A review of object detection based on deep learning

• Published in: Multimedia tools and applications Vol. 79; no. 33-34; pp. 23729 - 23791
• Main Authors: Xiao, Youzi, Tian, Zhiqiang, Yu, Jiachen, Zhang, Yinshu, Liu, Shuai, Du, Shaoyi, Lan, Xuguang
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.09.2020; Springer Nature B.V
• Subjects: Algorithms; Artificial neural networks; Computer Communication Networks; Computer networks; Computer Science; Data Structures and Information Theory; Deep learning; Machine learning; Meteorological satellites; Multimedia Information Systems; Neural networks; Object recognition; Special Purpose and Application-Based Systems; Deep learning; Deep convolutional neural networks; Computer vision; Object detection
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-020-08976-6

With the rapid development of deep learning techniques, deep convolutional neural networks (DCNNs) have become more important for object detection. Compared with traditional handcrafted feature-based methods, the deep learning-based object detection methods can learn both low-level and high-level image features. The image features learned through deep learning techniques are more representative than the handcrafted features. Therefore, this review paper focuses on the object detection algorithms based on deep convolutional neural networks, while the traditional object detection algorithms will be simply introduced as well. Through the review and analysis of deep learning-based object detection techniques in recent years, this work includes the following parts: backbone networks, loss functions and training strategies, classical object detection architectures, complex problems, datasets and evaluation metrics, applications and future development directions. We hope this review paper will be helpful for researchers in the field of object detection.