feat: add ObjectTrackingConfig and support apiEndpoint (#249)

protos/google/cloud/videointelligence/v1/video_intelligence.proto

@@ -108,6 +108,9 @@ message VideoContext {
 
   // Config for TEXT_DETECTION.
   TextDetectionConfig text_detection_config = 8;
+
+  // Config for OBJECT_TRACKING.
+  ObjectTrackingConfig object_tracking_config = 13;
 }
 
 // Config for LABEL_DETECTION.
@@ -126,6 +129,22 @@ message LabelDetectionConfig {
   // Supported values: "builtin/stable" (the default if unset) and
   // "builtin/latest".
   string model = 3;
+
+  // The confidence threshold we perform filtering on the labels from
+  // frame-level detection. If not set, it is set to 0.4 by default. The valid
+  // range for this threshold is [0.1, 0.9]. Any value set outside of this
+  // range will be clipped.
+  // Note: for best results please follow the default threshold. We will update
+  // the default threshold everytime when we release a new model.
+  float frame_confidence_threshold = 4;
+
+  // The confidence threshold we perform filtering on the labels from
+  // video-level and shot-level detections. If not set, it is set to 0.3 by
+  // default. The valid range for this threshold is [0.1, 0.9]. Any value set
+  // outside of this range will be clipped.
+  // Note: for best results please follow the default threshold. We will update
+  // the default threshold everytime when we release a new model.
+  float video_confidence_threshold = 5;
 }
 
 // Config for SHOT_CHANGE_DETECTION.
@@ -155,6 +174,14 @@ message FaceDetectionConfig {
   bool include_bounding_boxes = 2;
 }
 
+// Config for OBJECT_TRACKING.
+message ObjectTrackingConfig {
+  // Model to use for object tracking.
+  // Supported values: "builtin/stable" (the default if unset) and
+  // "builtin/latest".
+  string model = 1;
+}
+
 // Config for TEXT_DETECTION.
 message TextDetectionConfig {
   // Language hint can be specified if the language to be detected is known a
@@ -163,6 +190,11 @@ message TextDetectionConfig {
   //
   // Automatic language detection is performed if no hint is provided.
   repeated string language_hints = 1;
+
+  // Model to use for text detection.
+  // Supported values: "builtin/stable" (the default if unset) and
+  // "builtin/latest".
+  string model = 2;
 }
 
 // Video segment.