Abstract
Moving object tracking techniques using machine and deep learning require large datasets for neural model training. New strategies need to be invented that utilize smaller data training sizes to realize the impact of large-sized datasets. However, current research does not balance the training data size and neural parameters, which creates the problem of inadequacy of the information provided by the low visual data content for parameter optimization. To enhance the performance of moving object tracking that appears in only a few frames, this research proposes a deep learning model using an abundant encoder–decoder (a high-resolution transformer (HRT) encoder–decoder). An HRT encoder–decoder employs feature map extraction that focuses on high resolution feature maps that are more representative of the moving object. In addition, we employ the proposed HRT encoder–decoder for feature map extraction and fusion to reimburse the few frames that have the visual information. Our extensive experiments on the Pascal DOC19 and MS-DS17 datasets have implied that the HRT encoder–decoder abundant model outperforms those of previous studies involving few frames that include moving objects.
Subject
Earth and Planetary Sciences (miscellaneous),Computers in Earth Sciences,Geography, Planning and Development
Reference43 articles.
1. Direct monocular non-alluded SLAM;Engel;Comput. Vis.,2019
2. ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras
3. DynaSLAM: Tracking, Mapping, and Inpainting in Dynamic Scenes
4. AGV global localization using indistinguishable artificial landmarks;Ronzoni;Proceedings of the IEEE Conference on Robotics,2020
5. SLAM2: A SLAM system for monocular stereo and RGB-D cameras;Hafez;IEEE Trans. Robot.,2020
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. A Face Image Processing System Based on Object Tracking Technology;2023 International Conference on Integrated Intelligence and Communication Systems (ICIICS);2023-11-24
2. Siamese network based on global and local feature matching for object tracking;Journal of Electronic Imaging;2022-11-18