Edinburgh Napier University

  Real-time occupancy monitoring information is an important component in building energy management and security. Advances in technology enables us to develop vision-based systems. These systems have gained popularity among different scientific research communities due to their high accuracy. Based on real-time video from a single camera, people occupancy rates in buildings can be correctly estimated using neural network models. This paper proposes an intelligent real-time bidirectional system, using Random Neural Network (RNN) predictions. An overhead camera was used to capture RGB images and the number of people crossing a virtual line was counted using the proposed counting technique. The proposed algorithm extracts some important features such as occupant blob areas, major axis, minor axis, eccentricity, perimeters and area-perimeter ratio for total 1000 frames. Finally, a RNN model is trained with aforementioned features using a gradient decent algorithm. Real-time experimental results show the effectiveness of the proposed method, especially when occupants are in group and blob merge/split scenarios. Real-time testing revealed an accuracy between 100 and 93.38% for single and multiple occupants, respectively.