TY - GEN
T1 - Improved Counting and Localization From Density Maps for Object Detection in 2D and 3D Microscopy Imaging
AU - Li, Shijie
AU - Gerig, Guido
AU - Ach, Thomas
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Crowd object counting and localization are key steps for quantitative analysis in large-scale microscopy applications. Previous methods producing density maps based on deep learning have reached a high level of accuracy for object counting by assuming that object counting is equivalent to the integration of the density map. However, this model fails when objects overlap significantly and/or present fuzzy boundaries regarding accurate localization. To overcome this limitation, we propose an alternative method to count and localize objects from the density map. Our procedure includes the following three key aspects: 1) Proposing a new connected-component analysis method based on the statistical properties of the density map, 2) optimizing the counting results for those objects which are well-detected based on the proposed counting method, and 3) improving localization of poorly detected objects using the proposed counting method as prior information. Validation includes processing microscopy data with known ground truth and comparison with other models that use conventional processing of the density map. Our results show improved performance in counting and localization of objects in 2D and 3D microscopy data. Furthermore, the proposed method is generic, considering various applications that rely on the density map approach.
AB - Crowd object counting and localization are key steps for quantitative analysis in large-scale microscopy applications. Previous methods producing density maps based on deep learning have reached a high level of accuracy for object counting by assuming that object counting is equivalent to the integration of the density map. However, this model fails when objects overlap significantly and/or present fuzzy boundaries regarding accurate localization. To overcome this limitation, we propose an alternative method to count and localize objects from the density map. Our procedure includes the following three key aspects: 1) Proposing a new connected-component analysis method based on the statistical properties of the density map, 2) optimizing the counting results for those objects which are well-detected based on the proposed counting method, and 3) improving localization of poorly detected objects using the proposed counting method as prior information. Validation includes processing microscopy data with known ground truth and comparison with other models that use conventional processing of the density map. Our results show improved performance in counting and localization of objects in 2D and 3D microscopy data. Furthermore, the proposed method is generic, considering various applications that rely on the density map approach.
KW - density map
KW - object counting
KW - object localization
UR - http://www.scopus.com/inward/record.url?scp=85172097867&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85172097867&partnerID=8YFLogxK
U2 - 10.1109/ISBI53787.2023.10230754
DO - 10.1109/ISBI53787.2023.10230754
M3 - Conference contribution
AN - SCOPUS:85172097867
T3 - Proceedings - International Symposium on Biomedical Imaging
BT - 2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023
PB - IEEE Computer Society
T2 - 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023
Y2 - 18 April 2023 through 21 April 2023
ER -