Abstract Current models for computer vision in neural networks are trained using billions of images. The concept is that these models can improve their generalisation ability when the dataset includes a wide range of images, such as those with different lighting and environmental conditions of the same objects. This ability to generalize is essential in the task of object detection, particularly... Current models for computer vision in neural networks are trained using billions of images. The concept is that these models can improve their generalisation ability when the dataset includes a wide range of images, such as those with different lighting and environmental conditions of the same objects. This ability to generalize is essential in the task of object detection, particularly when it comes to the challenge of cross-depiction. In this research, we investigate the application of Neural Style Transfer as a new method to transform the initial data and improve model generalization. To test the impact on performance for object detection models, we chose the Faster R-CNN model for application on the Pascal VOC 2012 dataset. Several experiments were conducted, including style changes on images and adjustments to the parameters of Neural Style Transfer to preserve the content of the original images. The results were encouraging, suggesting a promising basis for further research on cross-depiction through Neural Style Transfer. Read More Read Less

Abstract A smart computer system designed to manage and oversee the crowd levels in restricted areas is extremely beneficial. It’s crucial to develop a solution that considers these locations’ computing power and built-in components. By leveraging computer vision, especially with the addition of smart CCTV cameras equipped with artificial intelligence, the issue of accurately tallying people in confined areas can be... A smart computer system designed to manage and oversee the crowd levels in restricted areas is extremely beneficial. It’s crucial to develop a solution that considers these locations’ computing power and built-in components. By leveraging computer vision, especially with the addition of smart CCTV cameras equipped with artificial intelligence, the issue of accurately tallying people in confined areas can be addressed. We outline a control mechanism tailored for this purpose, optimizing the existing infrastructure and improving artificial intelligence to increase the speed of capturing frames. Read More Read Less

Abstract Our research takes a bold step in the field of rendering, focusing on an innovative approach that seamlessly blends 3D objects into reconstructed 3D spaces, offering fresh perspectives of the scene. By using Neural Radiance Field (NeRF) models to create detailed 3D spaces and depth estimation algorithms to extract 3D features of objects from single images, we aim to align... Our research takes a bold step in the field of rendering, focusing on an innovative approach that seamlessly blends 3D objects into reconstructed 3D spaces, offering fresh perspectives of the scene. By using Neural Radiance Field (NeRF) models to create detailed 3D spaces and depth estimation algorithms to extract 3D features of objects from single images, we aim to align the depth information from the NeRF model with the depth data of the added object. This precise and spatially consistent placement of the object in the scene not only enhances the realism of the virtual world but also opens up new possibilities in the field of computer graphics. Read More Read Less