Merge branch 'master' into dev

LICENSE

@@ -1,6 +1,6 @@
 BSD 3-Clause License
 
-Copyright (c) 2018, Douglas De Rizzo Meneghetti
+Copyright (c) 2019, Douglas De Rizzo Meneghetti
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without

README.md

@@ -6,7 +6,7 @@ This package makes information regarding detected objects available in a topic,
 
 When using an OpenNI-compatible sensor (like Kinect) the package uses point cloud information to locate objects in the world, wrt. to the sensor.
 
-Click the image below for a YouTube vudeo showcasing the package at work.
+Click the image below for a YouTube video showcasing the package at work.
 
 [![Youtube video](https://img.youtube.com/vi/fXJYmJOaSxQ/0.jpg)](https://www.youtube.com/watch?v=fXJYmJOaSxQ)
 
@@ -33,7 +33,7 @@ The package works in two steps. First, it detects objects by using a video feed
 
 Object detection is done via the [dodo detector](https://github.com/douglasrizzo/dodo_detector) package. In case the single-shot detector is to be used, point the `inference_graph` and `label_map` parameters to your corresponding files. These files are created when training an object detection neural network using [TensorFlow Object Detection API](https://github.com/tensorflow/models/tree/master/research/object_detection). Also, the `ssd_confidence` parameter can be changed to adjust the detection threshold of the network.
 
-In case the keypoint-based detector is to be used (either SIFT or RootSIFT), you need to create a database directory. The procedure to do so is described [here](http://douglasrizzo.github.io/dodo_detector#keypoint-based-detector).
+In case the keypoint-based detector is to be used (either SIFT or RootSIFT), you need to create a database directory. The procedure to do so is described [here](https://douglasrizzo.github.io/dodo_detector/#keypoint-based-detector).
 
 ## Usage
 

src/detector.py

@@ -151,9 +151,9 @@ def run(self):
                         rospy.logdebug('Found ' + str(len(objects[obj_class])) + ' object(s) of type ' + obj_class)
 
                         for obj_type_index, coordinates in enumerate(objects[obj_class]):
-                            rospy.logdebug('...' + obj_class + ' ' + str(obj_type_index) + ' at ' + str(coordinates))
+                            rospy.logdebug('...' + obj_class + ' ' + str(obj_type_index) + ' at ' + str(coordinates['box']))
 
-                            ymin, xmin, ymax, xmax = coordinates
+                            ymin, xmin, ymax, xmax = coordinates['box']
                             y_center = ymax - ((ymax - ymin) / 2)
                             x_center = xmax - ((xmax - xmin) / 2)