Intelligent Human Counting through Environmental Sensing in Closed Indoor Settings

Detecting count of human beings accurately in a closed indoor environment is crucial in diverse application areas including search and rescue, surveillance, customer analytics, abnormal event detection, human gait characterization, congestion analysis, and many more. Moreover, it has significant importance in preventing any intrusion in a secured indoor space such as a bank vault. Sensor-based technologies (for example camera, Passive Infrared sensor (PIR), etc.) are becoming more popular day by day to ensure enhanced security in such closed indoor setting. However, sensors used in these technologies have to be deployed in visible places. Thus, there exist possibilities of damaging the sensors by intruders. Therefore, this paper proposes a novel methodology to detect human count in such closed indoor setting, which can be deployed in any hidden place being oblivious to intruders. Here, we perform human counting based on different environmental gaseous parameters (Carbon Dioxide, Liquefied Petroleum Gas or LPG, Nitrogen Dioxide, and Sulfur Dioxide) and two weather parameters (temperature and humidity). We conduct numerous experiments under closed controlled settings and perform the counting task using different machine learning algorithms such as Bagging, RandomForest, IBK, and J48. We also propose a novel Deep Neural Network based framework for this task and evaluate its performance on the collected data sets. Using this method, we achieve 95% accuracy in detecting the number of humans present even in the unseen test case scenario.