Robust Deep Transfer Learning Based Object Detection and Tracking Approach

作     者：C.Narmadha T.Kavitha R.Poonguzhali V.Hamsadhwani Ranjan walia Monia B.Jegajothi 

作者机构：Electronics and Communication EngineeringPeriyar Maniammai Institute of Science&Technology(PMIST)Thanjavur613403India Department of Computer Science and EngineeringPeriyar Maniammai Institute of Science&TechnologyThanjavur613403India Department of Electrical and Electronics EngineeringPeriyar Maniammai Institute of Science and TechnologyThanjavur613403India Electrical Engineering DepartmentModel Institute of Engineering&Technology(Autonomous)Jammu181122India Department of Computer Science and EngineeringShri Mata Vaishno Devi UniversityKatra182320India Center for Energy ResearchChennai Institute of TechnologyChennai600069India 

出 版 物：《Intelligent Automation & Soft Computing》 (智能自动化与软计算（英文）)

年 卷 期：2023年第35卷第3期

页      面：3613-3626页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Object detection tracking deep learning deep transfer learning image annotation 

摘      要：At present days,object detection and tracking concepts have gained more importance among researchers and business ***,deep learning(DL)approaches have been used for object tracking as it increases the perfor-mance and speed of the tracking *** paper presents a novel robust DL based object detection and tracking algorithm using Automated Image Anno-tation with ResNet based Faster regional convolutional neural network(R-CNN)named(AIA-FRCNN)*** AIA-RFRCNN method performs image anno-tation using a Discriminative Correlation Filter(DCF)with Channel and Spatial Reliability tracker(CSR)called DCF-CSRT *** AIA-RFRCNN model makes use of Faster RCNN as an object detector and tracker,which involves region proposal network(RPN)and Fast *** RPN is a full convolution network that concurrently predicts the bounding box and score of different *** RPN is a trained model used for the generation of the high-quality region proposals,which are utilized by Fast R-CNN for detection ***,Residual Network(ResNet 101)model is used as a shared convolutional neural network(CNN)for the generation of feature *** performance of the ResNet 101 model is further improved by the use of Adam optimizer,which tunes the hyperparameters namely learning rate,batch size,momentum,and weight ***,softmax layer is applied to classify the *** performance of the AIA-RFRCNN method has been assessed using a benchmark dataset and a detailed comparative analysis of the results takes *** outcome of the experiments indicated the superior characteristics of the AIA-RFRCNN model under diverse aspects.