From 4f6e0e3ff08acecfcf22520852e7eee903dc8732 Mon Sep 17 00:00:00 2001
From: Tobias Klockau <tobias.klockau@deutschebahn.com>
Date: Mon, 4 Nov 2024 08:46:17 +0100
Subject: [PATCH] feat: add JSONStreamCamera

---
 raillabel/json_format/stream_camera.py | 55 ++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)
 create mode 100644 raillabel/json_format/stream_camera.py

diff --git a/raillabel/json_format/stream_camera.py b/raillabel/json_format/stream_camera.py
new file mode 100644
index 0000000..c268acf
--- /dev/null
+++ b/raillabel/json_format/stream_camera.py
@@ -0,0 +1,55 @@
+# Copyright DB InfraGO AG and contributors
+# SPDX-License-Identifier: Apache-2.0
+
+from __future__ import annotations
+
+from typing import Literal
+
+from pydantic import BaseModel
+
+
+class JSONStreamCamera(BaseModel):
+    """A stream describes the source of a data sequence, usually a sensor.
+
+    This specific object contains the intrinsics of a camera sensor.
+    """
+
+    type: Literal["camera"]
+    "A string encoding the type of the stream."
+
+    stream_properties: JSONStreamCameraProperties
+    "Intrinsic calibration of the stream."
+
+    uri: str
+    "A string encoding the subdirectory containing the sensor files."
+
+    description: str | None
+    "Description of the stream."
+
+
+class JSONStreamCameraProperties(BaseModel):
+    """Intrinsic calibration of the stream."""
+
+    intrinsics_pinhole: JSONIntrinsicsPinhole
+
+
+class JSONIntrinsicsPinhole(BaseModel):
+    """JSON object defining an instance of the intrinsic parameters of a pinhole camera."""
+
+    camera_matrix: tuple[
+        float, float, float, float, float, float, float, float, float, float, float, float
+    ]
+    """This is a 3x4 camera matrix which projects 3D homogeneous points (4x1) from a camera
+    coordinate system into the image plane (3x1). This is the usual K matrix for camera projection as
+    in OpenCV. It is extended from 3x3 to 3x4 to enable its direct utilisation to project 4x1
+    homogeneous 3D points. The matrix is defined to follow the camera model: x-to-right, y-down,
+    z-forward. The following equation applies: x_img = camera_matrix * X_ccs."""
+
+    distortion_coeffs: tuple[float, float, float, float, float]
+    "This is the array 1x5 radial and tangential distortion coefficients."
+
+    height_px: int
+    "Height of the camera output in pixel."
+
+    width_px: int
+    "Width of the camera output in pixel."