A Collection of ML Tools for Conservation Research

---

Documentation for package ‘animl’ version 1.1.0

• DESCRIPTION file.

Help Pages

animl	Title
applyPredictions	Apply Classifier Predictions and Merge DataFrames
bestGuess	Select Best Classification From Multiple Frames
buildFileManifest	Extract exif Data and Create File Manifest
checkFile	Check for files existence and prompt user if they want to load
convertCoordinates	Convert bbox from Relative to Absolute Coordinates
cropImageGenerator	Tensorflow data generator that crops images to bounding box.
cropImageTrainGenerator	Tensorflow data generator for training that crops images to bounding box.
detectObject	Run MD on a Single Image
detectObjectBatch	Run MegaDetector on a batch of images
extractBoxes	Extract bounding boxes and save as new image from a batch of images
extractBoxesFromFlat	Extract crops from a single image represented by a processed dataframe
extractBoxesFromMD	Extract bounding boxes for a single image and save as new images
getAnimals	Return a dataframe of only MD animals
getEmpty	Return MD empty, vehicle and human images in a dataframe
imageAugmentationColor	Perform image augmentation through random color adjustments on an image/label pair.
imageAugmentationGeometry	Perform random geometric transformations on an image.
ImageGenerator	Tensorflow data generator that resizes images.
ImageGeneratorSize	Tensorflow data generator that resizes images and returns original image size.
imageLabel	Load image and return a tensor with an image and a corresponding label.
imageLabelCrop	Load image, crop and return a tensor with an image and a corresponding label.
imagesFromVideos	Extract frames from video for classification
loadData	Load .csv or .Rdata file
loadImage	Load an image and return the full size image as an image tensor.
loadImageResize	Load and resize an image and return an image tensor.
loadImageResizeCrop	Load, resize and crop an image and return an image tensor.
loadImageResizeSize	Load and resize an image and return an image tensor as well as a tensor with the original image size.
loadMDModel	Load MegaDetector model file from directory or file
parseMD	parse MD results into a simple dataframe
parseMDjson	converte the JSON file produced bye the Python version of MegaDetector into the format produced by detectObjectBatch
plotBoxes	Plot bounding boxes on image from md results
predictSpecies	Classifies Crops Using Specified Models
processYOLO5	Process YOLO5 output and convert to MD format
resizePad	Resize an image with padding
saveData	Save Data to Given File
sequenceClassification	Leverage sequences to classify images
setupDirectory	Set Working Directory and Save File Global Variables
symlinkMD	Create SymLink Directories and Sort Classified Images Based on MD Results
symlinkSpecies	Create SymLink Directories and Sort Classified Images
symUnlink	Remove Symlinks
testMD	Select a Random Image and Run Through MegaDetector
updateResults	Title