Real Time Multiple-Object Detection Based On Enhanced SSD

Object detection and recognition are widely employed in a variety of computer vision applications, and numerous techniques have been suggested in the literature. Object detection is one of the areas of computer vision that has seen a lot of achievement. In the last decade, various applications of computer vision have been presented. Some of these include autonomous cars, video surveillance, and scene interpretation. Visual recognition systems, including image categorization, localization, and detection, are at the heart of all of these applications and have gathered a lot of research attention. These visual identification algorithms have achieved extraordinary performance because of considerable advancements in neural networks, particularly deep learning (DL). Object detection techniques in real-time systems, on the other hand, necessitate minimal computing time and a thorough performance assessment prior to deployment. In this paper multiple image detection approach is used to identify and locate the object concerning their class label, and an enhanced feature map is used for object detection. All this is possible due to the recent advancement in DL along with image processing. These images, fed to the model, come from the video source. To tackle the problem related to the aspect ratio, the model uses the multi-scale feature map together with a distinct filter for diverse default boxes.