From 1b878c9155d7ff9783929d55035c942dd8bb7933 Mon Sep 17 00:00:00 2001
From: aka <47563398+todateman@users.noreply.github.com>
Date: Tue, 15 Jul 2025 18:33:02 +0900
Subject: [PATCH] fix(record): Improve OpenCV backend handling for Windows
 systems (#1495)

* fix(record): Improve OpenCV backend handling for Windows systems

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Resolved ruff's E402 error (import statements not at the beginning of the file):
- Moved all import statements to the beginning of the file
- Defined _fix_opencv_backend() as a function
- Adjusted the timing of the fix call
- Code structure conforming to ruff

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix(record): Correct OpenCV backend for Windows systems

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix(opencv): Set OpenCV environment variable for Windows systems

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix(opencv): Refactor MSMF hardware transform environment variable setting for Windows

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
---
 src/lerobot/cameras/opencv/camera_opencv.py | 4 ++++
 src/lerobot/cameras/utils.py                | 6 ++++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/src/lerobot/cameras/opencv/camera_opencv.py b/src/lerobot/cameras/opencv/camera_opencv.py
index fd99922a..1d7a1645 100644
--- a/src/lerobot/cameras/opencv/camera_opencv.py
+++ b/src/lerobot/cameras/opencv/camera_opencv.py
@@ -18,12 +18,16 @@ Provides the OpenCVCamera class for capturing frames from cameras using OpenCV.
 
 import logging
 import math
+import os
 import platform
 import time
 from pathlib import Path
 from threading import Event, Lock, Thread
 from typing import Any, Dict, List
 
+# Fix MSMF hardware transform compatibility for Windows before importing cv2
+if platform.system() == "Windows" and "OPENCV_VIDEOIO_MSMF_ENABLE_HW_TRANSFORMS" not in os.environ:
+    os.environ["OPENCV_VIDEOIO_MSMF_ENABLE_HW_TRANSFORMS"] = "0"
 import cv2
 import numpy as np
 
diff --git a/src/lerobot/cameras/utils.py b/src/lerobot/cameras/utils.py
index f8bbd6e7..1eb69840 100644
--- a/src/lerobot/cameras/utils.py
+++ b/src/lerobot/cameras/utils.py
@@ -60,6 +60,8 @@ def get_cv2_backend() -> int:
     import cv2
 
     if platform.system() == "Windows":
-        return cv2.CAP_AVFOUNDATION
-    else:
+        return cv2.CAP_MSMF  # Use MSMF for Windows instead of AVFOUNDATION
+    # elif platform.system() == "Darwin":  # macOS
+    #     return cv2.CAP_AVFOUNDATION
+    else:  # Linux and others
         return cv2.CAP_ANY