook, 4th Edition , 2003, J. Electronic Imaging.

[23]  Volker Walter,et al.  Automatic interpretation of digital maps , 2011 .

[24]  D. Lu,et al.  Change detection techniques , 2004 .

[25]  J. Russell,et al.  Post-calving photo-census of the Rivière George caribou herd in July 1993 , 1996 .

[26]  M. Lowry.  COUNTS OF CALIFORNIA SEA LION (ZALOPHUS CALIFORNIANUS) PUPS FROM AERIAL COLOR PHOTOGRAPHS AND FROM THE GROUND: A COMPARISON OF TWO METHODS , 1999 .

[27]  Dezhen Song,et al.  A Low False Negative Filter for Detecting Rare Bird Species From Short Video Segments Using a Probable Observation Data Set-Based EKF Method , 2010, IEEE Transactions on Image Processing.

[28]  Andrea S. Laliberte,et al.  Automated wildlife counts from remotely sensed imagery , 2003 .

[29]  Pol Coppin,et al.  Review ArticleDigital change detection methods in ecosystem monitoring: a review , 2004 .

[30]  S. Pizer,et al.  The Image Processing Handbook , 1994 .

[31]  Bruce C. Lubow,et al.  Validating Aerial Photographic Mark–Recapture for Naturally Marked Feral Horses , 2009 .

[32]  Dengsheng Lu,et al.  Land‐cover binary change detection methods for use in the moist tropical region of the Amazon: a comparative study , 2005 .

[33]  A. Sinclair.  Population increases of buffalo and wildebeest in the Serengeti , 1973 .

[34]  M. Conroy,et al.  Analysis and Management of Animal Populations , 2002 .

[35]  Blake G. Crowther,et al.  An airborne multispectral video/radiometer remote sensing system: Development and calibration , 1994 .

[36]  Lloyd L. Coulter,et al.  DETECTION OF PIXEL-LEVEL LAND-COVER CHANGES WITH MULTI-TEMPORAL IMAGERY: THEORY AND EXAMPLES WITH IMAGERY OF 1 METER AND 1 KILOMETER SPATIAL RESOLUTIONS , 2002 .

[37]  M. Endsley.  Automation and situation awareness. , 1996 .

[38]  J. Zeh,et al.  Abundance of Bering-Chukchi-Beaufort bowhead whales (Balaena mysticetus) in 2004 estimated from photo-identification data , 2023, J. Cetacean Res. Manage..

[39]  M. Cody,et al.  Observer variability in pinniped counts: Ground-based enumeration of walruses at haul-out sites , 2005 .

[40]  A. N. R. Law,et al.  Automating the Analysis of Remotely Sensed Data , 2004 .

[41]  Louis-Paul Rivest,et al.  Calving photocensus of the Rivière George Caribou Herd and comparison with an independent census , 1996 .

[42]  Paul L. Rosin,et al.  Remote sensing image thresholding methods for determining landslide activity , 2005 .

[43]  M. L. Wolfe,et al.  Comparison of Bison Population Estimates with a Total Count , 1989 .

[44]  P. Bayliss,et al.  Correcting bias in aerial survey population estimates of feral livestock in Northern Australia using the double-count technique , 1989 .

[45]  Takeo Kanade,et al.  People detection and tracking in high resolution panoramic video mosaic , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[46]  P. Terletzky.  Utilizing Remote Sensing and Geospatial Techniques to Determine Detection Probabilities of Large Mammals , 2013 .

[47]  S. Hess.  Aerial survey methodology for bison population estimation in Yellowstone National Park , 2002 .

[48]  M. Heide-Jørgensen,et al.  Aerial digital photographic surveys of narwhals, Monodon monoceros, in northwest Greenland , 2004 .

[49]  M. Gilabert,et al.  Vegetation dynamics from NDVI time series analysis using the wavelet transform , 2009 .