Synthetic aperture radar (SAR) plays an essential role in earth observation and projection due to its capability to penetrate clouds, which makes it possible to monitor terrestrial surfaces under all weather conditions. Multiplicative noise often occurs in the SAR signal, hampering the retrieval of information from SAR imagery. Convolutional neural networks (CNNs) have been used in many computer vision tasks and are helpful in image denoising. However, current CNN-based denoising approaches inevitably lead to a “washed out” effect that loses spatial details. Another limitation is that most typical CNN-based denoising models require a noise-free image for training. To address these issues, we propose a novel end-to-end self-supervised SAR denoising model: Enhanced Noise2Noise (EN2N), which can be trained without a noise-free image. To enhance the quality of the result images, the perceptual features from a pre-learned CNN are introduced to restore the spatial details by a hybrid loss function. Experiments show that our proposed method outperforms the typical denoising methods in terms of noise reduction and feature preservation based on image quality metrics. Also, the new hybrid loss could enhance the spatial details significantly. The good performance maintains the robustness throughout time, which reduces the uncertainty in time-series SAR caused by random noise. Benefiting from optimization of graphics processing unit (GPU) and multi-threading, the proposed method has higher computation efficiency than traditional methods. This study demonstrates the great potential of using our self-supervised deep learning approaches for SAR image denoising in the future.

Crop diseases pose a significant threat to agricultural productivity and global food security. Timely and accurate disease identification is crucial for improving crop yield and quality. While most existing deep learning-based methods focus primarily on image datasets for disease recognition, they often overlook the complementary role of textual features in enhancing visual understanding. To address this problem, we proposed a cross-modal data fusion via a vision-language model for crop disease recognition. Our approach leverages the Zhipu.ai multi-model to generate comprehensive textual descriptions of crop leaf diseases, including global description, local lesion description, and color-texture description. These descriptions are encoded into feature vectors, while an image encoder extracts image features. A cross-attention mechanism then iteratively fuses multimodal features across multiple layers, and a classification prediction module generates classification probabilities. Extensive experiments on the Soybean Disease, AI Challenge 2018, and PlantVillage datasets demonstrate that our method outperforms state-of-the-art image-only approaches with higher accuracy and fewer parameters. Specifically, with only 1.14M model parameters, our model achieves a 98.74%, 87.64% and 99.08% recognition accuracy on the three datasets, respectively. The results highlight the effectiveness of cross-modal learning in leveraging both visual and textual cues for precise and efficient disease recognition, offering a scalable solution for crop disease recognition.

In the article titled “Embedded YOLO: A Real-Time Object Detector for Small Intelligent Trajectory Cars” [1], Dr. Jiali Liu has been added to the author list, who contributed to programming, experiment, and performance evaluation. With the agreement of all authors, the corrected author list is shown above.

The purpose of this work is to create an efficient optimization framework for demand-responsive feeder transit services to assign vehicles to cover all pickup locations to transport passengers to a rail station. The proposed methodology features passengers placing a personalized travel order involving the subway schedule chosen by passengers and windows of service time, etc. Moreover, synchronous transfer between the shuttle and feeder bus is fully accounted for in the problem. A mixed-integer linear programming model is formulated to minimize the total travel time for all passengers, which consists of ride-time for vehicles from the pickup locations to the rail station and wait-time for passengers taking the subway beforehand. Different from conventional methods, the proposed model benefits from using a real distribution of passenger demand aggregated from cellular data and travel time or the distance matrix obtained from an open GIS tool. A distributed genetic algorithm is further designed to obtain meta-optimal solutions in a reasonable amount of time. When applied to design a feeder bus system in Nanjing City, China, case study results reveal that the total travel time of the proposed model was reduced by 2.46% compared to the traditional model. Sensitivity analyses were also further performed to investigate the impact of the number of vehicles on the output. Finally, the difference in results of Cplex, standard GA, and the proposed algorithm were compared to prove the validity of the algorithm.

Visibility is a measure of the transparency of the atmosphere, which is an important factor for road, air, and water transportation safety. Recently, features extracted from convolutional neural networks (CNNs) have obtained state-of-the-art results for the estimation of the visibility range for images of foggy weather. However, existing CNN-based approaches have only adopted visible images as observational data. Unlike these previous studies, in this paper, visible–infrared image pairs are used to estimate the visibility range. A novel multimodal deep fusion architecture based on a CNN is then proposed to learn the robust joint features of the two sensor modalities. Our network architecture is composed of two integrated residual network processing streams and one CNN stream, which are connected in parallel. In addition, we construct a visible–infrared multimodal dataset for various fog densities and label the visibility range. We then compare our proposed method with conventional deep-learning-based approaches and analyze the contributions of various observational and classical deep fusion models to the classification of the visibility range. The experimental results demonstrate that both accuracy and robustness can be strongly enhanced using the proposed method, especially for small training datasets.