GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → pushkalkatara → darknet_ros

pushkalkatara / darknet_ros

Licence: MIT license
Robotics Operating System Package for Yolo v3 based on darknet with optimized tracking using Kalman Filter and Optical Flow.

Programming Languages

C++
36643 projects - #6 most used programming language
CMake
9771 projects

Labels

computer-visiondeep-learningrosyoloobject-detectiondarknetkalman-filterdarknet-rosalexeyab-darknet

Projects that are alternatives of or similar to darknet ros

Darknet ros
YOLO ROS: Real-Time Object Detection for ROS
Stars: ✭ 1,101 (+2058.82%)
Mutual labels:  ros, yolo, darknet
darknet-vis
Visualize YOLO feature map in prediction for easily checking your model performance
Stars: ✭ 68 (+33.33%)
Mutual labels:  yolo, darknet
OpenCV-Flask
🐛 🐛 Opencv视频流传输到网页浏览器并做目标检测 🐛 🐛
Stars: ✭ 35 (-31.37%)
Mutual labels:  yolo, darknet
pnn
pnn is Darknet compatible neural nets inference engine implemented in Rust.
Stars: ✭ 17 (-66.67%)
Mutual labels:  yolo, darknet
object-tracking
Multiple Object Tracking System in Keras + (Detection Network - YOLO)
Stars: ✭ 89 (+74.51%)
Mutual labels:  yolo, darknet
vehicle-rear
Vehicle-Rear: A New Dataset to Explore Feature Fusion For Vehicle Identification Using Convolutional Neural Networks
Stars: ✭ 99 (+94.12%)
Mutual labels:  yolo, darknet
DroNet
DroNet: Efficient convolutional neural network detector for Real-Time UAV applications
Stars: ✭ 54 (+5.88%)
Mutual labels:  yolo, darknet
Venom
All Terrain Autonomous Quadruped
Stars: ✭ 145 (+184.31%)
Mutual labels:  ros, kalman-filter
JSON2YOLO
Convert JSON annotations into YOLO format.
Stars: ✭ 222 (+335.29%)
Mutual labels:  yolo, darknet
Tracking-with-darkflow
Real-time people Multitracker using YOLO v2 and deep_sort with tensorflow
Stars: ✭ 522 (+923.53%)
Mutual labels:  yolo, darknet
ffcnn
ffcnn is a cnn neural network inference framework, written in 600 lines C language.
Stars: ✭ 50 (-1.96%)
Mutual labels:  yolo, darknet
DarkPlate
License plate parsing using Darknet and YOLO
Stars: ✭ 36 (-29.41%)
Mutual labels:  yolo, darknet
yolor
implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)
Stars: ✭ 1,867 (+3560.78%)
Mutual labels:  yolo, darknet
darknet
php ffi darknet
Stars: ✭ 21 (-58.82%)
Mutual labels:  yolo, darknet
darknet-nnpack
Darknet with NNPACK
Stars: ✭ 302 (+492.16%)
Mutual labels:  yolo, darknet
VG AlexeyAB darknet
A forked AlexeyAB Darknet repo with extra convenient functions.
Stars: ✭ 82 (+60.78%)
Mutual labels:  yolo, alexeyab-darknet
Ros Sensor Fusion Tutorial
An in-depth step-by-step tutorial for implementing sensor fusion with robot_localization! 🛰
Stars: ✭ 306 (+500%)
Mutual labels:  ros, kalman-filter
lightDenseYOLO
A real-time object detection app based on lightDenseYOLO Our lightDenseYOLO is the combination of two components: lightDenseNet as the CNN feature extractor and YOLO v2 as the detection module
Stars: ✭ 20 (-60.78%)
Mutual labels:  yolo, darknet
darknet.js
A NodeJS wrapper of pjreddie's darknet / yolo.
Stars: ✭ 61 (+19.61%)
Mutual labels:  yolo, darknet
VideoRecognition-realtime-autotrainer-alerts
State of the art object detection in real-time using YOLOV3 algorithm. Augmented with a process that allows easy training of the classifier as a plug & play solution . Provides alert if an item in an alert list is detected.
Stars: ✭ 36 (-29.41%)
Mutual labels:  yolo, darknet
View All Similar Projects ➔

YOLO ROS: Real-Time Object Detection for ROS

Updates

  • Influenced from Memory Leak Issue on leggedrobotics/darket_ros repository. While running the ROS Node on Jetson TX1, the node was being killed in some time due to overflow in memory. This repository solves the issue of memory leak implementing multithreading techniques.

  • Removed Boost as dependency.

  • Updated darknet version - AlexeyAB/darknet. Improves the neural network performance ~7% by fusing 2 layers into 1: Convolutional + Batch-norm

  • Implemented Object Detection and Tracking.

  • Updated darknet_msgs according to bbox_t structure.

  • Credits - Marko Bjelonic, AlexeyAB

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.

The YOLO packages have been tested under ROS Kinetic and Ubuntu 16.04. This is research code, expect that it changes often and any fitness for a particular purpose is disclaimed.

Based on the Pascal VOC 2012 dataset, YOLO can detect the 20 Pascal object classes:

  • person
  • bird, cat, cow, dog, horse, sheep
  • aeroplane, bicycle, boat, bus, car, motorbike, train
  • bottle, chair, dining table, potted plant, sofa, tv/monitor

Based on the COCO dataset, YOLO can detect the 80 COCO object classes:

  • person
  • bicycle, car, motorbike, aeroplane, bus, train, truck, boat
  • traffic light, fire hydrant, stop sign, parking meter, bench
  • cat, dog, horse, sheep, cow, elephant, bear, zebra, giraffe
  • backpack, umbrella, handbag, tie, suitcase, frisbee, skis, snowboard, sports ball, kite, baseball bat, baseball glove, skateboard, surfboard, tennis racket
  • bottle, wine glass, cup, fork, knife, spoon, bowl
  • banana, apple, sandwich, orange, broccoli, carrot, hot dog, pizza, donut, cake
  • chair, sofa, pottedplant, bed, diningtable, toilet, tvmonitor, laptop, mouse, remote, keyboard, cell phone, microwave, oven, toaster, sink, refrigerator, book, clock, vase, scissors, teddy bear, hair drier, toothbrush

Installation

Dependencies

This software is built on the Robotic Operating System ([ROS]), which needs to be installed first. Additionally, YOLO for ROS depends on following software:

  • OpenCV (computer vision library),

Building

In order to install darknet_ros, clone the latest version using SSH from this repository into your catkin workspace and compile the package using ROS.

cd catkin_workspace/src
git clone --recursive https://github.com/pushkalkatara/darknet_ros.git
cd ../

Darknet on the CPU is fast (approximately 1.5 seconds on an Intel Core i7-6700HQ CPU @ 2.60GHz × 8) but it's like 500 times faster on GPU! You'll have to have an Nvidia GPU and you'll have to install CUDA. The CMakeLists.txt file automatically detects if you have CUDA installed or not. CUDA is a parallel computing platform and application programming interface (API) model created by Nvidia. If you do not have CUDA on your System the build process will switch to the CPU version of YOLO. If you are compiling with CUDA, you might receive the following build error:

nvcc fatal : Unsupported gpu architecture 'compute_61'.

This means that you need to check the compute capability (version) of your GPU. You can find a list of supported GPUs in CUDA here: CUDA - WIKIPEDIA. Simply find the compute capability of your GPU and add it into darknet_ros/CMakeLists.txt. Simply add a similar line like

-O3 -gencode arch=compute_62,code=sm_62

Download weights

The yolo-voc.weights and tiny-yolo-voc.weights are downloaded automatically in the CMakeLists.txt file. If you need to download them again, go into the weights folder and download the two pre-trained weights from the COCO data set:

cd catkin_workspace/src/darknet_ros/darknet_ros/yolo_network_config/weights/
wget http://pjreddie.com/media/files/yolov2.weights
wget http://pjreddie.com/media/files/yolov2-tiny.weights

And weights from the VOC data set can be found here:

wget http://pjreddie.com/media/files/yolov2-voc.weights
wget http://pjreddie.com/media/files/yolov2-tiny-voc.weights

And the pre-trained weight from YOLO v3 can be found here:

wget http://pjreddie.com/media/files/yolov3-voc.weights
wget http://pjreddie.com/media/files/yolov3.weights

Use your own detection objects

In order to use your own detection objects you need to provide your weights and your cfg file inside the directories:

catkin_workspace/src/darknet_ros/darknet_ros/yolo_network_config/weights/
catkin_workspace/src/darknet_ros/darknet_ros/yolo_network_config/cfg/

In addition, you need to create your config file for ROS where you define the names of the detection objects. You need to include it inside:

catkin_workspace/src/darknet_ros/darknet_ros/config/

Then in the launch file you have to point to your new config file in the line:

<rosparam command="load" ns="darknet_ros" file="$(find darknet_ros)/config/your_config_file.yaml"/>

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.

Nodes

Node: darknet_ros

This is the main YOLO ROS: Real-Time Object Detection for ROS node. It uses the camera measurements to detect pre-learned objects in the frames.

ROS related parameters

You can change the names and other parameters of the publishers, subscribers and actions inside darkned_ros/config/ros.yaml.

Subscribed Topics

  • /camera_reading ([sensor_msgs/Image])

    The camera measurements.

Published Topics

  • object_detector ([std_msgs::Int8])

    Publishes the number of detected objects.

  • bounding_boxes ([darknet_ros_msgs::BoundingBoxes])

    Publishes an array of bounding boxes that gives information of the position and size of the bounding box in pixel coordinates.

  • detection_image ([sensor_msgs::Image])

    Publishes an image of the detection image including the bounding boxes.

Actions

  • camera_reading ([sensor_msgs::Image])

    Sends an action with an image and the result is an array of bounding boxes.

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.

  • 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/.

  • 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/.

  • 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/.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].