OpenPose run command ([email protected])

模型说明（BODY_25、COCO 和 MPI 模型）

BODY_25模型(——model_pose BODY_25)Include key points for the body and feet,它基于OpenPose,Real-time multi-person 2D pose estimation using partial affinity fields.
COCO 和 MPI 模型速度较慢,精度较低,And does not include foot key points.They are based on real-time multi-person 2D pose estimation using partial affinity fields in our previous paper.We strongly recommend using onlyBODY_25模型.

CPU pattern for standard recognition

Running on Video

# Ubuntu and Mac
./build/examples/openpose/openpose.bin --video examples/media/video.avi
# With face and hands
./build/examples/openpose/openpose.bin --video examples/media/video.avi --face --hand

:: Windows - Portable Demo
bin\OpenPoseDemo.exe --video examples\media\video.avi
:: With face and hands
bin\OpenPoseDemo.exe --video examples\media\video.avi --face --hand

Running on Webcam

# Ubuntu and Mac
./build/examples/openpose/openpose.bin
# With face and hands
./build/examples/openpose/openpose.bin --face --hand

:: Windows - Portable Demo
bin\OpenPoseDemo.exe
:: With face and hands
bin\OpenPoseDemo.exe --face --hand

Running on Images

# Ubuntu and Mac
./build/examples/openpose/openpose.bin --image_dir examples/media/
# With face and hands
./build/examples/openpose/openpose.bin --image_dir examples/media/ --face --hand

:: Windows - Portable Demo
bin\OpenPoseDemo.exe --image_dir examples\media\
:: With face and hands
bin\OpenPoseDemo.exe --image_dir examples\media\ --face --hand

GPU high-precision identification

• The following commands provide the most accurate results,Achievable body,Hand and face keypoint detection.
• 无法在 CPU 模式下工作,Because it requires a lot of memory,对于 CPU 版本,The only option is to manually crop the characters,以适应 OpenPose The entire area of ​​the provided image
• 对于 body-foot (BODY_25) 模型,它还需要 10.5 GB 的GPU内存(对于COCO模型,约6.7 GB).
• 需要像Titan X, Titan XP,一些 Quadro 模型,P100, V100 等 GPU.
• Including hands and face will be required >= 16GB 的 GPU (所以像 Titan X 和 XPs 这样的 12GB GPU 将不再工作).
• 这些命令在 Titan X The running speed is 2帧/秒(对于身体-foot model for1帧/秒).
• 递增 --net_resolution Will greatly reduce frame rate and increase latency,But may improve accuracy.但是,Not all scenarios warrant this increase in accuracy,A more detailed analysis of each specific scenario is required.例如,It works better for photos of very short people,But it doesn't work well for a large percentage of people.因此,在大多数情况下,Both tall and short people,We all recommend following the commands below for maximum accuracy.
• Do not use this configuration for MPII 模型,This multi-scale setting may compromise its accuracy.此配置仅对 COCO 和 COCO扩展(例如,默认的BODY_25)模型是最佳的.

Method Overview

# Ubuntu and Mac: Body
./build/examples/openpose/openpose.bin --net_resolution "1312x736" --scale_number 4 --scale_gap 0.25
# Ubuntu and Mac: Body + Hand + Face
./build/examples/openpose/openpose.bin --net_resolution "1312x736" --scale_number 4 --scale_gap 0.25 --hand --hand_scale_number 6 --hand_scale_range 0.4 --face

:: Windows - Portable Demo: Body
bin\OpenPoseDemo.exe --net_resolution "1312x736" --scale_number 4 --scale_gap 0.25
:: Windows - Portable Demo: Body + Hand + Face
bin\OpenPoseDemo.exe --net_resolution "1312x736" --scale_number 4 --scale_gap 0.25 --hand --hand_scale_number 6 --hand_scale_range 0.4 --face

3-D Reconstruction

1 Real-time demo

# Ubuntu and Mac
./build/examples/openpose/openpose.bin --flir_camera --3d --number_people_max 1
# With face and hands
./build/examples/openpose/openpose.bin --flir_camera --3d --number_people_max 1 --face --hand

:: Windows - Portable Demo
bin\OpenPoseDemo.exe --flir_camera --3d --number_people_max 1
:: With face and hands
bin\OpenPoseDemo.exe --flir_camera --3d --number_people_max 1 --face --hand

2 Saving 3-D keypoints and video

# Ubuntu and Mac (same flags for Windows version)
./build/examples/openpose/openpose.bin --flir_camera --3d --number_people_max 1 --write_json output_folder_path/ --write_video_3d output_folder_path/video_3d.avi

3 Fast stereo camera image saving (without keypoint detection) for later post-processing

# Ubuntu and Mac (same flags for Windows version)
# Saving video
# Note: saving in PNG rather than JPG will improve image quality, but slow down FPS (depending on hard disk writing speed and camera number)
./build/examples/openpose/openpose.bin --flir_camera --num_gpu 0 --write_video output_folder_path/video.avi --write_video_fps 5
# Saving images
# Note: saving in PNG rather than JPG will improve image quality, but slow down FPS (depending on hard disk writing speed and camera number)
./build/examples/openpose/openpose.bin --flir_camera --num_gpu 0 --write_images output_folder_path/ --write_images_format jpg

4 Reading and processing previouly saved stereo camera images

# Ubuntu and Mac (same flags for Windows version)
# Optionally add `--face` and/or `--hand` to include face and/or hands
# Assuming 3 cameras
# Note: We highly recommend to reduce `--output_resolution`. E.g., for 3 cameras recording at 1920x1080, the resulting image is (3x1920)x1080, so we recommend e.g. 640x360 (x3 reduction).
# Video
./build/examples/openpose/openpose.bin --video output_folder_path/video.avi --3d_views 3 --3d --number_people_max 1 --output_resolution {
    desired_output_resolution}
# Images
./build/examples/openpose/openpose.bin --image_dir output_folder_path/ --3d_views 3 --3d --number_people_max 1 --output_resolution {
    desired_output_resolution}

5 Reconstruction when the keypoint is visible in at least x camera views out of the total n cameras

# Ubuntu and Mac (same flags for Windows version)
# Reconstruction when a keypoint is visible in at least 2 camera views (assuming `n` >= 2)
./build/examples/openpose/openpose.bin --flir_camera --3d --number_people_max 1 --3d_min_views 2 --output_resolution {
    desired_output_resolution}
# Reconstruction when a keypoint is visible in at least max(2, min(4, n-1)) camera views
./build/examples/openpose/openpose.bin --flir_camera --3d --number_people_max 1 --output_resolution {
    desired_output_resolution}

Tracking

1 Runtime huge speed up by reducing the accuracy

# Using OpenPose 1 frame, tracking the following e.g., 5 frames
./build/examples/openpose/openpose.bin --tracking 5 --number_people_max 1

2 Runtime speed up while keeping most of the accuracy

:: Using OpenPose 1 frame and tracking another frame
./build/examples/openpose/openpose.bin --tracking 1 --number_people_max 1

3 Visual smoothness

# Running both OpenPose and tracking on each frame. Note: There is no speed up/slow down
./build/examples/openpose/openpose.bin --tracking 0 --number_people_max 1