This paper presents an investigation of a neural-based technique for detecting and quantifying persons in beach imagery for the purpose of predicting trends of tourist activities at beach sites. The proposed system uses various pre-processing and segmentation techniques to initially isolate potential objects in cluttered scenes. A structural feature extraction technique is then used to represent objects of interest for training a neural classifier. An exhaustive search strategy, incorporating a neural network, is proposed to effectively scan beach images to determine whether objects are "person" or "non-person". Encouraging results are presented for person detection using video imagery collected from a beach site on the coast of Australia.