diff --git a/google/cloud/vision/v1/image_annotator.proto b/google/cloud/vision/v1/image_annotator.proto
index acd7b268..f8d82084 100644
--- a/google/cloud/vision/v1/image_annotator.proto
+++ b/google/cloud/vision/v1/image_annotator.proto
@@ -103,6 +103,9 @@ message Feature {
 
     // Run web detection.
     WEB_DETECTION = 10;
+
+    // Run localizer for object detection.
+    OBJECT_LOCALIZATION = 19;
   }
 
   // The feature type.
@@ -410,6 +413,26 @@ message EntityAnnotation {
   repeated Property properties = 9;
 }
 
+// Set of detected objects with bounding boxes.
+message LocalizedObjectAnnotation {
+  // Object ID that should align with EntityAnnotation mid.
+  string mid = 1;
+
+  // The BCP-47 language code, such as "en-US" or "sr-Latn". For more
+  // information, see
+  // http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
+  string language_code = 2;
+
+  // Object name, expressed in its `language_code` language.
+  string name = 3;
+
+  // Score of the result. Range [0, 1].
+  float score = 4;
+
+  // Image region to which this object belongs. This must be populated.
+  BoundingPoly bounding_poly = 5;
+}
+
 // Set of features pertaining to the image, computed by computer vision
 // methods over safe-search verticals (for example, adult, spoof, medical,
 // violence).
@@ -569,6 +592,10 @@ message AnnotateImageResponse {
   // If present, label detection has completed successfully.
   repeated EntityAnnotation label_annotations = 4;
 
+  // If present, localized object detection has completed successfully.
+  // This will be sorted descending by confidence score.
+  repeated LocalizedObjectAnnotation localized_object_annotations = 22;
+
   // If present, text (OCR) detection has completed successfully.
   repeated EntityAnnotation text_annotations = 5;