Wheat Ear Recognition Based on RetinaNet and Transfer Learning

Li, Jingbo; Li, Changchun; Fei, Shuaipeng; Ma, C.; Weinan, Chen; Ding, Fan; Wang, Yilin; Li, Yacong; Shi, Jinjin; Xiao, Zhen

doi:10.3390/s21144845

Cited by 49 publications

(25 citation statements)

References 52 publications

(96 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mAP50 values were 91.32, 86.10, and 76.32%, respectively. Li et al (2021) also investigated the GWHD dataset. They trained RetinaNet models using migration learning.…”

Section: Introductionmentioning

confidence: 99%

Wheat Spike Detection and Counting in the Field Based on SpikeRetinaNet

Cheng

Chen

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

The number of wheat spikes per unit area is one of the most important agronomic traits associated with wheat yield. However, quick and accurate detection for the counting of wheat spikes faces persistent challenges due to the complexity of wheat field conditions. This work has trained a RetinaNet (SpikeRetinaNet) based on several optimizations to detect and count wheat spikes efficiently. This RetinaNet consists of several improvements. First, a weighted bidirectional feature pyramid network (BiFPN) was introduced into the feature pyramid network (FPN) of RetinaNet, which could fuse multiscale features to recognize wheat spikes in different varieties and complicated environments. Then, to detect objects more efficiently, focal loss and attention modules were added. Finally, soft non-maximum suppression (Soft-NMS) was used to solve the occlusion problem. Based on these improvements, the new network detector was created and tested on the Global Wheat Head Detection (GWHD) dataset supplemented with wheat-wheatgrass spike detection (WSD) images. The WSD images were supplemented with new varieties of wheat, which makes the mixed dataset richer in species. The method of this study achieved 0.9262 for mAP50, which improved by 5.59, 49.06, 2.79, 1.35, and 7.26% compared to the state-of-the-art RetinaNet, single-shot multiBox detector (SSD), You Only Look Once version3 (Yolov3), You Only Look Once version4 (Yolov4), and faster region-based convolutional neural network (Faster-RCNN), respectively. In addition, the counting accuracy reached 0.9288, which was improved from other methods as well. Our implementation code and partial validation data are available at https://github.com/wujians122/The-Wheat-Spikes-Detecting-and-Counting.

show abstract

“…The mAP50 values were 91.32, 86.10, and 76.32%, respectively. Li et al (2021) also investigated the GWHD dataset. They trained RetinaNet models using migration learning.…”

Section: Introductionmentioning

confidence: 99%

Wheat Spike Detection and Counting in the Field Based on SpikeRetinaNet

Cheng

Chen

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“… Pound et al (2017) used the deep learning method to calculate the number of wheat spikes through the images of wheat spikes taken under greenhouse conditions. Hasan et al (2018) and Li et al (2021) use the R-CNN method to detect, count, and analyze wheat spikes, which has high recognition accuracy, but the detection speed is slow and cannot be deployed in real-time detection equipment. Compared with the above methods, our proposed method has a faster detection speed while improving accuracy than the two-stage target detection method.…”

Section: Introductionmentioning

confidence: 99%

Detection method of wheat spike improved YOLOv5s based on the attention mechanism

Zang

Wang²,

Ru³

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

In wheat breeding, spike number is a key indicator for evaluating wheat yield, and the timely and accurate acquisition of wheat spike number is of great practical significance for yield prediction. In actual production; the method of using an artificial field survey to count wheat spikes is time-consuming and labor-intensive. Therefore, this paper proposes a method based on YOLOv5s with an improved attention mechanism, which can accurately detect the number of small-scale wheat spikes and better solve the problems of occlusion and cross-overlapping of the wheat spikes. This method introduces an efficient channel attention module (ECA) in the C3 module of the backbone structure of the YOLOv5s network model; at the same time, the global attention mechanism module (GAM) is inserted between the neck structure and the head structure; the attention mechanism can be more Effectively extract feature information and suppress useless information. The result shows that the accuracy of the improved YOLOv5s model reached 71.61% in the task of wheat spike number, which was 4.95% higher than that of the standard YOLOv5s model and had higher counting accuracy. The improved YOLOv5s and YOLOv5m have similar parameters, while RMSE and MEA are reduced by 7.62 and 6.47, respectively, and the performance is better than YOLOv5l. Therefore, the improved YOLOv5s method improves its applicability in complex field environments and provides a technical reference for the automatic identification of wheat spike numbers and yield estimation. Labeled images, source code, and trained models are available at: https://github.com/228384274/improved-yolov5.

show abstract

“…Traditional counting methods rely on field surveys, sampling, and weighing, which is inefficient and time-consuming. It is difficult to use these methods to accurately estimate the yield on a large area, which severely limits their application in seed screening and breeding, pest control, density estimation, gene trait expression, and field management ( Li et al, 2021 ). Due to these reasons, the application of deep learning techniques in detection of wheat spike has received much attention in recent years.…”

Section: Introductionmentioning

confidence: 99%

Lightweight and efficient neural network with SPSA attention for wheat ear detection

Dong

Liu

Kang

et al. 2022

PeerJ Computer Science

View full text Add to dashboard Cite

Advancements in deep neural networks have made remarkable leap-forwards in crop detection. However, the detection of wheat ears is an important yet challenging task due to the complex background, dense targets, and overlaps between wheat ears. Currently, many detectors have made significant progress in improving detection accuracy. However, some of them are not able to make a good balance between computational cost and precision to meet the needs of deployment in real world. To address these issues, a lightweight and efficient wheat ear detector with Shuffle Polarized Self-Attention (SPSA) is proposed in this paper. Specifically, we first utilize a lightweight backbone network with asymmetric convolution for effective feature extraction. Next, SPSA attention is given to adaptively select focused positions and produce a more discriminative representation of the features. This strategy introduces polarized self-attention to spatial dimension and channel dimension and adopts Shuffle Units to combine those two types of attention mechanisms effectively. Finally, the TanhExp activation function is adopted to accelerate the inference speed and reduce the training time, and CIOU loss is used as the border regression loss function to enhance the detection ability of occlusion and overlaps between targets. Experimental results on the Global Wheat Head Detection dataset show that our method achieves superior detection performance compared with other state-of-the-art approaches.

show abstract

Wheat Ear Recognition Based on RetinaNet and Transfer Learning

Cited by 49 publications

References 52 publications

Wheat Spike Detection and Counting in the Field Based on SpikeRetinaNet

Wheat Spike Detection and Counting in the Field Based on SpikeRetinaNet

Detection method of wheat spike improved YOLOv5s based on the attention mechanism

Lightweight and efficient neural network with SPSA attention for wheat ear detection

Contact Info

Product

Resources

About