diff --git a/qrb_ros_vision_msgs/CMakeLists.txt b/qrb_ros_vision_msgs/CMakeLists.txt
new file mode 100644
index 0000000..83cf730
--- /dev/null
+++ b/qrb_ros_vision_msgs/CMakeLists.txt
@@ -0,0 +1,44 @@
+cmake_minimum_required(VERSION 3.8)
+project(qrb_ros_vision_msgs)
+
+# Default to C99
+if(NOT CMAKE_C_STANDARD)
+  set(CMAKE_C_STANDARD 99)
+endif()
+
+# Default to C++14
+if(NOT CMAKE_CXX_STANDARD)
+  set(CMAKE_CXX_STANDARD 14)
+endif()
+
+if(CMAKE_COMPILER_IS_GNUCXX OR CMAKE_CXX_COMPILER_ID MATCHES "Clang")
+  add_compile_options(-Wall -Wextra -Wpedantic)
+endif()
+
+# find dependencies
+find_package(ament_cmake REQUIRED)
+find_package(rosidl_default_generators REQUIRED)
+find_package(std_msgs REQUIRED)
+find_package(sensor_msgs REQUIRED)
+find_package(vision_msgs REQUIRED)
+
+rosidl_generate_interfaces(${PROJECT_NAME}
+  "msg/Detection2DWithMask.msg"
+  "msg/Detection2DWithMaskArray.msg"
+  DEPENDENCIES std_msgs vision_msgs sensor_msgs
+)
+
+if(BUILD_TESTING)
+  find_package(ament_lint_auto REQUIRED)
+  # the following line skips the linter which checks for copyrights
+  # comment the line when a copyright and license is added to all source files
+  set(ament_cmake_copyright_FOUND TRUE)
+  # the following line skips cpplint (only works in a git repo)
+  # comment the line when this package is in a git repo and when
+  # a copyright and license is added to all source files
+  set(ament_cmake_cpplint_FOUND TRUE)
+  ament_lint_auto_find_test_dependencies()
+endif()
+
+ament_package()
+
diff --git a/qrb_ros_vision_msgs/msg/Detection2DWithMask.msg b/qrb_ros_vision_msgs/msg/Detection2DWithMask.msg
new file mode 100644
index 0000000..e715637
--- /dev/null
+++ b/qrb_ros_vision_msgs/msg/Detection2DWithMask.msg
@@ -0,0 +1,6 @@
+std_msgs/Header header
+
+vision_msgs/Detection2D detection
+
+# Binary mask(mono8 image format) of detected instance
+sensor_msgs/Image instance_mask
diff --git a/qrb_ros_vision_msgs/msg/Detection2DWithMaskArray.msg b/qrb_ros_vision_msgs/msg/Detection2DWithMaskArray.msg
new file mode 100644
index 0000000..cfc799e
--- /dev/null
+++ b/qrb_ros_vision_msgs/msg/Detection2DWithMaskArray.msg
@@ -0,0 +1,3 @@
+std_msgs/Header header
+
+Detection2DWithMask[] array
\ No newline at end of file
diff --git a/qrb_ros_vision_msgs/package.xml b/qrb_ros_vision_msgs/package.xml
new file mode 100644
index 0000000..d4b2a62
--- /dev/null
+++ b/qrb_ros_vision_msgs/package.xml
@@ -0,0 +1,25 @@
+<?xml version="1.0"?>
+<?xml-model href="http://download.ros.org/schema/package_format3.xsd" schematypens="http://www.w3.org/2001/XMLSchema"?>
+<package format="3">
+  <name>qrb_ros_vision_msgs</name>
+  <version>1.0.0</version>
+  <description>Messages for computer vision pipelines.</description>
+  <maintainer email="quic_xiaolee@quicinc.com">Xiao Li</maintainer>
+  <license>BSD-3-Clause-Clear</license>
+
+  <buildtool_depend>ament_cmake</buildtool_depend>
+  <buildtool_depend>rosidl_default_generators</buildtool_depend>
+
+  <depend>std_msgs</depend>
+  <depend>sensor_msgs</depend>
+  <depend>vision_msgs</depend>
+  <exec_depend>rosidl_default_runtime</exec_depend>
+
+  <test_depend>ament_lint_auto</test_depend>
+  <test_depend>ament_lint_common</test_depend>
+
+  <member_of_group>rosidl_interface_packages</member_of_group>
+  <export>
+    <build_type>ament_cmake</build_type>
+  </export>
+</package>