Forgot password?

Vehicle Counting


Vehicle Counting Challenge requires participating algorithms to count vehicles in each frame.

The goal of counting here is to estimate the number of vehicles and their density map in an image. We will provide a dataset for counting vehicles. Each algorithm is evaluated through computing the number of vehicle, mean absolute error (MAE) and mean squared error (MSE) between the predicted number of vehicle 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.