High level info of Image segmentation
The most common use case of image segmantation is in the driverless cars. The basic operation that needs to be performed part of the driverless cars is to detect the objects but this doesn't fit well in the real world scenarios. Example lets says there is a turn in the road ahead and our system draws a rectangular box around the road. The car might not be able to understand whether to turn or go straight.
we need a technique that can detect the exact shape of the road so our self-driving car system can safely navigate the turns as well.
how does image segmentation work?
We can divide or partition the image into various parts called segments. By dividing the image into segments, we can make use of the important segments for processing the image.
An image is a collection or set of different pixels. We group together the pixels that have similar attributes using image segmentation.
Image segmentation creates a pixel-wise mask for each object in the image. This technique gives us a far more granular understanding of the object(s) in the image.
Types of image segmentation techniques
1/ Semantic segmentation
2/ Instance segmentation
3/ Region-based Segmentation
4/ Edge Detection Segmentation
5/ Image Segmentation based on Clustering
There are few state of art models for image segmentation namely the mask R-CNN and extension of faster R-CNN object detection model.
The Faster R-CNN method generates two things for each object in the image: Its class and The bounding box coordinates Mask R-CNN adds a third branch to this which outputs the object mask as well.