Object Detection With Deep Learning: A Review
Обнаружение объектов с помощью глубокого обучения: обзор
2019-01-28
SCID: 54.1/u9yerdg7
Discuss with AI
convolutional neural network (CNN)deep learning-based object detectiongeneric object detection architecturespedestrian and face detectionsalient object detection
Figures from the paper
Abstract (AI)
Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable architectures. Their performance easily stagnates by constructing complex ensembles that combine multiple low-level image features with high-level context from object detectors and scene classifiers. With the rapid development in deep learning, more powerful tools, which are able to learn semantic, high-level, deeper features, are introduced to address the problems existing in traditional architectures. These models behave differently in network architecture, training strategy, and optimization function. In this paper, we provide a review of deep learning-based object detection frameworks. Our review begins with a brief introduction on the history of deep learning and its representative tool, namely, the convolutional neural network. Then, we focus on typical generic object detection architectures along with some modifications and useful tricks to improve detection performance further. As distinct specific detection tasks exhibit different characteristics, we also briefly survey several specific tasks, including salient object detection, face detection, and pedestrian detection. Experimental analyses are also provided to compare various methods and draw some meaningful conclusions. Finally, several promising directions and tasks are provided to serve as guidelines for future work in both object detection and relevant neural network-based learning systems.
Key Findings
1
Deep learning, especially convolutional neural networks, has introduced powerful tools that learn semantic, high-level, deep features improving over traditional handcrafted-feature detectors.
2
Deep-learning-based object detection models differ in network architecture, training strategy, and optimization functions, which affect detection performance.
3
Experimental analyses compare various methods and draw conclusions, and the paper identifies promising directions and tasks for future research in object detection.
4
The paper surveys specific detection tasks—salient object detection, face detection, and pedestrian detection—highlighting task-specific characteristics.
5
The review summarizes typical generic object detection architectures plus modifications and practical tricks that further improve detection performance.
Research Object
Deep learning-based object detection frameworks
Research Subject
Architectures, training strategies, optimization functions, modifications and tricks, and performance comparisons for improving generic and specific object detection tasks
Publication Details
Publication Date
2019-01-28
Journal
Publisher
ISSN
Cited by
5535
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai12
Deep Residual Learning for Image Recognition2016
ImageNet classification with deep convolutional neural networks2017
Very Deep Convolutional Networks for Large-Scale Image Recognition2014
ImageNet: A large-scale hierarchical image database2009
Rethinking the Inception Architecture for Computer Vision2016
Distilling the Knowledge in a Neural Network2015
Reducing the Dimensionality of Data with Neural Networks2006
Aggregated Residual Transformations for Deep Neural Networks2017
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups2012
Bidirectional recurrent neural networks1997
Vision meets robotics: The KITTI dataset2013
Improving neural networks by preventing co-adaptation of feature detectors2012
Cited by11
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions2021
A Survey of Autonomous Driving: Common Practices and Emerging Technologies2020
Artificial intelligence in the creative industries: a review2021
State of the Art in Defect Detection Based on Machine Vision2021
Visual-Based Defect Detection and Classification Approaches for Industrial Applications—A SURVEY2020
A Comprehensive Review of Deep Learning: Architectures, Recent Advances, and Applications2024
Large Language Models: A Comprehensive Survey of its Applications, Challenges, Limitations, and Future Prospects2023
Deep Learning-Based UAV Detection in Pulse-Doppler Radar2021
Automated defect detection in digital radiography of aerospace welds using deep learning2022
Pair Programming Education Aided by ChatGPT2023
Review of optical pre-sensor computing2026