In recent years, people-counting problems have increased in popularity, especially in crowded indoor spaces, e.g., public transport. In peak hours, trains move significant numbers of passengers, producing delays and inconveniences for their users. Therefore, analysing how people use public transport is essential to solving this problem. The current analysis estimates how many people are inside a train station by using the number of people entering and leaving the ticket gates or estimating the train occupancy based on conventional CCTV cameras. However, this information is insufficient for knowing the train occupancy. The required data includes vehicle usage: how many people enter or leave a vehicle or which door is the most used. This paper presents a solution to the stated problem based on a multi-object tracker with a sequential visual appearance predictor and a line-based counting strategy to analyse each passenger's trajectory using an overhead fisheye camera. The camera selection inside the train was made after profoundly studying the railway environment. The method proposes a module to compute the total train occupancy. The solution is robust against occlusions thanks to the selected tracker and the fisheye camera field of view. This work shows a proof of concept dataset containing pseudo-real case scenarios of people's affluence in train doors recorded by fisheye cameras. Its purpose is to prove the system's functionality in these scenarios. The proposed approach achieved an overall accuracy of counting people getting on and off of 90.78% in the pseudo-real dataset, proving that this approach is valid.