Add KITTI format

cvat/apps/dataset_manager/formats/kitti.py

@@ -0,0 +1,53 @@
+# Copyright (C) 2021 Intel Corporation
+#
+# SPDX-License-Identifier: MIT
+
+import os.path as osp
+from tempfile import TemporaryDirectory
+
+from datumaro.components.dataset import Dataset
+from datumaro.plugins.kitti_format.format import KittiPath, write_label_map
+from pyunpack import Archive
+
+from cvat.apps.dataset_manager.bindings import (GetCVATDataExtractor,
+    ProjectData, import_dm_annotations)
+from cvat.apps.dataset_manager.util import make_zip_archive
+
+from .registry import dm_env, exporter, importer
+from .utils import make_colormap
+
+
+@exporter(name='KITTI', ext='ZIP', version='1.0')
+def _export(dst_file, instance_data, save_images=False):
+    dataset = Dataset.from_extractors(GetCVATDataExtractor(instance_data,
+        include_images=save_images), env=dm_env)
+
+    with TemporaryDirectory() as tmp_dir:
+        dataset.transform('polygons_to_masks')
+        dataset.transform('merge_instance_segments')
+        dataset.export(tmp_dir, format='kitti',
+            label_map={k: v[0] for k, v in make_colormap(instance_data).items()},
+            apply_colormap=True, save_images=save_images
+        )
+
+        make_zip_archive(tmp_dir, dst_file)
+
+@importer(name='KITTI', ext='ZIP', version='1.0')
+def _import(src_file, instance_data):
+    with TemporaryDirectory() as tmp_dir:
+        Archive(src_file.name).extractall(tmp_dir)
+
+        color_map = {k: v[0] for k, v in make_colormap(instance_data).items()}
+        color_map_path = osp.join(tmp_dir, KittiPath.LABELMAP_FILE)
+        if not osp.isfile(color_map_path):
+            write_label_map(color_map_path, color_map)
+
+        dataset = Dataset.import_from(tmp_dir, format='kitti', env=dm_env)
+        labels_meta = instance_data.meta['project']['labels'] \
+            if isinstance(instance_data, ProjectData) else instance_data.meta['task']['labels']
+        if 'background' not in [label['name'] for _, label in labels_meta]:
+            dataset.filter('/item/annotation[label != "background"]',
+                filter_annotations=True)
+        dataset.transform('masks_to_polygons')
+
+        import_dm_annotations(dataset, instance_data)

cvat/apps/dataset_manager/formats/registry.py

@@ -121,4 +121,4 @@ def make_exporter(name):
 import cvat.apps.dataset_manager.formats.icdar
 import cvat.apps.dataset_manager.formats.velodynepoint
 import cvat.apps.dataset_manager.formats.pointcloud
-
+import cvat.apps.dataset_manager.formats.kitti

cvat/apps/dataset_manager/formats/utils.py

@@ -7,7 +7,6 @@
 
 from datumaro.util.os_util import make_file_name
 
-
 def get_color_from_index(index):
     def get_bit(number, index):
         return (number >> index) & 1

cvat/apps/dataset_manager/tests/assets/annotations.json

@@ -1168,5 +1168,23 @@
       }
     ],
     "tracks": []
+  },
+  "KITTI 1.0": {
+    "version": 0,
+    "tags": [],
+    "shapes": [
+      {
+        "type": "polygon",
+        "occluded": false,
+        "z_order": 0,
+        "points": [10.0, 20.0, 10.0, 25.0, 20.0, 10.0, 20.0, 25.0, 10.0, 20.0],
+        "frame": 0,
+        "label_id": null,
+        "group": 0,
+        "source": "manual",
+        "attributes": []
+      }
+    ],
+    "tracks": []
   }
 }

cvat/apps/dataset_manager/tests/test_formats.py

@@ -295,8 +295,8 @@ def test_export_formats_query(self):
             'ICDAR Localization 1.0',
             'ICDAR Segmentation 1.0',
             'Kitti Raw Format 1.0',
-            'Sly Point Cloud Format 1.0'
-
+            'Sly Point Cloud Format 1.0',
+            'KITTI 1.0'
         })
 
     def test_import_formats_query(self):
@@ -323,6 +323,7 @@ def test_import_formats_query(self):
             'ICDAR Segmentation 1.0',
             'Kitti Raw Format 1.0',
             'Sly Point Cloud Format 1.0',
+            'KITTI 1.0',
             'Datumaro 1.0',
             'Datumaro 3D 1.0'
         })
@@ -371,6 +372,7 @@ def test_empty_images_are_exported(self):
             ('ICDAR Recognition 1.0', 'icdar_word_recognition'),
             ('ICDAR Localization 1.0', 'icdar_text_localization'),
             ('ICDAR Segmentation 1.0', 'icdar_text_segmentation'),
+            # ('KITTI 1.0', 'kitti') format does not support empty annotations
         ]:
             with self.subTest(format=format_name):
                 if not dm.formats.registry.EXPORT_FORMATS[format_name].ENABLED:
@@ -784,25 +786,14 @@ def _generate_annotations(self, task, annotation_format):
                 "type": "rectangle",
                 "occluded": False,
             }]
-        elif annotation_format == "VGGFace2 1.0":
-            shapes = [{
-                "frame": 1,
-                "label_id": task["labels"][1]["id"],
-                "group": None,
-                "source": "manual",
-                "attributes": [],
-                "points": [2.0, 2.1, 40, 50.7],
-                "type": "rectangle",
-                "occluded": False
-            }]
         else:
             rectangle_shape_wo_attrs = {
                 "frame": 1,
                 "label_id": task["labels"][1]["id"],
                 "group": 0,
                 "source": "manual",
                 "attributes": [],
-                "points": [2.0, 2.1, 40, 50.7],
+                "points": [2.0, 2.1, 40, 10.7],
                 "type": "rectangle",
                 "occluded": False,
             }
@@ -822,7 +813,7 @@ def _generate_annotations(self, task, annotation_format):
                         "value": task["labels"][0]["attributes"][1]["default_value"]
                     }
                 ],
-                "points": [1.0, 2.1, 10.6, 53.22],
+                "points": [1.0, 2.1, 10.6, 13.22],
                 "type": "rectangle",
                 "occluded": False,
             }
@@ -837,7 +828,7 @@ def _generate_annotations(self, task, annotation_format):
                     {
                         "frame": 0,
                         "attributes": [],
-                        "points": [1.0, 2.1, 10.6, 53.22, 100, 300.222],
+                        "points": [1.0, 2.1, 10.6, 53.22, 30, 20.222],
                         "type": "polygon",
                         "occluded": False,
                         "outside": False
@@ -870,7 +861,7 @@ def _generate_annotations(self, task, annotation_format):
             }
 
             if annotation_format == "VGGFace2 1.0":
-                shapes = rectangle_shape_wo_attrs
+                shapes = [rectangle_shape_wo_attrs]
             elif annotation_format == "CVAT 1.1":
                 shapes = [rectangle_shape_wo_attrs,
                     rectangle_shape_with_attrs]
@@ -880,8 +871,8 @@ def _generate_annotations(self, task, annotation_format):
             else:
                 shapes = [rectangle_shape_wo_attrs,
                     rectangle_shape_with_attrs]
-                tags = tag_wo_attrs
-                tracks = track_wo_attrs
+                tags = [tag_wo_attrs]
+                tracks = [track_wo_attrs]
 
         annotations = {
             "version": 0,
@@ -917,7 +908,6 @@ def test_can_import_annotations_for_image_with_dots_in_filename(self):
 
             images = self._generate_task_images(3, "img0.0.0")
             task = self._generate_task(images, format_name)
-            self._generate_annotations(task, format_name)
 
             with self.subTest(format=format_name):
                 if not f.ENABLED:

cvat/apps/dataset_manager/tests/test_rest_api_formats.py

@@ -871,6 +871,7 @@ def test_api_v1_dump_empty_frames(self):
                 with self.subTest(format=upload_format_name):
                     if upload_format_name in [
                         "MOTS PNG 1.0",  # issue #2925 and changed points values
+                        "KITTI 1.0", # format does not support empty annotation
                     ]:
                         self.skipTest("Format is fail")
                     images = self._generate_task_images(3)
@@ -916,7 +917,8 @@ def test_api_v1_rewriting_annotations(self):
                         "MOT 1.1", "MOTS PNG 1.0", \
                         "PASCAL VOC 1.1", "Segmentation mask 1.1", \
                         "TFRecord 1.0", "YOLO 1.1", "ImageNet 1.0", \
-                        "WiderFace 1.0", "VGGFace2 1.0", "Datumaro 1.0" \
+                        "WiderFace 1.0", "VGGFace2 1.0", "KITTI 1.0", \
+                        "Datumaro 1.0" \
                     ]:
                         self._create_annotations(task, dump_format_name, "default")
                     else:
@@ -1007,6 +1009,7 @@ def test_api_v1_tasks_annotations_dump_and_upload_with_datumaro(self):
                         "ICDAR Segmentation 1.0", # changed points values
                         'Kitti Raw Format 1.0',
                         'Sly Point Cloud Format 1.0',
+                        'KITTI 1.0', # changed points values
                         'Datumaro 3D 1.0'
                     ]:
                         self.skipTest("Format is fail")
@@ -1028,7 +1031,8 @@ def test_api_v1_tasks_annotations_dump_and_upload_with_datumaro(self):
                         "MOT 1.1", "MOTS PNG 1.0", \
                         "PASCAL VOC 1.1", "Segmentation mask 1.1", \
                         "TFRecord 1.0", "YOLO 1.1", "ImageNet 1.0", \
-                        "WiderFace 1.0", "VGGFace2 1.0", "Datumaro 1.0", \
+                        "WiderFace 1.0", "VGGFace2 1.0", "KITTI 1.0", \
+                        "Datumaro 1.0", \
                     ]:
                         self._create_annotations(task, dump_format_name, "default")
                     else:

cvat/apps/engine/tests/test_rest_api.py

@@ -4811,6 +4811,10 @@ def _get_initial_annotation(annotation_format):
                 annotations["shapes"] = points_wo_attrs \
                                       + rectangle_shapes_wo_attrs
 
+            elif annotation_format == "KITTI 1.0":
+                annotations["shapes"] = rectangle_shapes_wo_attrs \
+                                            + polygon_shapes_wo_attrs
+
             elif annotation_format == "Market-1501 1.0":
                 tags_with_attrs = [{
                     "frame": 1,

site/content/en/docs/manual/advanced/formats/format-coco.md

@@ -5,11 +5,11 @@ weight: 5
 
 # [MS COCO Object Detection](http://cocodataset.org/#format-data)
 
-- [Format specification](https://github.com/openvinotoolkit/datumaro/blob/develop/docs/formats/coco_user_manual.md#format-specification)
+- [Format specification](https://openvinotoolkit.github.io/datumaro/docs/formats/coco/)
 
 ## COCO export
 
-Downloaded file: a zip archive with the structure described [here](https://github.com/openvinotoolkit/datumaro/blob/develop/docs/formats/coco_user_manual.md#load-coco-dataset)
+Downloaded file: a zip archive with the structure described [here](https://openvinotoolkit.github.io/datumaro/docs/formats/coco/#import-coco-dataset)
 
 - supported annotations: Polygons, Rectangles
 - supported attributes:
@@ -21,13 +21,13 @@ Downloaded file: a zip archive with the structure described [here](https://githu
   - `score` (number) - the annotation `score` field
   - arbitrary attributes - will be stored in the `attributes` annotation section
 
-Support for COCO tasks via Datumaro is described [here](https://github.com/openvinotoolkit/datumaro/blob/develop/docs/formats/coco_user_manual.md#export-to-coco)
+Support for COCO tasks via Datumaro is described [here](https://openvinotoolkit.github.io/datumaro/docs/formats/coco/#export-to-other-formats)
 For example, [support for COCO keypoints over Datumaro](https://github.com/openvinotoolkit/cvat/issues/2910#issuecomment-726077582):
 
 1. Install [Datumaro](https://github.com/openvinotoolkit/datumaro)
    `pip install datumaro`
-1. Export the task in the `Datumaro` format, unzip
-1. Export the Datumaro project in `coco` / `coco_person_keypoints` formats
+2. Export the task in the `Datumaro` format, unzip
+3. Export the Datumaro project in `coco` / `coco_person_keypoints` formats
    `datum export -f coco -p path/to/project [-- --save-images]`
 
 This way, one can export CVAT points as single keypoints or
@@ -36,29 +36,29 @@ keypoint lists (without the `visibility` COCO flag).
 ## COCO import
 
 Uploaded file: a single unpacked `*.json` or a zip archive with the structure described
-[here](https://github.com/openvinotoolkit/datumaro/blob/develop/docs/formats/coco_user_manual.md#load-coco-dataset)
+[here](https://openvinotoolkit.github.io/datumaro/docs/formats/coco/#import-coco-dataset)
 (without images).
 
 - supported annotations: Polygons, Rectangles (if the `segmentation` field is empty)
 
 ## How to create a task from MS COCO dataset
 
-1. Download the [MS COCO dataset](https://github.com/openvinotoolkit/datumaro/blob/develop/docs/formats/coco_user_manual.md#load-COCO-dataset).
+1. Download the [MS COCO dataset](https://openvinotoolkit.github.io/datumaro/docs/formats/coco/#import-coco-dataset).
 
    For example `val images` and `instances` annotations
 
-1. Create a CVAT task with the following labels:
+2. Create a CVAT task with the following labels:
 
    ```bash
    person bicycle car motorcycle airplane bus train truck boat "traffic light" "fire hydrant" "stop sign" "parking meter" bench bird cat dog horse sheep cow elephant bear zebra giraffe backpack umbrella handbag tie suitcase frisbee skis snowboard "sports ball" kite "baseball bat" "baseball glove" skateboard surfboard "tennis racket" bottle "wine glass" cup fork knife spoon bowl banana apple sandwich orange broccoli carrot "hot dog" pizza donut cake chair couch "potted plant" bed "dining table" toilet tv laptop mouse remote keyboard "cell phone" microwave oven toaster sink refrigerator book clock vase scissors "teddy bear" "hair drier" toothbrush
    ```
 
-1. Select `val2017.zip` as data
+3. Select `val2017.zip` as data
    (See [Creating an annotation task](/docs/manual/basics/creating_an_annotation_task/)
    guide for details)
 
-2. Unpack `annotations_trainval2017.zip`
+4. Unpack `annotations_trainval2017.zip`
 
-3. click `Upload annotation` button,
+5. click `Upload annotation` button,
    choose `COCO 1.1` and select `instances_val2017.json`
    annotation file. It can take some time.