[Documentation] [TitleIndex] [WordIndex

Package Summary

DNN based detection

  • Maintainer status: developed
  • Maintainer: Jim Vaughan <jimv AT mrjim DOT com>, Rohan Agrawal <send2arohan AT gmail DOT com>
  • Author: Jim Vaughan <jimv AT mrjim DOT com>
  • License: BSD
  • Source: git https://github.com/UbiquityRobotics/dnn_detect.git (branch: kinetic-devel)



dnn_detect uses the OpenCV Deep Neural Network module to find objects in an image stream and provide their bounding boxes.

Subscribed Topics

/camera (sensor_msgs/Image)

Published Topics

/dnn_objects (dnn_detect/DetectedObjectArray) /dnn_images (sensor_msgs/Image)


~detect (dnn_detect/Detect)


~single_shot (bool, default: false) ~publish_images (bool, default: true) ~data_dir (string) ~protonet_file (string) ~caffe_model_file (string) ~min_confidence (float, default: 0.2) ~im_size (int, default: 300) ~scale_factor (float, default: 0.007843) ~mean_val (float, default: 127.5) ~class_names (string, default: background, aeroplane, bicycle, bird, boat, bottle, bus, car, cat, chair, cow, diningtable, dog, horse, motorbike, person, pottedplant, sheep, sofa, train, tvmonitor)


sudo apt install ros-kinetic-dnn-detect

Sample Usage

The sample launch file uses chuanqi305's MobileNet-SSD

A camera node, such as usb_cam needs to be running

For example:

rosrun usb_cam usb_cam_node

Then dnn_detect can be launched:

roslaunch dnn_detect dnn_detect.launch camera:=/usb_cam image:=image_raw

and the results viewed with: {{ rqt_image_view /dnn_images or:

rostopic echo /dnn_objects

2020-04-04 12:38