CentroidNet: A Deep Neural Network for Joint Object Localization and CountingDijkstra, K., van de Loosdrecht, J., Schomaker, L. R. B. & Wiering, M. A., 2019, ECML PKDD 2018: Machine Learning and Knowledge Discovery in Databases. Brefeld, U., Curry, E., Daly, E., MacNamee, B., Marascu, A., Pinelli, F., Berlingerio, M. & Hurly, N. (eds.). Cham: Springer, p. 585-601 17 p. ( Lecture Notes in Computer Science; vol. 11053).
Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic › peer-review
In precision agriculture, counting and precise localization of crops is important for optimizing crop yield. In this paper CentroidNet is introduced which is a Fully Convolutional Neural Network (FCNN) architecture specifically designed for object localization and counting. A field of vectors pointing to the nearest object centroid is trained and combined with a learned segmentation map to produce accurate object centroids by majority voting. This is tested on a crop dataset made using a UAV (drone) and on a cell-nuclei dataset which was provided by a Kaggle challenge. We define the mean Average F1 score (mAF1) for measuring the trade-off between precision and recall. CentroidNet is compared to the state-of-the-art networks YOLOv2 and RetinaNet, which share similar properties. The results show that CentroidNet obtains the best F1 score. We also explicitly show that CentroidNet can seamlessly switch between patches of images and full-resolution images without the need for retraining.
|Title of host publication||ECML PKDD 2018|
|Subtitle of host publication||Machine Learning and Knowledge Discovery in Databases|
|Editors||Ulf Brefeld, Edward Curry, Elizabeth Daly, Brian MacNamee, Alice Marascu, Fabio Pinelli, Michele Berlingerio, Neil Hurly|
|Place of Publication||Cham|
|Number of pages||17|
|Publication status||Published - 2019|
|Name||Lecture Notes in Computer Science|