Hi Luxonis Team,
I would like to get frames with larger FOV apart from preview. For example, I am OK running object detection on the 1:1 preview frame which is cropped portion. However, I would like also to get the full FOV video frames to run more inference on the host side.
Here is the code:
xoutVideo = pipeline.create(dai.node.XLinkOut)
xoutVideo.setStreamName("video")
camRgb = pipeline.create(dai.node.ColorCamera)
camRgb.setResolution(dai.ColorCameraProperties.SensorResolution.THE_800_P)
camRgb.setIspScale(2,3)
camRgb.video.link(xoutVideo.input)
camRgb.setPreviewSize(300, 300)
camRgb.setInterleaved(False)
camRgb.setFps(10)
"video" frame is same FOV as preview. I also tried using "camRgb.setVideoSize(1280, 720)" which didn't help with FOV. Is there a way to get a full FOV frame separately while running object detection? Also same question goes for depth image too, the depth image FOV is also cropped.
Thank you
Best,
Jagadish