You are on page 1of 8

OBJECT DETECTION

WITH MASK R-CNN

By
19IT065 Kishan & 19IT066 Ayush
Agenda
Products or Services

Object Detection Mask R-CNN Demonstration screenshots


What is Object-Detection? What is Mask R-CNN? Screenshots of projects
Different types of algorithm for OD. Why Mask R-CNN?
Approch for object detection
Object Detection
What is Object Detection?
Object detection is a computer vision technique for locating instances of objects in images or videos.
we can detect and track objects in an image or live camera feed.

Algorithms for Object Detection


RCNN (2014)
Fast RCNN (2015)
Faster RCNN (2016)
YOLO - You Look Only Once (2016)
SSD - Single Shot Detection (2016)
Mask RCNN (2017)
Object Detection
Our approch for Object Detection
Our approch efficiently detects objects in an image while simultaneously generating a high-quality
segmentation mask for each instance.

Mask RCNN extends Faster RCNN by adding branch for predicting an object mask in parallel with existing
branch for bounding box recognition.
Mask R-CNN
What is Mask R-CNN?
Mask R-CNN is basically an extension of Faster
R-CNN.

Faster R-CNN is widely used for object detection


tasks.

For a given image, it returns the class label and


bounding box coordinates for each object in the
image.
Mask R-CNN
Why Mask R-CNN?
The Region-based CNN (R-CNN) approach to bounding-box object detection is to attend to a manageable number
of candidate object regions and evaluate convolutional networks independently on each RoI.

The model can return both the bounding box and a mask for each detected object in an image.

Results demonstrated that the overall detection accuracy of Mask R-CNN is >80%

whereas detection accuracy of ResNet-50 is >75%. The counting accuracies of Faster R-CNN, Mask R-CNN and
ResNet-50 are >75%,>70% and >62% respectively.
Tools & Technology
Tools
Google Colab

Language
Python

Algorithm
Mask R-CNN
Future work
We'll train our model for real-time object detection.

We'll enhance our model and gain higher accuracy in


complexity also.
Deploy our model and create a object detection web app.

You might also like