Object-detection-with-Yolo-models

The goal was to recognize objects from a number of visual object classes in realistic scenes. It is fundamentally a supervised learning learning problem in that a training set of labelled images is provided. The twenty object classes that have been selected are:

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

Dataset used: PASCAL VOC 2012

Object detection

It is the task of correctly recognizing and efficiently locating multiple objects in an image automatically, by a supervised machine, given a sufficiently large training set, while avoiding false predictions and multiple bounding boxes of the same object.

Categories of Object detectors

● Single stage Object detectors

● Two stage object detectors

Two stage object detectors

The architecture for most of the object detectors of this type has the following stages:

● First stage is responsible for generating region of interest using Region Proposal Network (RPN),

● In the second stage, the network is responsible for optimizing the classification and bounding boxes for the proposed region. Some of the two stage object detection algorithms are

● R-CNN

● Fast R-CNN

● Faster R-CNN

● Feature Pyramid Network

One stage object detectors

Single stage object detectors have a single deep network to predict the bounding boxes as well as object confidence score. In one stage object detectors the image is passed through a single network for classification and localization. And has the intuition that localization is a regression problem. Some of the one stage object detection algorithms:

● YOLO

● YOLO (v2)

● YOLO(v3)

● YOLO(v4)

Predictions on Images

Yolo version-1 predictions after 40k epochs

Yolo version-2 predictions after 40k epochs

Yolo version-3 predictions after 40k epochs

Yolo version-4 predictions after 40k epochs

Loss function of Yolo versions on PASCAL VOC 2012 dataset

mean Average Precision(mAP) of Yolo versions on PASCAL VOC 2012 dataset

Predictions on Videos

Yolo version-1 predictions on a video

Yolo version-2 predictions on a video

Yolo version-3 predictions on a video

Yolo version-4 predictions on a video

Yolo weights

Yolo-1 weights file

Yolo-2 weights file

Yolo-3 weights file

Yolo-4 weights file

References

[1] Yolo-1 paper

[2] Yolo-2 paper

[3] Yolo-3 paper

[4] Yolo-4 paper

[5] https://pjreddie.com/darknet/yolo/

[6] https://github.com/AlexeyAB/darknet