CREATING ALERT MESSAGES BASED ON WILD ANIMAL ACTIVITY DETECTION

Abstract

In regions where wildlife encroachment poses risks to human safety and property, timely detection and alerting
systems are essential for mitigating potential dangers. This study proposes a novel approach for creating alert messages
based on wild animal activity detection using hybrid deep neural networks. The system integrates both convolutional
neural networks (CNNs) and recurrent neural networks (RNNs) to efficiently analyze surveillance camera footage and
detect instances of wildlife presence. The CNN component processes spatial features from images, while the RNN
component captures temporal dependencies in sequential frames, enhancing the model's ability to recognize animal
behaviour patterns. Upon detection of significant animal activity, the system generates alert messages, notifying
relevant authorities or individuals to take precautionary measures. Experimental results demonstrate the effectiveness
of the proposed hybrid deep neural network architecture in accurately identifying wildlife activity, thereby facilitating
timely response and risk mitigation strategies.