Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework
This work incrementally extends a counting framework to a new domain (cars) and adds localization capability.
The paper adapted the CLIP-EBC framework from crowd counting to car counting on the CARPK dataset, achieving second-best performance among existing methods, and proposed a K-means weighted clustering method to estimate object positions from density maps.
In this paper, we investigate the applicability of the CLIP-EBC framework, originally designed for crowd counting, to car object counting using the CARPK dataset. Experimental results show that our model achieves second-best performance compared to existing methods. In addition, we propose a K-means weighted clustering method to estimate object positions based on predicted density maps, indicating the framework's potential extension to localization tasks.