An Efficient Processing Approach for Colored Point Cloud-Based High-Throughput Seedling Phenotyping

Yang, Shuanying; Zheng, Lihua; Gao, Wanlin; Wang, Bingbing; Xia, Hao; Mi, Jiaqi; Wang, Minjuan

doi:10.3390/rs12101540

Cited by 21 publications

(12 citation statements)

References 50 publications

(80 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While we generated the synthetic soybean seeds test dataset by the method described in the previous section, a real-world soybean seeds test dataset was prepared consisting of 40 images by the following steps: (a) use a 100-seed board to select about 100 soybean seeds randomly one time; (b) tile these seeds upon the black-colored flannel randomly and make these seeds densely sampled (e.g., physically touching) to simulate the phenotypic investigation in the real scene; (c) capture 8 images (4 images for 2 cultivars) with the image size of 3024 × 3024 by the camera sensor of an iPhone 6 s plus (Apple) erected on a tripod with about 0.3 m working distance and 32 images (16 images for 2 cultivars) with the image size of 1920 × 1080 at 96 dpi by the RGB sensor of Kinect v2 (Microsoft, Redmond, WA, USA) erected on a tripod with about 0.75 m [ 20 ] working distance as shown in Fig. 3 .…”

Section: Methodsmentioning

confidence: 99%

“…These software and methods mentioned above can realize the phenotype parameters measurement of high throughput seeds which are sparsely placed without overlap under consistent light condition to achieve an effective segmentation. When soybean seeds are densely sampled and physically contacted with each other or when the illumination condition of seeds is inconsistent, these seeds cannot be effectively segmented into individual seed to calculate each individual seed phenotype parameters, and these tailored image segmentation algorithms which are based on classic image processing technology are sensitive to the texture of object and illumination conditions [ 20 ]. Above all, traditional image processing methods show weak robustness and poor generalization ability.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

High-throughput soybean seeds phenotyping with convolutional neural networks and transfer learning

Yang

Zheng

et al. 2021

Plant Methods

Self Cite

View full text Add to dashboard Cite

Background Effective soybean seed phenotyping demands large-scale accurate quantities of morphological parameters. The traditional manual acquisition of soybean seed morphological phenotype information is error-prone, and time-consuming, which is not feasible for large-scale collection. The segmentation of individual soybean seed is the prerequisite step for obtaining phenotypic traits such as seed length and seed width. Nevertheless, traditional image-based methods for obtaining high-throughput soybean seed phenotype are not robust and practical. Although deep learning-based algorithms can achieve accurate training and strong generalization capabilities, it requires a large amount of ground truth data which is often the limitation step. Results We showed a novel synthetic image generation and augmentation method based on domain randomization. We synthesized a plenty of labeled image dataset automatedly by our method to train instance segmentation network for high throughput soybean seeds segmentation. It can pronouncedly decrease the cost of manual annotation and facilitate the preparation of training dataset. And the convolutional neural network can be purely trained by our synthetic image dataset to achieve a good performance. In the process of training Mask R-CNN, we proposed a transfer learning method which can reduce the computing costs significantly by finetuning the pre-trained model weights. We demonstrated the robustness and generalization ability of our method by analyzing the result of synthetic test datasets with different resolution and the real-world soybean seeds test dataset. Conclusion The experimental results show that the proposed method realized the effective segmentation of individual soybean seed and the efficient calculation of the morphological parameters of each seed and it is practical to use this approach for high-throughput objects instance segmentation and high-throughput seeds phenotyping.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

High-throughput soybean seeds phenotyping with convolutional neural networks and transfer learning

Yang

Zheng

et al. 2021

Plant Methods

Self Cite

View full text Add to dashboard Cite

show abstract

“…Manual classification is time-consuming, laborious, inefficient, and prone to error, making it challenging to meet the demands of large-scale seedling production. Consequently, it is essential to investigate the automated plug seedling quality classification technology, and machine vision is a crucial component of this technology ( He et al, 2019 ; Yang et al, 2020 ; Tong et al, 2021 ). Early identification of plug seedlings using machine vision and conventional image processing techniques.…”

Section: Introductionmentioning

confidence: 99%

Classification of plug seedling quality by improved convolutional neural network with an attention mechanism

Jin

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

The classification of plug seedling quality plays an active role in enhancing the quality of seedlings. The EfficientNet-B7-CBAM model, an improved convolutional neural network (CNN) model, was proposed to improve classification efficiency and reduce high cost. To ensure that the EfficientNet-B7 model simultaneously learns crucial channel and spatial location information, the convolutional block attention module (CBAM) has been incorporated. To improve the model’s ability to generalize, a transfer learning strategy and Adam optimization algorithm were introduced. A system for image acquisition collected 8,109 images of pepper plug seedlings, and data augmentation techniques improved the resulting data set. The proposed EfficientNet-B7-CBAM model achieved an average accuracy of 97.99% on the test set, 7.32% higher than before the improvement. Under the same experimental conditions, the classification accuracy increased by 8.88–20.05% to classical network models such as AlexNet, VGG16, InceptionV3, ResNet50, and DenseNet121. The proposed method had high accuracy in the plug seedling quality classification task. It was well-adapted to numerous types of plug seedlings, providing a reference for developing a fast and accurate algorithm for plug seedling quality classification.

show abstract

“…Lin et al [22] detected the spherical or cylindrical fruits on plants in natural environments and guided harvesting robots to pick them automatically using a color-, depth-and shape-based 3D fruit detection method. Measurement using three-dimensional (3D) technology is an active area of research in agriculture [23]. It can be applied in measurements of leaf area, leaf angle, stem and shoots, fruit, and seeds [24,25].…”

Section: Introductionmentioning

confidence: 99%

High-Throughput Legume Seed Phenotyping Using a Handheld 3D Laser Scanner

2022

View full text Add to dashboard Cite

High-throughput phenotyping involves many samples and diverse trait types. For the goal of automatic measurement and batch data processing, a novel method for high-throughput legume seed phenotyping is proposed. A pipeline of automatic data acquisition and processing, including point cloud acquisition, single-seed extraction, pose normalization, three-dimensional (3D) reconstruction, and trait estimation, is proposed. First, a handheld laser scanner is used to obtain the legume seed point clouds in batches. Second, a combined segmentation method using the RANSAC method, the Euclidean segmentation method, and the dimensionality of the features is proposed to conduct single-seed extraction. Third, a coordinate rotation method based on PCA and the table normal is proposed to conduct pose normalization. Fourth, a fast symmetry-based 3D reconstruction method is built to reconstruct a 3D model of the single seed, and the Poisson surface reconstruction method is used for surface reconstruction. Finally, 34 traits, including 11 morphological traits, 11 scale factors, and 12 shape factors, are automatically calculated. A total of 2500 samples of five kinds of legume seeds are measured. Experimental results show that the average accuracies of scanning and segmentation are 99.52% and 100%, respectively. The overall average reconstruction error is 0.014 mm. The average morphological trait measurement accuracy is submillimeter, and the average relative percentage error is within 3%. The proposed method provides a feasible method of batch data acquisition and processing, which will facilitate the automation in high-throughput legume seed phenotyping.

show abstract

An Efficient Processing Approach for Colored Point Cloud-Based High-Throughput Seedling Phenotyping

Cited by 21 publications

References 50 publications

High-throughput soybean seeds phenotyping with convolutional neural networks and transfer learning

High-throughput soybean seeds phenotyping with convolutional neural networks and transfer learning

Classification of plug seedling quality by improved convolutional neural network with an attention mechanism

High-Throughput Legume Seed Phenotyping Using a Handheld 3D Laser Scanner

Contact Info

Product

Resources

About