Provided are embodiments of a system and method for performing a last-minute hall call request to a departing cab using gestures. The embodiments include a sensing device that is in communication with a processor, wherein the sensing device is configured to monitor and detect a gesture from a potential passenger, and a processor configured to process video data received from the sensing device. The embodiments also include a video analyzer configured to predict a hall call request based at least in part on the gesture, and a controller is configured to control an operation of the system based at least in part on predicting the hall request.