Improved Panicle Counting With Density-Aware Sampling and Enhanced Matching

Paddy is a critical global food crop, and its productivity is directly dependent on the number of panicles. Accurate panicle counting is essential for effective crop management. Existing localization-based methods rely on intermediate representations like density maps, which are often counter-intuitive and prone to errors. To quantify and locate panicles directly rather than sequentially, we propose P2PNet-Paddy, a novel approach based on the Point-to-Point Network (P2PNet) architecture, which was initially developed for crowd counting and localization. While the original P2PNet uses the Hungarian algorithm for point matching, it is found to result in uncertain matching results without context, reducing the counting efficiency. It is found that P2PNet encounters significant performance limitations when applied to agricultural datasets characterized by highly imbalanced panicle density distributions. We suggest integrating a density-based sampler to mitigate the impact of panicle density imbalance in the dataset and the k-nearest neighbors Matching Objective (KMO) Hungarian matcher to enhance the matching process by incorporating additional contextual information. Our proposed approach led to notable improvements, reducing MAE by 36% and MAPE by 48.3% compared to the baseline P2PNet model. The proposed method achieved an MAE of 7.31, MAPE of 39.18, and R2 score of 0.87 on the test data. The dataset and code will be made publicly available.