YOLO v4 + ROS2 Humble (Foxy) + CUDA11 + cuDNN (FP16)

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,33 @@
+---
+name: 🐛 Bug report
+about: Create a report to help us improve
+title: ""
+labels: bug
+assignees: ''
+
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**To Reproduce**
+Steps to reproduce the behavior:
+1. Go to '...'
+2. Click on '....'
+3. Scroll down to '....'
+4. See error
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
+
+**System specs (please complete the following information):**
+ - OS
+ - ROS version
+ - Library versions when non-standard
+ - GPU / CUDA version when relevant
+
+**Additional context**
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/compilation-and-runtime-issue.md

@@ -0,0 +1,32 @@
+---
+name: ⁉️  Compilation and runtime issue
+about: Use this template if you're facing issues running or compiling darknet_ros.
+title: ""
+labels: question
+assignees: ''
+
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**To Reproduce**
+Steps to reproduce the behavior:
+1. Go to '...'
+2. Click on '....'
+3. Scroll down to '....'
+4. See error
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
+
+**System (please complete the following information):**
+ - OS: [e.g. Ubuntu 20.04]
+ - ROS version: [e.g., Noetic, Foxy]
+ - GPU when relevant: [e.g., Intel UHD, NVidia GTX 3090] 
+
+**Additional context**
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,20 @@
+---
+name: ✨ Feature request
+about: Suggest an idea for this project
+title: ""
+labels: enhancement
+assignees: mbjelonic
+
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+
+**Describe the solution you'd like**
+A clear and concise description of what you want to happen.
+
+**Describe alternatives you've considered**
+A clear and concise description of any alternative solutions or features you've considered.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.

.gitignore

@@ -0,0 +1,2 @@
+.vscode/
+build/

.gitmodules

@@ -1,3 +1,3 @@
 [submodule "darknet"]
-	path = darknet
-	url = https://github.com/pjreddie/darknet
+    path = darknet
+    url = https://github.com/AlexeyAB/darknet

README.md

@@ -2,9 +2,11 @@
 
 ## Overview
 
-This is a ROS package developed for object detection in camera images. You only look once (YOLO) is a state-of-the-art, real-time object detection system. In the following ROS package you are able to use YOLO (V3) on GPU and CPU. The pre-trained model of the convolutional neural network is able to detect pre-trained classes including the data set from VOC and COCO, or you can also create a network with your own detection objects. For more information about YOLO, Darknet, available training data and training YOLO see the following link: [YOLO: Real-Time Object Detection](http://pjreddie.com/darknet/yolo/).
+This is a ROS package developed for **object detection in camera images**. You only look once (YOLO) is a state-of-the-art, real-time object detection system. In the following ROS package you are able to use **YOLO (V3) on GPU and CPU**. The pre-trained model of the convolutional neural network is able to detect pre-trained classes including the data set from VOC and COCO, or you can also create a network with your own detection objects. For more information about YOLO, Darknet, available training data and training YOLO see the following link: [YOLO: Real-Time Object Detection](http://pjreddie.com/darknet/yolo/).
 
-The YOLO packages have been tested under ROS Foxy, Ubuntu 20.04 and OpenCV 4.2.0. This is research code, expect that it changes often and any fitness for a particular purpose is disclaimed.
+The YOLO packages have been tested under **ROS Noetic** and **Ubuntu 20.04**. Note: We also provide branches that work under **ROS Melodic**, **ROS Foxy** and **ROS2**.
+
+This is research code, expect that it changes often and any fitness for a particular purpose is disclaimed.
 
 **Author: [Marko Bjelonic](https://www.markobjelonic.com), marko.bjelonic@mavt.ethz.ch**
 
@@ -113,7 +115,7 @@ In order to use your own detection objects you need to provide your weights and
 
 ## Basic Usage
 
-In order to get YOLO ROS: Real-Time Object Detection for ROS to run with your robot, you will need to adapt a few parameters. It is the easiest if duplicate and adapt all the parameter files that you need to change from the `darkned_ros` package. These are specifically the parameter files in `config` and the launch file from the `launch` folder.
+In order to get YOLO ROS: Real-Time Object Detection for ROS to run with your robot, you will need to adapt a few parameters. It is the easiest if duplicate and adapt all the parameter files that you need to change from the `darknet_ros` package. These are specifically the parameter files in `config` and the launch file from the `launch` folder.
 
 ## Nodes
 
@@ -123,7 +125,7 @@ This is the main YOLO ROS: Real-Time Object Detection for ROS node. It uses the
 
 ### ROS related parameters
 
-You can change the names and other parameters of the publishers, subscribers and actions inside `darkned_ros/config/ros.yaml`.
+You can change the names and other parameters of the publishers, subscribers and actions inside `darknet_ros/config/ros.yaml`.
 
 #### Subscribed Topics
 
@@ -153,7 +155,7 @@ You can change the names and other parameters of the publishers, subscribers and
 
 ### Detection related parameters
 
-You can change the parameters that are related to the detection by adding a new config file that looks similar to `darkned_ros/config/yolo.yaml`.
+You can change the parameters that are related to the detection by adding a new config file that looks similar to `darknet_ros/config/yolo.yaml`.
 
 * **`image_view/enable_opencv`** (bool)
 
@@ -165,16 +167,16 @@ You can change the parameters that are related to the detection by adding a new
 
 * **`yolo_model/config_file/name`** (string)
 
-    Name of the cfg file of the network that is used for detection. The code searches for this name inside `darkned_ros/yolo_network_config/cfg/`.
+    Name of the cfg file of the network that is used for detection. The code searches for this name inside `darknet_ros/yolo_network_config/cfg/`.
 
 * **`yolo_model/weight_file/name`** (string)
 
-    Name of the weights file of the network that is used for detection. The code searches for this name inside `darkned_ros/yolo_network_config/weights/`.
+    Name of the weights file of the network that is used for detection. The code searches for this name inside `darknet_ros/yolo_network_config/weights/`.
 
 * **`yolo_model/threshold/value`** (float)
 
     Threshold of the detection algorithm. It is defined between 0 and 1.
 
 * **`yolo_model/detection_classes/names`** (array of strings)
 
-    Detection names of the network used by the cfg and weights file inside `darkned_ros/yolo_network_config/`.
+    Detection names of the network used by the cfg and weights file inside `darknet_ros/yolo_network_config/`.

darknet_ros/CHANGELOG.rst

@@ -2,6 +2,54 @@
 Changelog for package darknet_ros
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
+1.1.5 (2021-04-08)
+------------------
+* Merge pull request `#308 <https://github.com/leggedrobotics/darknet_ros/issues/308>`_ from leggedrobotics/noetic
+  Noetic
+* Minor fix in CMake.
+* Minor fix in test.
+* Updated readme.
+* Updated to newest darknet and fixed opencv on Ubuntu 20.04.
+* First changes in CMakeLists.
+* Merge pull request `#287 <https://github.com/leggedrobotics/darknet_ros/issues/287>`_ from leggedrobotics/feature/nodeletize
+  Feature/nodeletize
+* Small adjustments
+* Added pointer deletion in destructor and minor formatting
+* Minor formatting
+* Adding option to use nodelet
+* Add libxext
+* Add libxt-dev
+* Retrieve binaries from Github releases
+* Merge pull request `#232 <https://github.com/leggedrobotics/darknet_ros/issues/232>`_ from leggedrobotics/add-required-deps
+  Update package.xml dependencies
+* Don't require cmake-clang-tools
+* Update package.xml dependencies
+* Added clang tooling.
+* Merge pull request `#207 <https://github.com/leggedrobotics/darknet_ros/issues/207>`_ from umdlife/install_weights
+  Add install targets for configuration files
+* Add install targets for configuration files
+  Adds the `launch`, `config`, and `yolo_network_config` folders to the
+  install target for `darknet_ros` so they are available in the catkin
+  install directory.
+* Fixed linking of cuda libraries.
+* Merge branch 'kunaltyagi-cleanup'
+* Cleaned up CMakeLists.txt, used OpenCV C++ API for cpp file
+* Merge pull request `#189 <https://github.com/leggedrobotics/darknet_ros/issues/189>`_ from martinspedro/master
+  /darknet_ros/found_object uses custom msg with Header for improving synchronization
+* YOLO publishes Object Count with Time stamp using custom msg with Header
+* Merge pull request `#183 <https://github.com/leggedrobotics/darknet_ros/issues/183>`_ from kunaltyagi/id_num
+  Add numerical ID and launch param for image
+* Adding numerical ID and launch param for image
+* Merge pull request `#182 <https://github.com/leggedrobotics/darknet_ros/issues/182>`_ from leggedrobotics/fix/image_publisher
+  Fixed copy of image publisher.
+* Fixed copy of image publisher.
+* Merge branch 'kjbilton-master'
+* Increased scope of image acquisition mutex to prevent image overwriting
+* Merge branch 'utra-robosoccer-master'
+* Removed warnings caused by catkin builds
+* Added test_depend of wget to accomodate Jenkins.
+* Contributors: Jason Wang, Kunal Tyagi, Kyle Bilton, Marko Bjelonic, Pedro Martins, Tom Lankhorst, Tomas Gareau, timonh
+
 1.1.4 (2019-03-03)
 ------------------
 * Merge pull request `#141 <https://github.com/leggedrobotics/darknet_ros/issues/141>`_ from lorenwel/feature/launch_file_arg