Earticle

초록

영어

In this paper, we propose a new framework that enables an object detector trained with only point-level annotations to estimate the centroids and sizes of objects in dense scenes. Specifically, the framework is based on the Swin Transformer structure and introduces a self-designed resolution feature fusion module in the hierarchical structure, where the estimation of object centroids is done directly by point supervision, and the object pseudo-size is initialized based on the assumption of local uniform distribution, and the regression of object size is guided by an improved congestion-aware loss function. In the NWPU-Crowd dataset, our method outperformed the existing state-of-the-art detection counting methods in F1-measure, precision, MSE evaluation criteria.

목차

Abstract
I. INTRODUCTION
II. METHOD
A. Swin Transformer
B. Resolution feature fusion module
C. Congestion-aware loss function
III. EXPERIMENTS
A. Evaluation Criteria
B. Dataset
C. Parameter Setting
D. Ablation experiments
E. Experiment results
IV. CONCLUSION
REFERENCES

키워드

저자

• Yi Ren [ Computer Science Chongqing University of Posts and Telecommunications Chongqing, China ] Corresponding Author
• Xin He [ Computer Science Chongqing University of Posts and Telecommunication Chongqing, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  한국차세대컴퓨팅학회 학술대회

• 간기

  반년간

• 수록기간

  2021~2025

• 십진분류

  KDC 566 DDC 004