Only released in EOL distros:
This package provides face detection.
- Maintainer status: developed
- Maintainer: Siddhartha Banerjee <banerjs.sid AT gmail DOT com>, Andrew Silva <andrew.silva AT gatech DOT edu>
- Author: Siddhartha Banerjee <banerjs.sid AT gmail DOT com>, Andrew Silva <andrew.silva AT gatech DOT edu>
- License: MIT
- Source: git https://github.com/GT-RAIL/rail_face_detection.git (branch: indigo-devel)
Two Minute Intro
This detector uses Caffe to perform face detection. It publishes faces found in images from a subscribed image topic. The face detector itself can be found here: https://github.com/kpzhang93/MTCNN_face_detection_alignment.
The message type coming back from the face detector is a Detections.msg which contains an array of Face.msg objects. Each Face.msg has:
top_left_x - X pixel value of top-left corner of bounding box
top_left_y - Y pixel value of top-left corner of bounding box
bot_right_x - X pixel value of bottom-right corner of bounding box
bot_right_y - Y pixel value of bottom-right corner of bounding box
nose_x - X coordinate of the nose
nose_y - Y coordinate of the nose
left_eye_x - X coordinate of the left eye
left_eye_y - Y coordinate of the left eye
right_eye_x - X coordinate of the right eye
right_eye_y - Y coordinate of the right eye
left_mouth_x - X coordinate of the left corner of the mouth
left_mouth_y - Y coordinate of the left corner of the mouth
right_mouth_x - X coordinate of the right corner of the mouth
right_mouth_y - Y coordinate of the right corner of the mouth
This package contains a single ROS node - face_detector_node - which serves as an interface between a ROS system and the trained face recognition network.
Topic with face detections performed in the background by running on images as they come in the subscriber.
Topic with face detections visualized on incoming images as they come in from the subscriber. Only published if debug=true.
Image topic name to use for detections.
Enable or disable debug mode, which publishes incoming images with bounding boxes over faces
Enable or disable gpu mode. Enabled by default. Significantly speeds up detection.
Change to compressed image stream or not. Simply appends a "/compressed" to the image topic name. This lightens the load your local network if the images are being transmitted to the detector.