This resource contains a detection model which classifies if the input frame of an endoscopy video is inside the body or out of the body, as well as a sample surgical video.
Note: The provided model is in ONNX format. It will automatically be converted into a TensorRT model (.engine) the first time it is processed by a Holoscan application.
The sample data, provided by Activ Surgical, is an .mp4 video that consists of scenes from both in the body and out of the body during an endoscopic procedure.
Note: the .mp4 file must be converted into a GXF tensor file using the
convert_video_to_gxf_entities.py script on GitHub to be used with the
VideoStreamReplayer Holoscan operator.
Refer to the license agreement for use of the sample data.