IMPROVED OBJECT DETECTION IN VIDEO SURVEILLANCE USING DEEP CONVOLUTIONAL NEURAL NETWORK LEARNING

In this paper, a convolutional neural network is used to improve the functionality of object detection using probabilistic neural network in the analysis of surveillance images. Next, this research work attempts to examine the fundamental principles and some of the underlying theories of perceptual and neural networks are often missed. This helps you understand why, in many areas of usage, deep learning has increased. The processing of surveillance photos is obviously one of the areas most influenced by this exponential progress, particularly in the identification and detection of images. The simulation result shows that the CNN-PNN obtained improved achievements in simulation for the optimal detection of objects in video streaming or video surveillance systems. The results show that the proposed method achieves higher rate of accuracy, f-measure and reduced percentage error than other methods.