Recent Trends in 2D Object Detection and Applications in Video Event Recognition

TL;DR

This paper reviews recent advances in 2D object detection, emphasizing deep learning methods and their applications in video event recognition, along with datasets and performance comparisons.

Contribution

It provides a comprehensive overview of geometry-based and deep learning approaches, highlighting their integration in video event recognition and summarizing recent datasets and benchmarks.

Findings

Deep learning methods outperform traditional geometry-based techniques.

Unified architectures predict class and bounding boxes in a single pipeline.

Two-stage architectures improve detection accuracy in complex scenes.

Abstract

Object detection serves as a significant step in improving performance of complex downstream computer vision tasks. It has been extensively studied for many years now and current state-of-the-art 2D object detection techniques proffer superlative results even in complex images. In this chapter, we discuss the geometry-based pioneering works in object detection, followed by the recent breakthroughs that employ deep learning. Some of these use a monolithic architecture that takes a RGB image as input and passes it to a feed-forward ConvNet or vision Transformer. These methods, thereby predict class-probability and bounding-box coordinates, all in a single unified pipeline. Two-stage architectures on the other hand, first generate region proposals and then feed it to a CNN to extract features and predict object category and bounding-box. We also elaborate upon the applications of object detection in video event recognition, to achieve better fine-grained video classification performance. Further, we highlight recent datasets for 2D object detection both in images and videos, and present a comparative performance summary of various state-of-the-art object detection techniques.