WheatSpikeNet: an improved wheat spike segmentation model for accurate estimation from field imaging

M A Batin; Muhaiminul Islam; Md Mehedi Hasan; Akm Azad; Salem A Alyami; Md Azam Hossain; Stanley J Miklavcic

doi:10.3389/fpls.2023.1226190

WheatSpikeNet: an improved wheat spike segmentation model for accurate estimation from field imaging

Front Plant Sci. 2023 Aug 25:14:1226190. doi: 10.3389/fpls.2023.1226190. eCollection 2023.

Authors

M A Batin¹, Muhaiminul Islam¹, Md Mehedi Hasan¹, Akm Azad², Salem A Alyami², Md Azam Hossain³, Stanley J Miklavcic⁴

Affiliations

¹ Department of Robotics and Mechatronics Engineering, University of Dhaka, Dhaka, Bangladesh.
² Department of Mathematics and Statistics, College of Science, Imam Mohammad Ibn Saud Islamic University, Riyadh, Saudi Arabia.
³ Department of Computer Science and Engineering, Islamic University of Technology, Gazipur, Bangladesh.
⁴ Phenomics and Bioinformatics Research Centre, University of South Australia, Adelaide, SA, Australia.

Abstract

Phenotyping is used in plant breeding to identify genotypes with desirable characteristics, such as drought tolerance, disease resistance, and high-yield potentials. It may also be used to evaluate the effect of environmental circumstances, such as drought, heat, and salt, on plant growth and development. Wheat spike density measure is one of the most important agronomic factors relating to wheat phenotyping. Nonetheless, due to the diversity of wheat field environments, fast and accurate identification for counting wheat spikes remains one of the challenges. This study proposes a meticulously curated and annotated dataset, named as SPIKE-segm, taken from the publicly accessible SPIKE dataset, and an optimal instance segmentation approach named as WheatSpikeNet for segmenting and counting wheat spikes from field imagery. The proposed method is based on the well-known Cascade Mask RCNN architecture with model enhancements and hyperparameter tuning to provide state-of-the-art detection and segmentation performance. A comprehensive ablation analysis incorporating many architectural components of the model was performed to determine the most efficient version. In addition, the model's hyperparameters were fine-tuned by conducting several empirical tests. ResNet50 with Deformable Convolution Network (DCN) as the backbone architecture for feature extraction, Generic RoI Extractor (GRoIE) for RoI pooling, and Side Aware Boundary Localization (SABL) for wheat spike localization comprises the final instance segmentation model. With bbox and mask mean average precision (mAP) scores of 0.9303 and 0.9416, respectively, on the test set, the proposed model achieved superior performance on the challenging SPIKE datasets. Furthermore, in comparison with other existing state-of-the-art methods, the proposed model achieved up to a 0.41% improvement of mAP in spike detection and a significant improvement of 3.46% of mAP in the segmentation tasks that will lead us to an appropriate yield estimation from wheat plants.

Keywords: cascade RCNN; deformable convolution network; plant phenotyping; segmentation; wheat spikes.

Grants and funding

The authors extend their appreciation to the Deputyship for Research & Innovation, Ministry of Education in Saudi Arabia for funding this research through the project number IFP-IMSIU-2023003 . The authors also appreciate the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University (IMSIU) for supporting and supervising this project.