animl (version 3.2.0)

sequence_classification: Leverage sequences to classify images

Description

This function applies image classifications at a sequence level by leveraging information from multiple images. A sequence is defined as all images at the same camera/station where the time between consecutive images is <=maxdiff. This can improve classification accuracy, but assumes that only one species is present in each sequence. If you regularly expect multiple species to occur in an image or sequence don't use this function.

Usage

sequence_classification(
  animals,
  empty,
  predictions_raw,
  classes,
  station_col = "station",
  empty_class = "",
  human_class = "",
  vehicle_class = "",
  sort_columns = NULL,
  file_col = "filepath",
  maxdiff = 60
)

Value

data frame with predictions and confidence values for animals and empty images

Arguments

animals

sub-selection of all images that contain MD animals

empty

optional, data frame non-animal images (empty, human and vehicle) that will be merged back with animal imagages

predictions_raw

data frame of prediction probabilities from the classifySpecies function

classes

class list associated with classifier model

station_col

a column in the animals and empty data frame that indicates the camera or camera station

empty_class

a string indicating the class that should be considered 'Empty'

human_class

a string indicating the class that should be considered 'Human'

vehicle_class

a string indicating the class that should be considered 'Vehicle'

sort_columns

optional sort order. The default is 'station_column' and datetime.

file_col

a field indicating a single record. The default is FilePath for single images/videos.

maxdiff

maximum difference between images in seconds to be included in a sequence, defaults to 60

Details

This function retains "Empty" classification even if other images within the sequence are predicted to contain animals. Classification confidence is weighted by MD confidence.

Examples

if (FALSE) {
predictions_raw <-classify(classifier, images, resize_width=456, resize_height=456)
animals <- get_animals(images)
empty <- get_empty(images)
animals <- sequence_classification(animals, empty, predictions_raw, classes,
                                   station_column="StationID",
                                   empty_class = "Empty",
                                   sort_columns = c("StationID", "DateTime"),
                                   maxdiff=60)
}