Bird Detector

Utilizing the same workflow as the tree detection model, we have trained a bird detection model for airborne imagery.

#Load deepforest model and set bird label
m = main.deepforest(label_dict={"Bird":0})


We have created a GPU colab tutorial to demonstrate the workflow for using the bird model.

For more information, or specific questions about the bird detection, please create issues on the BirdDetector repo

Predict a folder of images and create a shapefile of annotations for each image

from deepforest import main
from deepforest.visualize import plot_predictions
from deepforest.utilities import boxes_to_shapefile

import rasterio as rio
import geopandas as gpd
from glob import glob
import os
import matplotlib.pyplot as plt
import numpy as np
from shapely import geometry

PATH_TO_DIR = "/Users/benweinstein/Dropbox/Weecology/everglades_species/easyidp/HiddenLittle_03_24_2022"
files = glob("{}/*.JPG".format(PATH_TO_DIR))
m = main.deepforest(label_dict={"Bird":0})
for path in files:
    #use predict_tile if each object is a orthomosaic
    boxes = m.predict_image(path=path)
    #Open each file and get the geospatial information to convert output into a shapefile
    rio_src =
    image =
    #Skip empty images
    if boxes is None:
    #View result
    image = np.rollaxis(image, 0, 3)
    fig = plot_predictions(df=boxes, image=image)   
    #Create a shapefile, in this case img data was unprojected
    shp = boxes_to_shapefile(boxes, root_dir=PATH_TO_DIR, projected=False)
    #Get name of image and save a .shp in the same folder
    basename = os.path.splitext(os.path.basename(path))[0]

Annotating new images

If you would like to train a model, here is a quick video on a simple way to annotate images.

Using a shapefile we could turn it into a dataframe of bounding box annotations by converting the points into boxes. If you already have boxes, you can exclude convert_to_boxes and buffer_size.

df = shapefile_to_annotations(
    rgb="image_path", convert_to_boxes=True, buffer_size=0.15

Optionally we can split these annotations into crops if the image is large and will not fit into memory. This is often the case.

annotations = preprocess.split_raster(

Multi-species models

DeepForest allows training on multiple species annotations. It is often, but not always, useful to start from the general bird detector when trying to identify multiple species. This helps the model focus on learning the multiple classes and not wasting data and time re-learning bird bounding boxes. To load the backboard and box prediction portions of the release model, but create a classification model for more than one species.

Here is an example using the alive/dead tree data stored in the package, but the same logic applies to the bird detector.

m = main.deepforest(num_classes=2, label_dict={"Alive":0,"Dead":0})
deepforest_release_model = main.deepforest()

m.config["train"]["csv_file"] = get_data("testfile_multi.csv") 
m.config["train"]["root_dir"] = os.path.dirname(get_data("testfile_multi.csv"))
m.config["train"]["fast_dev_run"] = True
m.config["batch_size"] = 2
m.config["validation"]["csv_file"] = get_data("testfile_multi.csv") 
m.config["validation"]["root_dir"] = os.path.dirname(get_data("testfile_multi.csv"))
m.config["validation"]["val_accuracy_interval"] = 1

assert m.num_classes == 2


Weinstein, B.G., Garner, L., Saccomanno, V.R., Steinkraus, A., Ortega, A., Brush, K., Yenni, G., McKellar, A.E., Converse, R., Lippitt, C.D., Wegmann, A., Holmes, N.D., Edney, A.J., Hart, T., Jessopp, M.J., Clarke, R.H., Marchowski, D., Senyondo, H., Dotson, R., White, E.P., Frederick, P. and Ernest, S.K.M. (2022), A general deep learning model for bird detection in high resolution airborne imagery. Ecological Applications. Accepted Author Manuscript e2694.