Photo from wikipedia
Crowd counting is an attracting computer vision problem. Solutions to crowd counting hold high adaptability to other counting problems such as traffic counting and cell counting. Numerous methods have been… Click to show full abstract
Crowd counting is an attracting computer vision problem. Solutions to crowd counting hold high adaptability to other counting problems such as traffic counting and cell counting. Numerous methods have been proposed for the problem. Deep learning-based methods play a significant role in recent advancement. However, no existing literature reviews capture their sophisticated development by challenges. In this paper, we discuss and categorize recent deep learning works in crowd counting by considering how they address the challenges.
Journal Title: International Journal of Multimedia Information Retrieval
Year Published: 2019
Link to full text (if available)
Share on Social Media: Sign Up to like & get
recommendations!