# Object-Detection-and-Tracking

**Repository Path**: tutu96177/Object-Detection-and-Tracking

## Basic Information

- **Project Name**: Object-Detection-and-Tracking
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 2
- **Created**: 2019-12-18
- **Last Updated**: 2020-12-29

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Object Detection and Tracking
***

<img src="https://github.com/yehengchen/ObjectDetection/blob/master/img/objectdetection.gif" width="50%" height="50%">

*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]](https://github.com/yehengchen/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](https://github.com/yehengchen/ObjectDetection/blob/master/OneStage/yolo): Real-Time Object Detection and Tracking

__How to train a YOLOv3 model on custom images - [[Link]](https://github.com/yehengchen/ObjectDetection/tree/master/OneStage/yolo/yolov3)__

***
<img src="https://github.com/yehengchen/ObjectDetection/blob/master/img/output_49.gif" width="60%" height="60%">

* #### YOLOv3 + Deep_SORT - Pedestrian&Car Counting - [[Link]](https://github.com/yehengchen/ObjectDetection/tree/master/OneStage/yolo/deep_sort_yolov3)

***
<img src="https://github.com/yehengchen/ObjectDetection/blob/master/OneStage/yolo/yolo_img/sort_1.gif" width="60%" height="60%">

* #### YOLOv3 + SORT - Pedestrian Counting - [[Link]](https://github.com/yehengchen/ObjectDetection/tree/master/OneStage/yolo/yolov3_sort)
***

### [Darknet_ROS](https://github.com/yehengchen/YOLOv3-ROS/tree/master/darknet_ros): Real-Time Object Detection and Rotation Grasp Detection With ROS 

<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 - [[Link]](https://github.com/yehengchen/YOLOv3_ROS)
***

<img src="https://github.com/yehengchen/YOLOv3-ROS/blob/master/yolov3_pytorch_ros/models/output.gif" width="60%" height="100%">

* #### YOLOv3 + ROS Melodic - Robot Grasp Detection - [[Link]](https://github.com/yehengchen/YOLOv3_ROS/tree/master/yolov3_pytorch_ros)
***

<img src="https://github.com/yehengchen/video_demo/blob/master/video_demo/chair_pin.gif" width="60%" height="100%">

* #### YOLOv3 + OpenCV + ROS Melodic - Rotation Object Detection - [[Link]](https://github.com/yehengchen/YOLOv3-ROS/tree/master/yolov3_grasp_detection_ros)

***
### [SSD](https://github.com/yehengchen/ObjectDetection/tree/master/OneStage/ssd): Single Shot MultiBox Detector
* #### How to train a SSD model on own images - [[Link]]()

***
## [TwoStage]
### [R-CNN](https://github.com/yehengchen/Object-Detection-and-Tracking/tree/master/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 - [[Link]](https://github.com/yehengchen/Object-Detection-and-Tracking/tree/master/TwoStage/R-CNN)__

<img src="https://github.com/yehengchen/mask_rcnn_ros/blob/master/scripts/mask_rcnn.gif" width="60%" height="60%">

* #### Mask R-CNN + ROS Kinetic - [[Link]](https://github.com/yehengchen/mask_rcnn_ros)

This project is ROS package of Mask R-CNN algorithm for object detection and segmentation.

***

### COCO & VOC Datasets
* #### COCO dataset and Pascal VOC dataset - [[Link]](https://github.com/yehengchen/ObjectDetection/blob/master/COCO%20and%20Pascal%20VOC.md)
* #### How to get it working on the COCO dataset __coco2voc__ - [[Link]](https://github.com/yehengchen/ObjectDetection/blob/master/OneStage/yolo/coco2voc.md)
* #### Convert Dataset2Yolo - COCO / VOC - [[Link]](https://github.com/yehengchen/ObjectDetection/tree/master/OneStage/yolo/convert2Yolo)

***
# Paper list from 2014 to now(2019)
<img src="https://github.com/yehengchen/ObjectDetection/blob/master/img/deep_learning_object_detection_history.PNG" width="60%" height="60%">

#### PapersWithCode: Browse > Computer Vision > Object Detection - [[Link]](https://paperswithcode.com/task/object-detection)

#### ObjectDetection Two-stage vs One-stage Detectors - [[Link]](https://github.com/yehengchen/ObjectDetection/blob/master/Two-stage%20vs%20One-stage%20Detectors.md)

#### ObjectDetection mAP & IoU - [[Link]](https://github.com/yehengchen/ObjectDetection/blob/master/mAP%26IoU.md)



***