Deep CNN Based Multi Object Detection And Tracking In Video Frames With Mean Distributed Feature Set

Abstract

The computer vision field of object identification and tracking has been put to use in a broad variety of settings, from medical monitoring to autonomous vehicle navigation to anomaly detection and beyond. The efficiency of object detectors and trackers has substantially increased with the rapid growth of Deep Learning (DL) networks and the computational power of GPUs. Due to their poor generalization performance, classic extracting feature models are limited in their ability to recognize many targets in complicated scenarios, relying instead on low-level feature information such as contour information and texture information. In addition to gleaning granular texture features from pre-level Convolution Neural Networks (CNN), these models trained with deep learning can also glean meta-level knowledge from the post-level convolution layer. This research proposes a Deep CNN based Multi Object Detection and Tracking in Video Frame with Mean Distributed Feature Set (DCNN-MODT-MDFS) model for automatically assigning input objects to one of several predefined categories. Following object detection and tracking, the suggested techniques assign a class label by analyzing numerous frames in a video. The images could be taken from the video frames that are used to train the model. In order to account for the disparity in aspect ratio, the proposed method employs multi-scale feature maps for object detection and uses filters with unique default boxes. The model is trained until there is a noticeable drop in the error rate. The proposed model multi object detection rate and tracking rate is contrasted with the existing models and the results represent that proposed model performance is high.