video: adding face detection and person detection samples for beta (#…

…2919)

* video: adding face detection and person detection samples for beta

* updating requirements.txt

* updating test names to faces

* fixing region tag typo

* responding to comments

* reverted tabs to fix  linting errors

* responding to comments

video/cloud-client/analyze/requirements.txt

@@ -1,2 +1,2 @@
-google-cloud-videointelligence==1.12.1
+google-cloud-videointelligence==1.13.0
 google-cloud-storage==1.23.0

video/cloud-client/analyze/video_detect_faces_beta.py

@@ -0,0 +1,85 @@
+# Copyright 2020 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# [START video_detect_faces_beta]
+import io
+from google.cloud import videointelligence_v1p3beta1 as videointelligence
+
+
+def detect_faces(local_file_path="path/to/your/video-file.mp4"):
+    """Detects faces in a video from a local file."""
+
+    client = videointelligence.VideoIntelligenceServiceClient()
+
+    with io.open(local_file_path, "rb") as f:
+        input_content = f.read()
+
+    # Configure the request
+    config = videointelligence.types.FaceDetectionConfig(
+        include_bounding_boxes=True, include_attributes=True
+    )
+    context = videointelligence.types.VideoContext(
+        face_detection_config=config
+    )
+
+    # Start the asynchronous request
+    operation = client.annotate_video(
+        input_content=input_content,
+        features=[videointelligence.enums.Feature.FACE_DETECTION],
+        video_context=context,
+    )
+
+    print("\nProcessing video for face detection annotations.")
+    result = operation.result(timeout=300)
+
+    print("\nFinished processing.\n")
+
+    # Retrieve the first result, because a single video was processed.
+    annotation_result = result.annotation_results[0]
+
+    for annotation in annotation_result.face_detection_annotations:
+        print("Face detected:")
+        for track in annotation.tracks:
+            print(
+                "Segment: {}s to {}s".format(
+                    track.segment.start_time_offset.seconds
+                    + track.segment.start_time_offset.nanos / 1e9,
+                    track.segment.end_time_offset.seconds
+                    + track.segment.end_time_offset.nanos / 1e9,
+                )
+            )
+
+            # Each segment includes timestamped faces that include
+            # characteristics of the face detected.
+            # Grab the first timestamped face
+            timestamped_object = track.timestamped_objects[0]
+            box = timestamped_object.normalized_bounding_box
+            print("Bounding box:")
+            print("\tleft  : {}".format(box.left))
+            print("\ttop   : {}".format(box.top))
+            print("\tright : {}".format(box.right))
+            print("\tbottom: {}".format(box.bottom))
+
+            # Attributes include glasses, headwear, facial hair, smiling,
+            # direction of gaze, etc.
+            print("Attributes:")
+            for attribute in timestamped_object.attributes:
+                print(
+                    "\t{}:{} {}".format(
+                        attribute.name, attribute.value, attribute.confidence
+                    )
+                )
+
+
+# [END video_detect_faces_beta]

video/cloud-client/analyze/video_detect_faces_beta_test.py

@@ -0,0 +1,30 @@
+# Copyright 2020 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import os
+
+import video_detect_faces_beta
+
+RESOURCES = os.path.join(os.path.dirname(__file__), "resources")
+
+
+def test_detect_faces(capsys):
+    local_file_path = os.path.join(RESOURCES, "googlework_short.mp4")
+
+    video_detect_faces_beta.detect_faces(local_file_path=local_file_path)
+
+    out, _ = capsys.readouterr()
+
+    assert "Face detected:" in out
+    assert "Attributes:" in out

video/cloud-client/analyze/video_detect_faces_gcs_beta.py

@@ -0,0 +1,81 @@
+# Copyright 2020 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# [START video_detect_faces_gcs_beta]
+from google.cloud import videointelligence_v1p3beta1 as videointelligence
+
+
+def detect_faces(gcs_uri="gs://YOUR_BUCKET_ID/path/to/your/video.mp4"):
+    """Detects faces in a video."""
+
+    client = videointelligence.VideoIntelligenceServiceClient()
+
+    # Configure the request
+    config = videointelligence.types.FaceDetectionConfig(
+        include_bounding_boxes=True, include_attributes=True
+    )
+    context = videointelligence.types.VideoContext(
+        face_detection_config=config
+    )
+
+    # Start the asynchronous request
+    operation = client.annotate_video(
+        input_uri=gcs_uri,
+        features=[videointelligence.enums.Feature.FACE_DETECTION],
+        video_context=context,
+    )
+
+    print("\nProcessing video for face detection annotations.")
+    result = operation.result(timeout=300)
+
+    print("\nFinished processing.\n")
+
+    # Retrieve the first result, because a single video was processed.
+    annotation_result = result.annotation_results[0]
+
+    for annotation in annotation_result.face_detection_annotations:
+        print("Face detected:")
+        for track in annotation.tracks:
+            print(
+                "Segment: {}s to {}s".format(
+                    track.segment.start_time_offset.seconds
+                    + track.segment.start_time_offset.nanos / 1e9,
+                    track.segment.end_time_offset.seconds
+                    + track.segment.end_time_offset.nanos / 1e9,
+                )
+            )
+
+            # Each segment includes timestamped faces that include
+            # characteristics of the face detected.
+            # Grab the first timestamped face
+            timestamped_object = track.timestamped_objects[0]
+            box = timestamped_object.normalized_bounding_box
+            print("Bounding box:")
+            print("\tleft  : {}".format(box.left))
+            print("\ttop   : {}".format(box.top))
+            print("\tright : {}".format(box.right))
+            print("\tbottom: {}".format(box.bottom))
+
+            # Attributes include glasses, headwear, facial hair, smiling,
+            # direction of gaze, etc.
+            print("Attributes:")
+            for attribute in timestamped_object.attributes:
+                print(
+                    "\t{}:{} {}".format(
+                        attribute.name, attribute.value, attribute.confidence
+                    )
+                )
+
+
+# [END video_detect_faces_gcs_beta]

video/cloud-client/analyze/video_detect_faces_gcs_beta_test.py

@@ -0,0 +1,30 @@
+# Copyright 2020 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import os
+
+import video_detect_faces_gcs_beta
+
+RESOURCES = os.path.join(os.path.dirname(__file__), "resources")
+
+
+def test_detect_faces(capsys):
+    input_uri = "gs://cloud-samples-data/video/googlework_short.mp4"
+
+    video_detect_faces_gcs_beta.detect_faces(gcs_uri=input_uri)
+
+    out, _ = capsys.readouterr()
+
+    assert "Face detected:" in out
+    assert "Attributes:" in out

video/cloud-client/analyze/video_detect_person_beta.py

@@ -0,0 +1,100 @@
+# Copyright 2020 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# [START video_detect_person_beta]
+import io
+from google.cloud import videointelligence_v1p3beta1 as videointelligence
+
+
+def detect_person(local_file_path="path/to/your/video-file.mp4"):
+    """Detects people in a video from a local file."""
+
+    client = videointelligence.VideoIntelligenceServiceClient()
+
+    with io.open(local_file_path, "rb") as f:
+        input_content = f.read()
+
+    # Configure the request
+    config = videointelligence.types.PersonDetectionConfig(
+        include_bounding_boxes=True,
+        include_attributes=True,
+        include_pose_landmarks=True,
+    )
+    context = videointelligence.types.VideoContext(
+        person_detection_config=config
+    )
+
+    # Start the asynchronous request
+    operation = client.annotate_video(
+        input_content=input_content,
+        features=[videointelligence.enums.Feature.PERSON_DETECTION],
+        video_context=context,
+    )
+
+    print("\nProcessing video for person detection annotations.")
+    result = operation.result(timeout=300)
+
+    print("\nFinished processing.\n")
+
+    # Retrieve the first result, because a single video was processed.
+    annotation_result = result.annotation_results[0]
+
+    for annotation in annotation_result.person_detection_annotations:
+        print("Person detected:")
+        for track in annotation.tracks:
+            print(
+                "Segment: {}s to {}s".format(
+                    track.segment.start_time_offset.seconds
+                    + track.segment.start_time_offset.nanos / 1e9,
+                    track.segment.end_time_offset.seconds
+                    + track.segment.end_time_offset.nanos / 1e9,
+                )
+            )
+
+            # Each segment includes timestamped objects that include
+            # characteristic - -e.g.clothes, posture of the person detected.
+            # Grab the first timestamped object
+            timestamped_object = track.timestamped_objects[0]
+            box = timestamped_object.normalized_bounding_box
+            print("Bounding box:")
+            print("\tleft  : {}".format(box.left))
+            print("\ttop   : {}".format(box.top))
+            print("\tright : {}".format(box.right))
+            print("\tbottom: {}".format(box.bottom))
+
+            # Attributes include unique pieces of clothing,
+            # poses, or hair color.
+            print("Attributes:")
+            for attribute in timestamped_object.attributes:
+                print(
+                    "\t{}:{} {}".format(
+                        attribute.name, attribute.value, attribute.confidence
+                    )
+                )
+
+            # Landmarks in person detection include body parts such as
+            # left_shoulder, right_ear, and right_ankle
+            print("Landmarks:")
+            for landmark in timestamped_object.landmarks:
+                print(
+                    "\t{}: {} (x={}, y={})".format(
+                        landmark.name,
+                        landmark.confidence,
+                        landmark.point.x,  # Normalized vertex
+                        landmark.point.y,  # Normalized vertex
+                    )
+                )
+
+
+# [END video_detect_person_beta]

video/cloud-client/analyze/video_detect_person_beta_test.py

@@ -0,0 +1,32 @@
+# Copyright 2020 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import os
+
+import video_detect_person_beta
+
+RESOURCES = os.path.join(os.path.dirname(__file__), "resources")
+
+
+def test_detect_person(capsys):
+    local_file_path = os.path.join(RESOURCES, "googlework_tiny.mp4")
+
+    video_detect_person_beta.detect_person(local_file_path=local_file_path)
+
+    out, _ = capsys.readouterr()
+
+    assert "Person detected:" in out
+    assert "Attributes:" in out
+    assert "x=" in out
+    assert "y=" in out