UCSD is a crowd counting and density estimation dataset collected at the University of California, San Diego, commonly used as a benchmark for evaluating crowd analysis algorithms. It consists of surveillance video footage of a pedestrian walkway with relatively sparse crowd densities, providing ground truth annotations for individual pedestrian locations and counts. The dataset has been a foundational benchmark in the crowd counting field, enabling standardized comparison of CNN-based and other data-driven methods, though its limited density range and controlled environment have motivated the development of more challenging datasets to complement it.

Source Papers

  • A survey of recent advances in CNN-based single image crowd counting and density estimation — A survey of recent advances in CNN-based single image crowd
  • Data-driven Crowd Modeling Techniques: A Survey — Data-driven Crowd Modeling Techniques: A Survey