A Comprehensive Review of Modern Object Segmentation Approaches

TL;DR

This paper provides a comprehensive review of traditional and modern object segmentation methods, emphasizing deep learning techniques, datasets, evaluation metrics, and future research directions in 2D, 3D, and video segmentation.

Contribution

It offers an extensive comparison of segmentation approaches, highlighting recent advances, challenges, and potential future directions in the field.

Findings

Deep learning methods have significantly advanced segmentation accuracy.

Various datasets and metrics are crucial for evaluating segmentation performance.

Future research should focus on real-time and multi-modal segmentation challenges.

Abstract

Image segmentation is the task of associating pixels in an image with their respective object class labels. It has a wide range of applications in many industries including healthcare, transportation, robotics, fashion, home improvement, and tourism. Many deep learning-based approaches have been developed for image-level object recognition and pixel-level scene understanding-with the latter requiring a much denser annotation of scenes with a large set of objects. Extensions of image segmentation tasks include 3D and video segmentation, where units of voxels, point clouds, and video frames are classified into different objects. We use "Object Segmentation" to refer to the union of these segmentation tasks. In this monograph, we investigate both traditional and modern object segmentation approaches, comparing their strengths, weaknesses, and utilities. We examine in detail the wide range of deep learning-based segmentation techniques developed in recent years, provide a review of the widely used datasets and evaluation metrics, and discuss potential future research directions.