The invention provides a
subway station passenger flow statistics method based on face recognition, and belongs to the technical field of
rail transit operation management. According to the method, astation
control room processor analyzes images acquired by
image acquisition devices mounted at entrances and exits of a
station and entrances and exits of shielding
doors, extracts face images, and performs functional
processing such as face recognition, entrance and exit people counting, face tracking based on a hash
algorithm, automatic capture and automatic storage; and the
station control room terminal performs
station passenger flow statistics and draws a passenger
flow time distribution diagram. Real-time statistics of passenger flow in a station is achieved, and figure images are tracked to identify criminals; a passenger
flow time distribution diagram is drawn in real time, and reference data are provided for subway operation managers to complete
safety monitoring, reasonably arrange operation plans, drive dispatch,
route planning design and the like. The method is high in recognition rate, strong in real-time performance and good in practicability, and can be used for passenger flow statistics of other places.