Nowadays, the need for research on an intelligent video monitoring system is increasingworldwide. Among the object detection methods, the core technology of the intelligent videomonitoring system, or object detection using a deep learning-based convolutional neural network,is used widely due to its proven performance. Nonetheless, deep learning-based object detectionrequires many hardware resources because it decodes the videos to analyze. Therefore, thisarticle suggests an advanced object recognition technique by conducting compressed videostream-based object detection in order to reduce consumption of resources for object detection aswell as improve performance and confirms via the performance evaluation that speed andrecognition rate improved compared to existing algorithms such as YOLO, SSD, and Faster RCNN.
展开▼
