A Survey of Modern Object Detection Literature using Deep Learning

TL;DR

This paper provides a comprehensive survey of modern deep learning-based object detection methods, comparing algorithms, metrics, and training techniques, with a focus on SSD and Faster R-CNN architectures and lightweight models for low-power devices.

Contribution

It offers a detailed review of current object detection algorithms, analyzing their strengths, weaknesses, and suitability for various applications, especially on resource-constrained devices.

Findings

SSD and Faster R-CNN are the predominant detection architectures.

Lightweight convolutional architectures improve detection speed on low-power devices.

The survey highlights trade-offs between detection accuracy and computational efficiency.

Abstract

Object detection is the identification of an object in the image along with its localisation and classification. It has wide spread applications and is a critical component for vision based software systems. This paper seeks to perform a rigorous survey of modern object detection algorithms that use deep learning. As part of the survey, the topics explored include various algorithms, quality metrics, speed/size trade offs and training methodologies. This paper focuses on the two types of object detection algorithms- the SSD class of single step detectors and the Faster R-CNN class of two step detectors. Techniques to construct detectors that are portable and fast on low powered devices are also addressed by exploring new lightweight convolutional base architectures. Ultimately, a rigorous review of the strengths and weaknesses of each detector leads us to the present state of the art.