Background subtraction is a crucial stage in many visual surveillance systems. The prime objective of any such system is to detect local changes, and the system could be utilized to face many real-life challenges. Most of the existing methods have addressed the problems of moderate and fast-moving object detection. However, very few literature have addressed the issues of slow moving object detection and these methods need further improvement to enhance the efficacy of detection. Hence, within this article, our significant endeavor involved identifying moving objects in challenging videos through an encoder-decoder architectural design, incorporating an enhanced VGG-19 model alongside a feature pooling framework. The proposed algorithm has various folds of novelties: a pre-trained VGG-19 architecture is modified and is used as an encoder with a transfer learning mechanism. The proposed model learns the weights of the improved VGG-19 model by a transfer-learning mechanism which enhances the model’s efficacy. The proposed encoder is designed using a smaller number of layers to extract crucial fine and coarse scale features necessary for detecting the moving objects. The feature pooling framework (FPF) employed is a hybridization of a max-pooling layer, a convolutional layer, and multiple convolutional layers with distinct sampling rates to retain the multi-scale and multi-dimensional features at different scales. The decoder network consists of stacked convolution layers projecting from feature to image space effectively. The developed technique’s efficacy is demonstrated against thirty-six state-of-the-art (SOTA) methods. The outcomes acquired by the developed technique are corroborated using subjective as well as objective analysis, which shows superior performance against other SOTA techniques. Additionally, the proposed model demonstrates enhanced accuracy when applied to unseen configurations. Further, the proposed technique (MOD-CVS) attained adequate efficiency for slow, moderate, and fast-moving objects simultaneously.

Background subtraction is an essential step in many computer vision tasks. In this article, we put forth a unique attempt to detect the local changes in challenging video scenes by exploring the capabilities of an encoder-decoder type network that employs a modified ResNet-152 architecture with a multi-scale features extraction framework. The proposed encoder network consists of a modified ResNet-152 network where the initial two blocks are freeze and the weights of the last blocks are learned using a transfer learning mechanism. The said encoder can reduce the computational complexity of the proposed model and extract fine as well as coarse-scale features. We have proposed a multiscale features extraction (MFE) mechanism block which is a hybridization of pyramidal pooling architecture (PPA), and various atrous convolutional layers where the high-level features from the encoder network are utilized to extract features at various scales. The use of PPA in the MFE block preserves maximum value in every pooling area, to retain the contextual relationship between the pixels in the complex video frames that can handle various challenging scenes. The proposed decoder network consists of stacked transposed convolution layers that learn a mapping from feature space to image space, predicting a score map. Then, a threshold is applied on the score map to get the binary class labels as the background and foreground. The shortcut connections followed by global average pooling (GAP) drive the low-level feature coefficients from the encoder network to the decoder network to enhance the feature representation. The performance of the proposed scheme is validated by testing it against thirty-one state-of-the-art techniques. The results obtained by the proposed method are corroborated qualitatively as well as quantitatively. Further, the efficacy of the proposed algorithm is verified with an unseen video setup and is found to provide better performance.

Quantum key distribution (QKD) is a viable technique for safeguarding image transmission against numerous attacks. To address the limitations of existing methods in securing electronic medical records, we have explored an encryption technique using a set of real-time medical images along with existing standard images using QKD protocols including BB84 (Bennett-Brassard 1984), CASCADE (Cascading Error Correction Algorithm for Data Exchange), and differential-phase-shift (DPS) under the fiber-based (OFC) and free-space (FSO) channels. It utilizes the quantum bit-plane representation of the Real Ket (QBRK) model and a logistic chaotic system with XOR operation. The performance of the developed framework is tested via visual illustration and 11 different quantitative assessments. The average entropy of the scrambled image for the medical source image is 7.9896, which is quite near to the optimum value of 8. The UACI (Unified Averaged Changed Intensity) and the NPCR (Number of Pixels Change Rate) metrics values lie between 33.7879 to 33.9711 and 99.6014 to 99.8000 for the FSO channel. The BB84 QKD protocol achieves a QBER (Quantum Bit Error Rate) of 0.0028 for an FSO channel with DCR (Dark Count Rate), which improves to 0.0012 when DCR is ignored for a 10 km link range. In addition, we analyzed and compared the effect of OFC on system output as the quantum channel. From several experiments, it is observed that the BB84 provides better results against CASCADE and DPS. The proposed work is validated using the Optisystem 15.1 software under FSO and for OFC.