Crowd Counting Challenge requires participating algorithms to count people in each frame.
The goal of this challenge is to estimate the number of people and their density map in each frame. We will provide a dataset for counting people. Each algorithm is evaluated through computing the number of people, mean absolute error (MAE) and mean squared error (MSE) between the predicted number of people and ground-truth in evaluation.
The crowd counting evaluation page lists detailed information regarding how submissions will be scored. We encourage the participants to use the provided training data, while they can also use additional training data. However, the use of external data must be specified during the submission process.