A survey on still image based human action recognition

• Published in: Pattern recognition Vol. 47; no. 10; pp. 3343 - 3361
• Main Authors: Guo, Guodong, Lai, Alice
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01.10.2014; Elsevier
• Subjects: Action recognition; Applied sciences; Artificial intelligence; Character recognition; Computer science; control theory; systems; Evaluation; Exact sciences and technology; Feature recognition; Human; Image processing; Information, signal and communications theory; Internet; Object recognition; Pattern recognition; Pattern recognition. Digital image processing. Computational geometry; Signal and communications theory; Signal processing; Signal representation. Spectral analysis; Signal, noise; Still image based; Survey; Telecommunications and information theory; Temporal logic; Various cues; Action recognition; Various cues; Evaluation; Survey; Databases; Still image based; Computer vision; State of the art; Image recognition; Background; Image retrieval; Video signal; Information retrieval; Review; Pattern recognition; Clutter; Image analysis; Image sequence; Database; Fixed image; Signal processing; Internet; Motion analysis

Recently still image-based human action recognition has become an active research topic in computer vision and pattern recognition. It focuses on identifying a person׳s action or behavior from a single image. Unlike the traditional action recognition approaches where videos or image sequences are us...