Awesome
<h1 align="center"> Object Detection and Tracking </h1> <div align="center"> <img src="https://github.com/yehengchen/ObjectDetection/blob/master/img/objectdetection.gif" width="60%" height="60%"> </div>Object detection is a computer technology related to computer vision and image processing that deals with detecting instances of semantic objects of a certain class (such as humans, buildings, or cars) in digital images and videos.
Environment
I have tested on Ubuntu 16.04/18.04. The code may work on other systems.
[Ubuntu-Deep-Learning-Environment-Setup]
-
Ubuntu 16.04 / 18.04
-
ROS Kinetic / Melodic
-
GTX 1080Ti / RTX 2080Ti
-
python 2.7 / 3.6
Installation
Clone the repository
git clone https://github.com/yehengchen/Object-Detection-and-Tracking.git
[OneStage]
YOLO-SORT: Real-Time Object Detection and Tracking
<img src="https://github.com/yehengchen/video_demo/blob/master/video_demo/output_49.gif" width="60%" height="60%">
-
YOLOv4 + Deep_SORT - Pedestrian Counting & Social Distance - [Here]
-
YOLOv3 + Deep_SORT - Pedestrian&Car Counting - [Here]
<img src="https://github.com/yehengchen/video_demo/blob/master/video_demo/sort_1.gif" width="60%" height="60%">
-
YOLOv3 + SORT - Pedestrian Counting - [Here]
Darknet_ROS: Real-Time Object Detection and Grasp Detection
<img src="https://github.com/yehengchen/YOLOv3-ROS/blob/master/darknet_ros/yolo_network_config/weights/output.gif" width="60%" height="60%">-
YOLOv3 + ROS Kinetic - For small Custom Data - [Here]
<img src="https://github.com/yehengchen/YOLOv3-ROS/blob/master/yolov3_pytorch_ros/models/output.gif" width="60%" height="100%">
<img src="https://github.com/yehengchen/video_demo/blob/master/video_demo/chair_pin.gif" width="60%" height="100%">
-
YOLOv3 + OpenCV + ROS Melodic - Object Detection (Rotated) - [Here]
DeepLabv3+_ROS: Mars Rover - Real-Time Object Tracking
<img src="https://github.com/HaosUtopia/Mars_Rover/blob/main/deeplabv3plus_ros/imgs/mars_rover_mastcam_rock_tracking.gif" width="60%" height="60%">-
DeepLab + OpenCV + ROS Melodic/Gazebo - Object Tracking - [Here]
-
Mars_Rover + ROS Melodic/Gazebo - [Here]
SSD: Single Shot MultiBox Detector
[TwoStage]
R-CNN: Region-based methods
Fast R-CNN / Faster R-CNN / Mask R-CNN
How to train a Mask R-CNN model on own images - [Here]
<img src="https://github.com/yehengchen/mask_rcnn_ros/blob/master/scripts/mask_rcnn.gif" width="60%" height="60%">-
Mask R-CNN + ROS Kinetic - [Here]
This project is ROS package of Mask R-CNN algorithm for object detection and segmentation.
COCO & VOC Datasets
-
COCO dataset and Pascal VOC dataset - [Here]
-
How to get it working on the COCO dataset coco2voc - [Here]
-
Convert Dataset2Yolo - COCO / VOC - [Here]