A comprehensive survey on 2D multi-person pose estimation methods. (June 2021)

• Record Type: Journal Article
• Authors: Wang, Chen; Zhang, Feng; Ge, Shuzhi Sam
• Is Part Of: Engineering applications of artificial intelligence. Volume 102(2021)
• Publication Date: 2021-06
• Subjects: 00-01 -- 99-00; Deep learning -- Multi-person pose estimation -- Survey; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2021.104260
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Human pose estimation is a fundamental yet challenging computer vision task and studied by many researchers around the world in recent years. As a basic task in computer vision, multi-person pose estimation is the core component for many practical applications. This paper extensively reviews recent works on multi-person pose estimation. Specifically, we illustrate and analyze popular methods in detail and compare their pros and cons to fill in the gaps existing in other surveys. In addition, the commonly used datasets, evaluation metrics, and open-source systems are also introduced respectively. Finally, we summarize the development of multi-person pose estimation frameworks and discuss the research trends. Highlights: Illustrate and analyze popular multi-person pose estimation methods. Compare the pros and cons of popular methods. Introduce commonly used datasets, evaluation metrics, and open-source systems. Summarize development of multi-person pose estimation.