-
Notifications
You must be signed in to change notification settings - Fork 1
Pickup an object
thib edited this page Aug 12, 2019
·
1 revision
This package is based on the object-recognition
package (see the References part). It allows to detect custom objects from a pre-trained network, using the bag-of-words methods, detect its pose on a table, thanks to OpenCV, and then grasp it.
Open a terminal, and execute the following command: roslaunch object_recognition demo.launch
According to the project Git repo (see References for further information):
- Browse to
src/object-recognition/src/bag_of_words
- Capture images from the Baxter's arm camera, thanks to the
baxter_capture_images.py
script (check the output folder location!) - Then use the
sift_train_classifier.py
script to train the classifier (check the output.pkl
file location!) - Check which weights file is used for the object recognition, in the
baxter_object_prediction.py
file (line 185)
-
object-recognition
project from apollack11 : https://github.com/apollack11/object-recognition