EMSPAN: Efficient Multi-Scale Pyramid Attention Network for Object Counting Under Size Heterogeneity and Dense Scenarios
Computer vision is becoming an increasingly vital field, offering significant opportunities for real-world applications. Object counting is one of its core aspects, with increasing utilization across scientific fields involving objects of varying sizes. Traditional counting methods, however, face ch...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10851276/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576750383529984 |
|---|---|
| author | Phu Nguyen Phan Hai Bao Bui Quoc Trang Hoang |
| author_facet | Phu Nguyen Phan Hai Bao Bui Quoc Trang Hoang |
| author_sort | Phu Nguyen Phan Hai |
| collection | DOAJ |
| description | Computer vision is becoming an increasingly vital field, offering significant opportunities for real-world applications. Object counting is one of its core aspects, with increasing utilization across scientific fields involving objects of varying sizes. Traditional counting methods, however, face challenges in dense scenarios, as they are often ineffective in handling objects of different sizes. To address these challenges, this paper proposes the Efficient Multi-Scale Pyramid Attention Network (EMSPAN) model, which is designed to tackle both dense and size-heterogeneous object counting tasks. Additionally, a novel ground truth density map generation method using size-adaptive Gaussian kernels is introduced, which dynamically adjusts kernel size based on object dimensions. This approach preserves spatial information more effectively and produces more accurate density maps, even in complex scenes. The EMSPAN model utilizes advanced attention mechanisms to capture the multi-scale spatial distribution and size variations of objects. Experiments on the shrimp larvae and crowd datasets, characterized by significant size diversity of individual objects, have demonstrated the superior performance of the proposed method in handling object counting tasks in dense and size-heterogeneous environments. |
| format | Article |
| id | doaj-art-3f0f0f007db0470e809d082d88d4910a |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-3f0f0f007db0470e809d082d88d4910a2025-01-31T00:01:08ZengIEEEIEEE Access2169-35362025-01-0113179451796210.1109/ACCESS.2025.353296210851276EMSPAN: Efficient Multi-Scale Pyramid Attention Network for Object Counting Under Size Heterogeneity and Dense ScenariosPhu Nguyen Phan Hai0https://orcid.org/0000-0002-8667-7746Bao Bui Quoc1https://orcid.org/0000-0002-8467-0532Trang Hoang2https://orcid.org/0000-0001-7317-9708Department of Electronics, Faculty of Electrical and Electronics Engineering, Ho Chi Minh City University of Technology (HCMUT), Ho Chi Minh City, VietnamDepartment of Electronics, Faculty of Electrical and Electronics Engineering, Ho Chi Minh City University of Technology (HCMUT), Ho Chi Minh City, VietnamDepartment of Electronics, Faculty of Electrical and Electronics Engineering, Ho Chi Minh City University of Technology (HCMUT), Ho Chi Minh City, VietnamComputer vision is becoming an increasingly vital field, offering significant opportunities for real-world applications. Object counting is one of its core aspects, with increasing utilization across scientific fields involving objects of varying sizes. Traditional counting methods, however, face challenges in dense scenarios, as they are often ineffective in handling objects of different sizes. To address these challenges, this paper proposes the Efficient Multi-Scale Pyramid Attention Network (EMSPAN) model, which is designed to tackle both dense and size-heterogeneous object counting tasks. Additionally, a novel ground truth density map generation method using size-adaptive Gaussian kernels is introduced, which dynamically adjusts kernel size based on object dimensions. This approach preserves spatial information more effectively and produces more accurate density maps, even in complex scenes. The EMSPAN model utilizes advanced attention mechanisms to capture the multi-scale spatial distribution and size variations of objects. Experiments on the shrimp larvae and crowd datasets, characterized by significant size diversity of individual objects, have demonstrated the superior performance of the proposed method in handling object counting tasks in dense and size-heterogeneous environments.https://ieeexplore.ieee.org/document/10851276/Computer visiondensity estimationsize-adjustable Gaussian kerneldeep learningconvolutional neural networksattention mechanisms |
| spellingShingle | Phu Nguyen Phan Hai Bao Bui Quoc Trang Hoang EMSPAN: Efficient Multi-Scale Pyramid Attention Network for Object Counting Under Size Heterogeneity and Dense Scenarios IEEE Access Computer vision density estimation size-adjustable Gaussian kernel deep learning convolutional neural networks attention mechanisms |
| title | EMSPAN: Efficient Multi-Scale Pyramid Attention Network for Object Counting Under Size Heterogeneity and Dense Scenarios |
| title_full | EMSPAN: Efficient Multi-Scale Pyramid Attention Network for Object Counting Under Size Heterogeneity and Dense Scenarios |
| title_fullStr | EMSPAN: Efficient Multi-Scale Pyramid Attention Network for Object Counting Under Size Heterogeneity and Dense Scenarios |
| title_full_unstemmed | EMSPAN: Efficient Multi-Scale Pyramid Attention Network for Object Counting Under Size Heterogeneity and Dense Scenarios |
| title_short | EMSPAN: Efficient Multi-Scale Pyramid Attention Network for Object Counting Under Size Heterogeneity and Dense Scenarios |
| title_sort | emspan efficient multi scale pyramid attention network for object counting under size heterogeneity and dense scenarios |
| topic | Computer vision density estimation size-adjustable Gaussian kernel deep learning convolutional neural networks attention mechanisms |
| url | https://ieeexplore.ieee.org/document/10851276/ |
| work_keys_str_mv | AT phunguyenphanhai emspanefficientmultiscalepyramidattentionnetworkforobjectcountingundersizeheterogeneityanddensescenarios AT baobuiquoc emspanefficientmultiscalepyramidattentionnetworkforobjectcountingundersizeheterogeneityanddensescenarios AT tranghoang emspanefficientmultiscalepyramidattentionnetworkforobjectcountingundersizeheterogeneityanddensescenarios |