Anomaly Detection in Surveillance Camera using Deep Learning Techniques

The purpose of safeguarding public safety,protecting vital infrastructure, and preventing security breaches, anomaly detection in surveillance camera systems is an essential responsibility. Deep learning techniques have made significant progress in recent years in terms of increasing the precision and effectiveness of anomaly identification. The DenseNet architecture is used in this paper to provide a unique technique for anomaly identification in surveillance camera data. Convolutional neural networks (CNNs) like DenseNet are renowned for their dense connection and capacity to recognize intricate elements in images. To improve the functionality of the system, we suggest utilizing its benefits in the context of anomaly detection. Our method's primary objective is to effectively find anomalies through the utilization of the spatial correlations that already exist between pixels in images.