Utilization of smart services for indoor environments has gained extensive interest in the past decade due to the resulting increases in energy savings, user comfort and degree of automation. Occupancy detection is a critical element in automation systems due to its potential use in controlling electrical systems and devices such as lighting, air-conditioning and ventilation. It also has a high potential for improving the performance of demand-driven applications which require fine-grained occupancy information to optimize the trade-off between energy consumption and user comfort. Occupancy detection has been researched using different estimation methods and communication technologies. However, it remains challenging to procure sensory data and to model the occupancy information accurately due to the limitations of hardware deployment and underlying cost. This paper reviews existing occupancy methods and applications, along with their underlying issues. It provides a comparative analysis of the strategies from the perspectives of cost, intrusiveness and accuracy. Additionally, a new taxonomy which classifies the occupancy sensing techniques as being conventional or as alternate sensing has been proposed.