WheatLFANet: in-field detection and counting of wheat heads with high-real-time global regression network.

BACKGROUND: 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. RESULTS: 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 R2 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). CONCLUSIONS: 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.

An Interpretable Time Series Data Prediction Framework for Severe Accidents in Nuclear Power Plants.

Accurately predicting severe accident data in nuclear power plants is of utmost importance for ensuring their safety and reliability. However, existing methods often lack interpretability, thereby limiting their utility in decision making. In this paper, we present an interpretable framework, called GRUS, for forecasting severe accident data in nuclear power plants. Our approach combines the GRU model with SHAP analysis, enabling accurate predictions and offering valuable insights into the underlying mechanisms. To begin, we preprocess the data and extract temporal features. Subsequently, we employ the GRU model to generate preliminary predictions. To enhance the interpretability of our framework, we leverage SHAP analysis to assess the contributions of different features and develop a deeper understanding of their impact on the predictions. Finally, we retrain the GRU model using the selected dataset. Through extensive experimentation utilizing breach data from MSLB accidents and LOCAs, we demonstrate the superior performance of our GRUS framework compared to the mainstream GRU, LSTM, and ARIMAX models. Our framework effectively forecasts trends in core parameters during severe accidents, thereby bolstering decision-making capabilities and enabling more effective emergency response strategies in nuclear power plants.

Corrigendum: Cotton boll localization method based on point annotation and multi-scale fusion.

[This corrects the article DOI: 10.3389/fpls.2022.960592.].

TasselLFANet: a novel lightweight multi-branch feature aggregation neural network for high-throughput image-based maize tassels detection and counting.

Accurately and rapidly counting the number of maize tassels is critical for maize breeding, management, and monitoring the growth stage of maize plants. With the advent of high-throughput phenotyping platforms and the availability of large-scale datasets, there is a pressing need to automate this task for genotype and phenotype analysis. Computer vision technology has been increasingly applied in plant science, offering a promising solution for automated monitoring of a large number of plants. However, the current state-of-the-art image algorithms are hindered by hardware limitations, which compromise the balance between algorithmic capacity, running speed, and overall performance, making it difficult to apply them in real-time sensing field environments. Thus, we propose a novel lightweight neural network, named TasselLFANet, with an efficient and powerful structure for accurately and efficiently detecting and counting maize tassels in high spatiotemporal image sequences. Our proposed approach improves the feature-learning ability of TasselLFANet by adopting a cross-stage fusion strategy that balances the variability of different layers. Additionally, TasselLFANet utilizes multiple receptive fields to capture diverse feature representations, and incorporates an innovative visual channel attention module to detect and capture features more flexibly and precisely. We conducted a series of comparative experiments on a new, highly informative dataset called MrMT, which demonstrate that TasselLFANet outperforms the latest batch of lightweight networks in terms of performance, flexibility, and adaptability, achieving an F1 measure value of 94.4%, a mAP.@5 value of 96.8%, and having only 6.0M parameters. Moreover, compared with the regression-based TasselNetV3-Seg† model, our proposed model achieves superior counting performance, with a mean absolute error (MAE) of 1.80, a root mean square error (RMSE) of 2.68, and a R2 of 0.99. The proposed model meets the accuracy and speed requirements of the vision system in maize tassel detection. Furthermore, our proposed method is reliable and unaffected by geographical changes, providing essential technical support for computerized counting in the field.

Cotton boll localization method based on point annotation and multi-scale fusion.

Cotton is an important source of fiber. The precise and intelligent management of cotton fields is the top priority of cotton production. Many intelligent management methods of cotton fields are inseparable from cotton boll localization, such as automated cotton picking, sustainable boll pest control, boll maturity analysis, and yield estimation. At present, object detection methods are widely used for crop localization. However, object detection methods require relatively expensive bounding box annotations for supervised learning, and some non-object regions are inevitably included in the annotated bounding boxes. The features of these non-object regions may cause misjudgment by the network model. Unlike bounding box annotations, point annotations are less expensive to label and the annotated points are only likely to belong to the object. Considering these advantages of point annotation, a point annotation-based multi-scale cotton boll localization method is proposed, called MCBLNet. It is mainly composed of scene encoding for feature extraction, location decoding for localization prediction and localization map fusion for multi-scale information association. To evaluate the robustness and accuracy of MCBLNet, we conduct experiments on our constructed cotton boll localization (CBL) dataset (300 in-field cotton boll images). Experimental results demonstrate that MCBLNet method improves by 49.4% average precision on CBL dataset compared with typically point-based localization state-of-the-arts. Additionally, MCBLNet method outperforms or at least comparable with common object detection methods.

A Spatio-Temporal Motion Network for Action Recognition Based on Spatial Attention.

Temporal modeling is the key for action recognition in videos, but traditional 2D CNNs do not capture temporal relationships well. 3D CNNs can achieve good performance, but are computationally intensive and not well practiced on existing devices. Based on these problems, we design a generic and effective module called spatio-temporal motion network (SMNet). SMNet maintains the complexity of 2D and reduces the computational effort of the algorithm while achieving performance comparable to 3D CNNs. SMNet contains a spatio-temporal excitation module (SE) and a motion excitation module (ME). The SE module uses group convolution to fuse temporal information to reduce the number of parameters in the network, and uses spatial attention to extract spatial information. The ME module uses the difference between adjacent frames to extract feature-level motion patterns between adjacent frames, which can effectively encode motion features and help identify actions efficiently. We use ResNet-50 as the backbone network and insert SMNet into the residual blocks to form a simple and effective action network. The experiment results on three datasets, namely Something-Something V1, Something-Something V2, and Kinetics-400, show that it out performs state-of-the-arts motion recognition networks.

A Generative Adversarial Network for Infrared and Visible Image Fusion Based on Semantic Segmentation.

This paper proposes a new generative adversarial network for infrared and visible image fusion based on semantic segmentation (SSGAN), which can consider not only the low-level features of infrared and visible images, but also the high-level semantic information. Source images can be divided into foregrounds and backgrounds by semantic masks. The generator with a dual-encoder-single-decoder framework is used to extract the feature of foregrounds and backgrounds by different encoder paths. Moreover, the discriminator's input image is designed based on semantic segmentation, which is obtained by combining the foregrounds of the infrared images with the backgrounds of the visible images. Consequently, the prominence of thermal targets in the infrared images and texture details in the visible images can be preserved in the fused images simultaneously. Qualitative and quantitative experiments on publicly available datasets demonstrate that the proposed approach can significantly outperform the state-of-the-art methods.

Cross-Weather Image Alignment via Latent Generative Model with Intensity Consistency.

Image alignment/registration/correspondence is a critical prerequisite for many vision-based tasks, and it has been widely studied in computer vision. However, aligning images from different domains, such as cross-weather/season road scenes, remains a challenging problem. Inspired by the success of classic intensity-constancy-based image alignment methods and the modern generative adversarial network (GAN) technology, we propose a cross-weather road scene alignment method called latent generative model with intensity constancy. From a novel perspective, the alignment problem is formulated as a constrained 2D flow optimization problem with latent encoding, which can be decoded into an intensity-constancy image on the latent image manifold. The manifold is parameterized by a pre-trained GAN, which is able to capture statistic characteristics from large datasets. Moreover, we employ the learned manifold to constrain the warped latent image identical to the target image, thereby producing a realistic warping effect. Experimental results on several cross-weather/season road scene datasets demonstrate that our approach can significantly outperform the state-of-the-art methods.

Nonrigid Point Set Registration With Robust Transformation Learning Under Manifold Regularization.

This paper solves the problem of nonrigid point set registration by designing a robust transformation learning scheme. The principle is to iteratively establish point correspondences and learn the nonrigid transformation between two given sets of points. In particular, the local feature descriptors are used to search the correspondences and some unknown outliers will be inevitably introduced. To precisely learn the underlying transformation from noisy correspondences, we cast the point set registration into a semisupervised learning problem, where a set of indicator variables is adopted to help distinguish outliers in a mixture model. To exploit the intrinsic structure of a point set, we constrain the transformation with manifold regularization which plays a role of prior knowledge. Moreover, the transformation is modeled in the reproducing kernel Hilbert space, and a sparsity-induced approximation is utilized to boost efficiency. We apply the proposed method to learning motion flows between image pairs of similar scenes for visual homing, which is a specific type of mobile robot navigation. Extensive experiments on several publicly available data sets reveal the superiority of the proposed method over state-of-the-art competitors, particularly in the context of the degenerated data.

Rectangular-Normalized Superpixel Entropy Index for Image Quality Assessment.

Image quality assessment (IQA) is a fundamental problem in image processing that aims to measure the objective quality of a distorted image. Traditional full-reference (FR) IQA methods use fixed-size sliding windows to obtain structure information but ignore the variable spatial configuration information. In order to better measure the multi-scale objects, we propose a novel IQA method, named RSEI, based on the perspective of the variable receptive field and information entropy. First, we find that consistence relationship exists between the information fidelity and human visual of individuals. Thus, we reproduce the human visual system (HVS) to semantically divide the image into multiple patches via rectangular-normalized superpixel segmentation. Then the weights of each image patches are adaptively calculated via their information volume. We verify the effectiveness of RSEI by applying it to data from the TID2008 database and denoise algorithms. Experiments show that RSEI outperforms some state-of-the-art IQA algorithms, including visual information fidelity (VIF) and weighted average deep image quality measure (WaDIQaM).