L2HCount:Generalizing Crowd Counting from Low to High Crowd Density via Density Simulation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916654394376192 |
|---|---|
| author | Xu, Guoliang Yin, Jianqin Zhang, Ren Dang, Yonghao Zhou, Feng Yu, Bo |
| author_facet | Xu, Guoliang Yin, Jianqin Zhang, Ren Dang, Yonghao Zhou, Feng Yu, Bo |
| contents | Since COVID-19, crowd-counting tasks have gained wide applications. While supervised methods are reliable, annotation is more challenging in high-density scenes due to small head sizes and severe occlusion, whereas it's simpler in low-density scenes. Interestingly, can we train the model in low-density scenes and generalize it to high-density scenes? Therefore, we propose a low- to high-density generalization framework (L2HCount) that learns the pattern related to high-density scenes from low-density ones, enabling it to generalize well to high-density scenes. Specifically, we first introduce a High-Density Simulation Module and a Ground-Truth Generation Module to construct fake high-density images along with their corresponding ground-truth crowd annotations respectively by image-shifting technique, effectively simulating high-density crowd patterns. However, the simulated images have two issues: image blurring and loss of low-density image characteristics. Therefore, we second propose a Head Feature Enhancement Module to extract clear features in the simulated high-density scene. Third, we propose a Dual-Density Memory Encoding Module that uses two crowd memories to learn scene-specific patterns from low- and simulated high-density scenes, respectively. Extensive experiments on four challenging datasets have shown the promising performance of L2HCount. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12935 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | L2HCount:Generalizing Crowd Counting from Low to High Crowd Density via Density Simulation Xu, Guoliang Yin, Jianqin Zhang, Ren Dang, Yonghao Zhou, Feng Yu, Bo Computer Vision and Pattern Recognition Since COVID-19, crowd-counting tasks have gained wide applications. While supervised methods are reliable, annotation is more challenging in high-density scenes due to small head sizes and severe occlusion, whereas it's simpler in low-density scenes. Interestingly, can we train the model in low-density scenes and generalize it to high-density scenes? Therefore, we propose a low- to high-density generalization framework (L2HCount) that learns the pattern related to high-density scenes from low-density ones, enabling it to generalize well to high-density scenes. Specifically, we first introduce a High-Density Simulation Module and a Ground-Truth Generation Module to construct fake high-density images along with their corresponding ground-truth crowd annotations respectively by image-shifting technique, effectively simulating high-density crowd patterns. However, the simulated images have two issues: image blurring and loss of low-density image characteristics. Therefore, we second propose a Head Feature Enhancement Module to extract clear features in the simulated high-density scene. Third, we propose a Dual-Density Memory Encoding Module that uses two crowd memories to learn scene-specific patterns from low- and simulated high-density scenes, respectively. Extensive experiments on four challenging datasets have shown the promising performance of L2HCount. |
| title | L2HCount:Generalizing Crowd Counting from Low to High Crowd Density via Density Simulation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.12935 |