Granulated RCNN And Multi-Class Deep SORT ... - Semantic Scholar

Skip to search formSkip to main contentSkip to account menu

• DOI:10.1109/tetci.2020.3041019
• Corpus ID: 234311804

Granulated RCNN and Multi-Class Deep SORT for Multi-Object Detection and Tracking@article{Pramanik2022GranulatedRA, title={Granulated RCNN and Multi-Class Deep SORT for Multi-Object Detection and Tracking}, author={Anima Pramanik and Sankar K. Pal and Jhareswar Maiti and Pabitra Mitra}, journal={IEEE Transactions on Emerging Topics in Computational Intelligence}, year={2022}, volume={6}, pages={171-181}, url={https://api.semanticscholar.org/CorpusID:234311804} }

• Anima Pramanik, S. Pal, +1 author Pabitra Mitra
• Published in IEEE Transactions on Emerging… 1 February 2022
• Computer Science

TLDRTwo new models, namely granulated RCNN (G-RCNN) and multi-class deep SORT (MCD-SORT), for object detection and tracking, respectively from videos are developed, establishing Superiority of the models over several state-of-the-art methodologies.ExpandView on IEEEdoi.orgSave to LibrarySaveCreate AlertAlertCiteShare104 CitationsHighly Influential Citations3Background Citations20 Methods Citations29View All

104 Citations

Citation TypeHas PDFAuthorMore FiltersMore FiltersFiltersSort by RelevanceSort by Most Influenced PapersSort by Citation CountSort by Recency

YOLO-SM: A Lightweight Single-Class Multi-Deformation Object Detection Network

Xuebin YueLin MengComputer ScienceIEEE Transactions on Emerging Topics in…
• 2024

TLDRThis paper designs a lightweight backbone structure for object detection, namely, DCMNet, and proposes the object detection network YOLO-SM, which has a good performance tradeoff between speed and accuracy in detecting single-class multi-deformation objects.Expand

• 27

• 1 Excerpt

Save

Multi-class object detection system using hybrid convolutional neural network architecture

J. BoradeM. A. LakshmiComputer ScienceMultimedia Tools and Applications
• 2022

TLDRThe proposed system generalized a hybrid convolutional neural network (H-CNN) model is used to realize the user object from an image and proved that the excluded result of Mean Average Precision (mAP), Precision, Accuracy, Recall values and F1-Score achieved better results than with recently developed works.Expand

• 1 Excerpt

Save

Granulated mask RCNN and eye detection index (EDI) for detection and localization of eye of tropical cyclone from satellite imagery

S. PalShreya BiswasDebashree DuttaEnvironmental Science, Computer ScienceJournal of Data, Information and Management
• 2024

TLDRThe results reveal that the performance of the G-MRCNN with k-means (k = 5) clustering-based granulation is better than other methods for the detection and localization of the eye of the tropical cyclone over NIO.Expand

• 3
• Highly Influenced

• 4 Excerpts

Save

Enhancing Object Detection and Tracking with Attention Mechanisms in Computer Vision

Xia ZhangZiheng ZhouShihao QiuComputer ScienceProceedings of the 4th International Conference…
• 2025

TLDRA structured deep learning architecture that relies on attention-based focalization to directly embed multi-scale attention modules into convolutional neural network (CNN) architecture to enhance the precision and effectiveness of object detection and tracking.Expand

• 1 Excerpt

Save

Deep learning in multi-object detection and tracking: state of the art

S. PalAnima PramanikJ. MaitiPabitra MitraComputer ScienceApplied Intelligence
• 2021

TLDRThis survey has critically analyzed the existing DL network-based methods of object detection and tracking and described various benchmark datasets and provided a comprehensive overview of a variety of both genericobject detection and specific object detection models.Expand

• 249
• Highly Influenced
• PDF

• 7 Excerpts

Save

Object detection and multi‐object tracking based on optimized deep convolutional neural network and unscented Kalman filtering

Thirumalai JaganathanAnandan PanneerselvamSenthilkumar KumaraswamyComputer ScienceConcurr. Comput. Pract. Exp.
• 2022

TLDRThe proposed Jaya‐PO‐based DCNN and HGSO‐based UKF outperformed other methods with high accuracy of 92%, high multiple object tracking precision (MOTP), high sensitivity of 91.7%, and high specificity of 92%.Expand

• 7

• 1 Excerpt

Save

Enhanced Lightweight Object Detection Model in Complex Scenes: An Improved YOLOv8n Approach

Sohaya El HamdouniBoutaina HdioudSanaa El FkihiComputer ScienceInformation
• 2025

TLDRA lightweight object detection algorithm, utilizing YOLOv8n as the baseline model, to address problems of complex scenes containing small, occluded, and multiscale objects, and ensures good detection performance while decreasing the number of parameters.ExpandSave

Research on Object Detection and Tracking Based on Deep Learning

Jing PanComputer Science, Engineering2024 4th International Conference on Machine…
• 2024

TLDRA novel framework of convolutional neural network (CNN) architecture is proposed, which optimizes the process of feature extraction and object classification, and significantly improves the detection accuracy.Expand

• 1 Excerpt

Save

On the Importance of Large Objects in CNN Based Object Detection Algorithms

Ahmed Ben SaadGabriele FaccioloAxel DavyComputer Science2024 IEEE/CVF Winter Conference on Applications…
• 2024

TLDRIt is shown that giving more weight to large objects leads to improved detection scores across all object sizes and so an overall improvement in Object Detectors performances.Expand

• 7
[PDF]

• 1 Excerpt

Save

DAF-Net: dense attention feature pyramid network for multiscale object detection

Divine Njengwie AchinekI. S. ShehuAthuman Mohamed AthumanXianping FuComputer ScienceInternational Journal of Multimedia Information…
• 2024

TLDRThis work proposed a more prominent architecture called dense attention feature pyramid network (DAF-Net) for multiscale object detection, which consists of two attention models, the spatial attention model and channel attention model and implemented a dense connected attention FPN to reduce the model’s complexity and resolve the learning of redundant feature maps.Expand

• 4

• 1 Excerpt

Save...12345...

Related Papers

Showing 1 through 3 of 0 Related Papers

• 104 Citations
• Related Papers

By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)ACCEPT & CONTINUEor Only Accept Required