# 3D Reconstruction-Based Seed Counting of Sorghum Panicles for Agricultural Inspection

arXiv: https://arxiv.org/abs/2211.07748 · HTML: https://mlsanity.com/paper/2211.07748/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 30 references that are in the map.
- First posted on arXiv 14 Nov 2022.

## Builds on (most cited first, 10 of 10)

- [RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching](https://mlsanity.com/paper/2109.07547/) (2021)
- [CenterMask : Real-Time Anchor-Free Instance Segmentation](https://mlsanity.com/paper/1911.06667/) (2019)
- [A Robust Illumination-Invariant Camera System for Agricultural Applications](https://mlsanity.com/paper/2101.02190/) (2021)
- [DeepCorn: A Semi-Supervised Deep Learning Method for High-Throughput Image-Based Corn Kernel Counting and Yield Estimation](https://mlsanity.com/paper/2007.10521/) (2020)
- [Bumblebee: A Path Towards Fully Autonomous Robotic Vine Pruning](https://mlsanity.com/paper/2112.00291/) (2021)
- [Monocular Camera Based Fruit Counting and Mapping with Semantic Data Association](https://mlsanity.com/paper/1811.01417/) (2018)
- [Design of an Autonomous Precision Pollination Robot](https://mlsanity.com/paper/1808.10010/) (2018)
- [Image-Based Sorghum Head Counting When You Only Look Once](https://mlsanity.com/paper/2009.11929/) (2020)
- [A metric for evaluating 3D reconstruction and mapping performance with no ground truthing](https://mlsanity.com/paper/2101.10402/) (2021)
- [AgriColMap: Aerial-Ground Collaborative 3D Mapping for Precision Farming](https://mlsanity.com/paper/1810.00457/) (2018)

## Built on by (most cited first, 3 of 3)

- [Detecting Olives with Synthetic or Real Data? Olive the Above](https://mlsanity.com/paper/2308.08271/) (2023)
- [Language-Guided Object Search in Agricultural Environments](https://mlsanity.com/paper/2503.01068/) (2025)
- [Transformer-Based Spatio-Temporal Association of Apple Fruitlets](https://mlsanity.com/paper/2503.03200/) (2025)

## Abstract (arXiv)

In this paper, we present a method for creating high-quality 3D models of sorghum panicles for phenotyping in breeding experiments. This is achieved with a novel reconstruction approach that uses seeds as semantic landmarks in both 2D and 3D. To evaluate the performance, we develop a new metric for assessing the quality of reconstructed point clouds without having a ground-truth point cloud. Finally, a counting method is presented where the density of seed centers in the 3D model allows 2D counts from multiple views to be effectively combined into a whole-panicle count. We demonstrate that using this method to estimate seed count and weight for sorghum outperforms count extrapolation from 2D images, an approach used in most state of the art methods for seeds and grains of comparable size.