Merge pull request #221 from oarriaga/refactor_hand_estimation

Refactor hand estimation

Author: oarriaga

README.md

@@ -16,11 +16,11 @@ PAZ is used in the following examples (links to **real-time demos** and training
 |---------------------------|--------------------------| -----------------------|
 |<img src="https://raw.githubusercontent.com/oarriaga/altamira-data/master/images/emotion.gif" width="250">| <img src="https://raw.githubusercontent.com/oarriaga/altamira-data/master/images/keypoints.png" width="410">| <img src="https://raw.githubusercontent.com/oarriaga/altamira-data/master/images/mask.png" width="400">|
 
-|[Semantic segmentation](https://github.com/oarriaga/paz/tree/master/examples/semantic_segmentation) | [Hand pose estimation](https://github.com/oarriaga/paz/tree/master/examples/minimal_hand) |  [Human pose estimation](https://github.com/oarriaga/paz/tree/master/examples/human_pose_estimation_2D) |
+|[Semantic segmentation](https://github.com/oarriaga/paz/tree/master/examples/semantic_segmentation) | [Hand pose estimation](https://github.com/oarriaga/paz/tree/master/examples/hand_pose_estimation) |  [Human pose estimation](https://github.com/oarriaga/paz/tree/master/examples/human_pose_estimation_2D) |
 |---------------------------|-----------------------|-----------------|
 | <img src="https://raw.githubusercontent.com/oarriaga/altamira-data/master/images/semantic_segmentation.png" width="325">| <img src="https://raw.githubusercontent.com/oarriaga/altamira-data/master/images/minimal_hand_example.jpg" width="330"> |<img src="https://raw.githubusercontent.com/oarriaga/altamira-data/master/images/human_pose.gif" width="250"> | 
 
-| [3D keypoint discovery](https://github.com/oarriaga/paz/tree/master/examples/discovery_of_latent_keypoints)     | [Hand closure detection](https://github.com/oarriaga/paz/tree/master/examples/minimal_hand)  | [6D pose estimation](https://github.com/oarriaga/paz/tree/master/examples/pix2pose) |
+| [3D keypoint discovery](https://github.com/oarriaga/paz/tree/master/examples/discovery_of_latent_keypoints)     | [Hand closure detection](https://github.com/oarriaga/paz/tree/master/examples/hand_pose_estimation)  | [6D pose estimation](https://github.com/oarriaga/paz/tree/master/examples/pix2pose) |
 |---------------------------|-----------------------| --------------------------|
 |<img src="https://raw.githubusercontent.com/oarriaga/altamira-data/master/images/discovery_keypoints.png" width="335"> | <img src="https://raw.githubusercontent.com/oarriaga/altamira-data/master/images/hand_closure_detection.gif" width="250">| <img src="https://raw.githubusercontent.com/oarriaga/altamira-data/master/images/pix2pose_example.jpg" width="330"> |
 

docs/structure.py

@@ -504,7 +504,8 @@
         'page': 'processors/pose.md',
         'classes': [
             processors.SolvePNP,
-            processors.SolveChangingObjectPnPRANSAC
+            processors.SolveChangingObjectPnPRANSAC,
+            processors.Translation3DFromBoxWidth
         ]
     },
 
@@ -551,7 +552,8 @@
             processors.UnwrapDictionary,
             processors.Scale,
             processors.AppendValues,
-            processors.BooleanToTextMessage
+            processors.BooleanToTextMessage,
+            processors.PrintTopics
         ]
     },
 

examples/hand_detection/pose_demo.py

@@ -9,7 +9,7 @@
                     help='Camera device ID')
 args = parser.parse_args()
 
-pipeline = SSD512MinimalHandPose(right_hand=False, offsets=[0.25, 0.25])
+pipeline = SSD512MinimalHandPose(right_hand=False, offsets=[0.5, 0.5])
 camera = Camera(args.camera_id)
 player = VideoPlayer((640, 480), pipeline, camera)
 player.run()

examples/hand_pose_estimation/HandPoseEstimation.py

@@ -0,0 +1,25 @@
+### This example detects hand pose from an image.
+
+To test the live hand pose estimation from camera, run:
+```py
+python demo.py
+```
+
+To test the hand pose estimation on image, run:
+```py
+python demo_image.py
+```
+
+To test the live hand closure status with the pose estimation from camera, run:
+```py
+python is_open_demo.py
+```
+
+To test the live hand pose estimation from camera and visualize keypoints in 3D, run (This module has an extra dependency of matplotlib): 
+```py
+python demo3D.py
+```
+
+### Additional notes
+To test a more robust hand pose estimation and open / close classification try out the "paz/examples/hand_detection/pose_demo.py"
+