360° Security in Cameras Using Linear Binary Pattern Histogram

This research study proposes a novel approach for enhancing the security of surveillance cameras by using a combination of panoramic cameras and linear binary pattern (LBP) histograms. The proposed method can detect and track intruders in a 360° field of view, which is achieved by stitching together multiple images captured by the panoramic camera. The LBP histogram is then used to extract features from the stitched image, which are fed into a support vector machine (SVM) classifier for intruder detection. The proposed method is compared to several state-of-the-art methods, and experimental results show that the proposed method outperforms them in terms of accuracy and detection rate. Furthermore, the proposed method is shown to be robust to lighting changes and occlusions, making it suitable for real-world applications and the approach is then evaluated on a dataset of 360° images captured by cameras and achieves high accuracy in detecting abnormal events such as intrusion and theft. The results demonstrate the effectiveness of the proposed approach in enhancing the security of cameras and can be useful in various applications such as surveillance systems, smart homes, and malls.