megadetector 10.0.13__py3-none-any.whl

megadetector/data_management/cct_to_md.py

@@ -0,0 +1,184 @@
+"""
+
+cct_to_md.py
+
+"Converts" a COCO Camera Traps file to a MD results file.  Currently ignores
+non-bounding-box annotations, and gives all annotations a confidence of 1.0.
+
+The only reason to do this is if you are going to add information to an existing
+CCT-formatted dataset, and you want to do that in Timelapse.
+
+Currently assumes that width and height are present in the input data, does not
+read them from images.
+
+"""
+
+#%% Constants and imports
+
+import os
+import json
+
+from collections import defaultdict
+from tqdm import tqdm
+
+
+#%% Functions
+
+def cct_to_md(input_filename,output_filename=None):
+    """
+    "Converts" a COCO Camera Traps file to a MD results file.  Currently ignores
+    non-bounding-box annotations.  If the semi-standard "score" field is present in
+    an annotation, or the totally non-standard "conf" field is present, it will be
+    transferred to the output, otherwise a confidence value of 1.0 is assumed for
+    all annotations.
+
+    The main reason to run this script the scenario where you are going to add information
+    to an existing CCT-formatted dataset, and you want to do that in Timelapse.
+
+    Currently assumes that width and height are present in the input data, does not
+    read them from images.
+
+    Args:
+        input_filename (str): the COCO Camera Traps .json file to read
+        output_filename (str, optional): the .json file to write in MD results format
+
+    Returns:
+        dict: MD-formatted results, identical to the content of [output_filename] if
+        [output_filename] is not None
+    """
+
+    ## Validate input
+
+    assert os.path.isfile(input_filename)
+
+    if (output_filename is None):
+
+        tokens = os.path.splitext(input_filename)
+        assert len(tokens) == 2
+        output_filename = tokens[0] + '_md-format' + tokens[1]
+
+
+    ## Read input
+
+    with open(input_filename,'r') as f:
+        d = json.load(f)
+
+    for s in ['annotations','images','categories']:
+        assert s in d.keys(), 'Cannot find key {} in input file, is this a CCT file?'.format(s)
+
+
+    ## Prepare metadata
+
+    image_id_to_annotations = defaultdict(list)
+
+    # ann = d['annotations'][0]
+    for ann in tqdm(d['annotations']):
+        image_id_to_annotations[ann['image_id']].append(ann)
+
+    category_id_to_name = {}
+    for cat in d['categories']:
+        category_id_to_name[str(cat['id'])] = cat['name']
+
+    results = {}
+
+    info = {}
+    info['format_version'] = '1.4'
+    info['detector'] = 'cct_to_md'
+    results['info'] = info
+    results['detection_categories'] = category_id_to_name
+
+
+    ## Process images
+
+    images_out = []
+
+    # im = d['images'][0]
+    for im in tqdm(d['images']):
+
+        im_out = {}
+        im_out['file'] = im['file_name']
+        im_out['location'] = im['location']
+        im_out['id'] = im['id']
+
+        image_h = im['height']
+        image_w = im['width']
+
+        detections = []
+
+        annotations_this_image = image_id_to_annotations[im['id']]
+
+        # This field is no longer included in MD output files by default
+        # max_detection_conf = 0
+
+        for ann in annotations_this_image:
+
+               if 'bbox' in ann:
+
+                   det = {}
+                   det['category'] = str(ann['category_id'])
+                   if 'score' in ann:
+                       det['conf'] = ann['score']
+                   elif 'conf' in ann:
+                       det['conf'] = ann['conf']
+                   else:
+                       det['conf'] = 1.0
+
+                   # MegaDetector: [x,y,width,height] (normalized, origin upper-left)
+                   # CCT: [x,y,width,height] (absolute, origin upper-left)
+                   bbox_in = ann['bbox']
+                   bbox_out = [bbox_in[0]/image_w,bbox_in[1]/image_h,
+                               bbox_in[2]/image_w,bbox_in[3]/image_h]
+                   det['bbox'] = bbox_out
+                   detections.append(det)
+
+              # ...if there's a bounding box
+
+        # ...for each annotation
+
+        im_out['detections'] = detections
+
+        # This field is no longer included in MD output files by default
+        # im_out['max_detection_conf'] = max_detection_conf
+
+        images_out.append(im_out)
+
+    # ...for each image
+
+
+    ## Write output
+
+    results['images'] = images_out
+
+    if output_filename is not None:
+        with open(output_filename,'w') as f:
+            json.dump(results, f, indent=1)
+
+    return results
+
+# ...cct_to_md()
+
+
+#%% Interactive driver
+
+if False:
+
+    pass
+
+    #%%
+
+    input_filename = r"G:\temp\noaa_estuary_fish.json"
+    output_filename = None
+    output_filename = cct_to_md(input_filename,output_filename)
+
+    #%%
+
+    from megadetector.visualization import visualize_detector_output
+
+    visualize_detector_output.visualize_detector_output(
+                              detector_output_path=output_filename,
+                              out_dir=r'g:\temp\fish_output',
+                              images_dir=r'g:\temp\noaa_estuary_fish-images\JPEGImages',
+                              output_image_width=-1,
+                              sample=100,
+                              render_detections_only=True)
+

megadetector/data_management/cct_to_wi.py

@@ -0,0 +1,293 @@
+"""
+
+cct_to_wi.py
+
+Converts COCO Camera Traps .json files to the Wildlife Insights
+batch upload format.
+
+**This is very much just a demo script; all the relevant constants are hard-coded
+at the top of main().**
+
+But given that caveat, it works.  You need to set up all the paths in the "paths" cell
+at the top of main().
+
+Also see:
+
+* https://github.com/ConservationInternational/Wildlife-Insights----Data-Migration
+* https://data.naturalsciences.org/wildlife-insights/taxonomy/search
+
+"""
+
+#%% Imports
+
+import os
+import json
+import pandas as pd
+from collections import defaultdict
+
+
+#%% Main wrapper
+
+def main(): # noqa
+    """
+    Converts COCO Camera Traps .json files to the Wildlife Insights
+    batch upload format; to use this, you need to modify all the paths in the "Paths"
+    cell.
+    """
+
+    #%% Paths
+
+    # A COCO camera traps file with information about this dataset
+    input_file = r'c:\temp\camera_trap_images_no_people\bellevue_camera_traps.2020-12-26.json'
+
+    # A .json dictionary mapping common names in this dataset to dictionaries with the
+    # WI taxonomy fields: common_name, wi_taxon_id, class, order, family, genus, species
+    taxonomy_file = r'c:\temp\camera_trap_images_no_people\bellevue_camera_traps_to_wi.json'
+
+    # The folder where the .csv template files live
+    templates_dir = r'c:\temp\wi_batch_upload_templates'
+
+    # The folder to which you want to write WI-formatted .csv files
+    output_base = r'c:\temp\wi_output'
+
+
+    #%% Path validation
+
+    assert os.path.isfile(input_file)
+    assert os.path.isfile(taxonomy_file)
+    assert os.path.isdir(templates_dir)
+    os.makedirs(output_base,exist_ok = True)
+
+
+    #%% Constants
+
+    projects_file_name = 'Template Wildlife Insights Batch Upload - Projectv1.0.csv'
+    deployments_file_name = 'Template Wildlife Insights Batch Upload - Deploymentv1.0.csv'
+    images_file_name = 'Template Wildlife Insights Batch Upload - Imagev1.0.csv'
+    cameras_file_name = 'Template Wildlife Insights Batch Upload - Camerav1.0.csv'
+
+    assert all([os.path.isfile(os.path.join(templates_dir,fn)) for fn in \
+                [projects_file_name,deployments_file_name,images_file_name,cameras_file_name]])
+
+
+    #%% Project information
+
+    project_info = {}
+    project_info['project_name'] = 'Bellevue Camera Traps'
+    project_info['project_id'] = 'bct_001'
+    project_info['project_short_name'] = 'BCT'
+    project_info['project_objectives'] = 'none'
+    project_info['project_species'] = 'Multiple'
+    project_info['project_species_individual'] = ''
+    project_info['project_sensor_layout'] = 'Convenience'
+    project_info['project_sensor_layout_targeted_type'] = ''
+    project_info['project_bait_use'] = 'No'
+    project_info['project_bait_type'] = 'None'
+    project_info['project_stratification'] = 'No'
+    project_info['project_stratification_type'] = ''
+    project_info['project_sensor_method'] = 'Sensor Detection'
+    project_info['project_individual_animals'] = 'No'
+    project_info['project_admin'] = 'Dan Morris'
+    project_info['project_admin_email'] = 'cameratraps@lila.science'
+    project_info['country_code'] = 'USA'
+    project_info['embargo'] = str(0)
+    project_info['initiative_id'] = ''
+    project_info['metadata_license'] = 'CC0'
+    project_info['image_license'] = 'CC0'
+
+    project_info['project_blank_images'] = 'No'
+    project_info['project_sensor_cluster'] = 'No'
+
+    camera_info = {}
+    camera_info['project_id'] = project_info['project_id']
+    camera_info['camera_id'] = '0000'
+    camera_info['make'] = ''
+    camera_info['model'] = ''
+    camera_info['serial_number'] = ''
+    camera_info['year_purchased'] = ''
+
+    deployment_info = {}
+
+    deployment_info['project_id'] = project_info['project_id']
+    deployment_info['deployment_id'] = 'test_deployment'
+    deployment_info['subproject_name'] = 'test_subproject'
+    deployment_info['subproject_design'] = ''
+    deployment_info['placename'] = 'yard'
+    deployment_info['longitude'] = '47.6101'
+    deployment_info['latitude'] = '-122.2015'
+    deployment_info['start_date'] = '2016-01-01 00:00:00'
+    deployment_info['end_date'] = '2026-01-01 00:00:00'
+    deployment_info['event_name'] = ''
+    deployment_info['event_description'] = ''
+    deployment_info['event_type'] = ''
+    deployment_info['bait_type'] = ''
+    deployment_info['bait_description'] = ''
+    deployment_info['feature_type'] = 'None'
+    deployment_info['feature_type_methodology'] = ''
+    deployment_info['camera_id'] = camera_info['camera_id']
+    deployment_info['quiet_period'] = str(60)
+    deployment_info['camera_functioning'] = 'Camera Functioning'
+    deployment_info['sensor_height'] = 'Chest height'
+    deployment_info['height_other'] = ''
+    deployment_info['sensor_orientation'] = 'Parallel'
+    deployment_info['orientation_other'] = ''
+    deployment_info['recorded_by'] = 'Dan Morris'
+
+    image_info = {}
+    image_info['identified_by'] = 'Dan Morris'
+
+
+    #%% Read templates
+
+    def parse_fields(templates_dir,file_name):
+
+        with open(os.path.join(templates_dir,file_name),'r') as f:
+            lines = f.readlines()
+            lines = [s.strip() for s in lines if len(s.strip().replace(',','')) > 0]
+            assert len(lines) == 1, 'Error processing template {}'.format(file_name)
+            fields = lines[0].split(',')
+            print('Parsed {} columns from {}'.format(len(fields),file_name))
+        return fields
+
+    projects_fields = parse_fields(templates_dir,projects_file_name)
+    deployments_fields = parse_fields(templates_dir,deployments_file_name)
+    images_fields = parse_fields(templates_dir,images_file_name)
+    cameras_fields = parse_fields(templates_dir,cameras_file_name)
+
+
+    #%% Compare dictionary to template lists
+
+    def compare_info_to_template(info,template_fields,name):
+
+        for s in info.keys():
+            assert s in template_fields,'Field {} not specified in {}_fields'.format(s,name)
+        for s in template_fields:
+            assert s in info.keys(),'Field {} not specified in {}_info'.format(s,name)
+
+
+    def write_table(file_name,info,template_fields):
+
+        assert len(info) == len(template_fields)
+
+        project_output_file = os.path.join(output_base,file_name)
+        with open(project_output_file,'w') as f:
+
+            # Write the header
+            for i_field,s in enumerate(template_fields):
+                f.write(s)
+                if i_field != len(template_fields)-1:
+                    f.write(',')
+            f.write('\n')
+
+            # Write values
+            for i_field,s in enumerate(template_fields):
+                f.write(info[s])
+                if i_field != len(template_fields)-1:
+                    f.write(',')
+            f.write('\n')
+
+
+    #%% Project file
+
+    compare_info_to_template(project_info,projects_fields,'project')
+    write_table(projects_file_name,project_info,projects_fields)
+
+
+    #%% Camera file
+
+    compare_info_to_template(camera_info,cameras_fields,'camera')
+    write_table(cameras_file_name,camera_info,cameras_fields)
+
+
+    #%% Deployment file
+
+    compare_info_to_template(deployment_info,deployments_fields,'deployment')
+    write_table(deployments_file_name,deployment_info,deployments_fields)
+
+
+    #%% Images file
+
+    # Read .json file with image information
+    with open(input_file,'r') as f:
+        input_data = json.load(f)
+
+    # Read taxonomy dictionary
+    with open(taxonomy_file,'r') as f:
+        taxonomy_mapping = json.load(f)
+
+    url_base = taxonomy_mapping['url_base']
+    taxonomy_mapping = taxonomy_mapping['taxonomy']
+
+    # Populate output information
+    # df = pd.DataFrame(columns = images_fields)
+
+    category_id_to_name = {cat['id']:cat['name'] for cat in input_data['categories']}
+
+    image_id_to_annotations = defaultdict(list)
+
+    annotations = input_data['annotations']
+
+    # annotation = annotations[0]
+    for annotation in annotations:
+        image_id_to_annotations[annotation['image_id']].append(
+            category_id_to_name[annotation['category_id']])
+
+    rows = []
+
+    # im = input_data['images'][0]
+    for im in input_data['images']:
+
+        row = {}
+
+        url = url_base + im['file_name'].replace('\\','/')
+        row['project_id'] = project_info['project_id']
+        row['deployment_id'] = deployment_info['deployment_id']
+        row['image_id'] = im['id']
+        row['location'] = url
+        row['identified_by'] = image_info['identified_by']
+
+        category_names = image_id_to_annotations[im['id']]
+        assert len(category_names) == 1
+        category_name = category_names[0]
+
+        taxon_info = taxonomy_mapping[category_name]
+
+        assert len(taxon_info.keys()) == 7
+
+        for s in taxon_info.keys():
+            row[s] = taxon_info[s]
+
+        # We don't have counts, but we can differentiate between zero and 1
+        if category_name == 'empty':
+            row['number_of_objects'] = 0
+        else:
+            row['number_of_objects'] = 1
+
+        assert isinstance(im['datetime'],str)
+
+        row['uncertainty'] = None
+        row['timestamp'] = im['datetime']
+        row['highlighted'] = 0
+        row['age'] = None
+        row['sex'] = None
+        row['animal_recognizable'] = 'No'
+        row['individual_id'] = None
+        row['individual_animal_notes'] = None
+        row['markings'] = None
+
+        assert len(row) == len(images_fields)
+        rows.append(row)
+
+    # ...for each image
+
+    df = pd.DataFrame(rows)
+
+    df.to_csv(os.path.join(output_base,images_file_name),index=False)
+
+# ...main()
+
+
+#%% Command-line driver
+
+if __name__ == '__main__':
+    main()