Ye Jianxiong, Yu Zhenghong, Wang Yangxu, Lu Dunlu, Zhou Huabing
College of Robotics, Guangdong Polytechnic of Science and Technology, Zhuhai, Guangdong, China.
Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan, China.
Plant Methods. 2023 Oct 4;19(1):103. doi: 10.1186/s13007-023-01079-x.
Detection and counting of wheat heads are of crucial importance in the field of plant science, as they can be used for crop field management, yield prediction, and phenotype analysis. With the widespread application of computer vision technology in plant science, monitoring of automated high-throughput plant phenotyping platforms has become possible. Currently, many innovative methods and new technologies have been proposed that have made significant progress in the accuracy and robustness of wheat head recognition. Nevertheless, these methods are often built on high-performance computing devices and lack practicality. In resource-limited situations, these methods may not be effectively applied and deployed, thereby failing to meet the needs of practical applications.
In our recent research on maize tassels, we proposed TasselLFANet, the most advanced neural network for detecting and counting maize tassels. Building on this work, we have now developed a high-real-time lightweight neural network called WheatLFANet for wheat head detection. WheatLFANet features a more compact encoder-decoder structure and an effective multi-dimensional information mapping fusion strategy, allowing it to run efficiently on low-end devices while maintaining high accuracy and practicality. According to the evaluation report on the global wheat head detection dataset, WheatLFANet outperforms other state-of-the-art methods with an average precision AP of 0.900 and an R value of 0.949 between predicted values and ground truth values. Moreover, it runs significantly faster than all other methods by an order of magnitude (TasselLFANet: FPS: 61).
Extensive experiments have shown that WheatLFANet exhibits better generalization ability than other state-of-the-art methods, and achieved a speed increase of an order of magnitude while maintaining accuracy. The success of this study demonstrates the feasibility of achieving real-time, lightweight detection of wheat heads on low-end devices, and also indicates the usefulness of simple yet powerful neural network designs.
小麦穗的检测与计数在植物科学领域至关重要，因为它们可用于作物田间管理、产量预测和表型分析。随着计算机视觉技术在植物科学中的广泛应用，对自动化高通量植物表型平台的监测已成为可能。目前，已经提出了许多创新方法和新技术，在小麦穗识别的准确性和鲁棒性方面取得了显著进展。然而，这些方法通常基于高性能计算设备，缺乏实用性。在资源有限的情况下，这些方法可能无法有效应用和部署，从而无法满足实际应用的需求。
在我们最近对玉米雄穗的研究中，我们提出了TasselLFANet，这是用于检测和计数玉米雄穗的最先进神经网络。在此基础上，我们现在开发了一种名为WheatLFANet的高实时轻量级神经网络用于小麦穗检测。WheatLFANet具有更紧凑的编码器 - 解码器结构和有效的多维度信息映射融合策略，使其能够在低端设备上高效运行，同时保持高精度和实用性。根据全球小麦穗检测数据集的评估报告，WheatLFANet在预测值与真实值之间的平均精度AP为0.900，R值为0.949，优于其他现有方法。此外，它的运行速度比所有其他方法快一个数量级（TasselLFANet：FPS：61）。
大量实验表明，WheatLFANet比其他现有方法具有更好的泛化能力，并且在保持准确性的同时实现了一个数量级的速度提升。这项研究的成功证明了在低端设备上实现小麦穗实时、轻量级检测的可行性，也表明了简单而强大的神经网络设计的有用性。
