Search

Images captured in rainy weather conditions often suffer from contamination, resulting in blurred or obscured objects, which can significantly impact detection performance due to the loss of identifiable texture and color information. Moreover, the quality of the detection model plays a pivotal role in determining detection outcomes. This study adopts a dual perspective, considering both pre-trained models and training data. It employs 15 image augmentation techniques, combined with neural style transfer (NST), CycleGAN, and an analytical method, to synthesize images under rainy conditions. The Real-Time Detection Transformer (RTDETR) and YOLOv8 pre-trained models are utilized to establish object detection frameworks tailored for rainy weather conditions. Testing is carried out using the DAWN (Detection in Adverse Weather Nature) dataset. The findings suggest compatibility between the pre-trained detection models and various data synthesis methods. Notably, YOLOv8 exhibits better compatibility with CycleGAN data synthesis, while RTDETR demonstrates a stronger alignment with the NST and analytical approaches. Upon the integration of synthesized rainy images into model training, RTDETR demonstrates significantly enhanced detection accuracy compared to YOLOv8, indicating a more pronounced improvement in performance. The proposed approach of combining RTDETR with NST in this study shows a significant improvement in Recall (R) and mAP50-95 by 16.35% and 15.50%, respectively, demonstrating the robust rainy weather resilience of this method. Additionally, RTDETR outperforms YOLOv8 in terms of inference speed and hardware requirements, making it easier to use and deploy in real-time applications.

Latent Low-Rank Representation (LatLRR) has emerged as a prominent approach for fusing visible and infrared images. In this approach, images are decomposed into three fundamental components: the base part, salient part, and sparse part. The aim is to blend the base and salient features to reconstruct images accurately. However, existing methods often focus more on combining the base and salient parts, neglecting the importance of the sparse component, whereas we advocate for the comprehensive inclusion of all three parts generated from LatLRR image decomposition into the image fusion process, a novel proposition introduced in this study. Moreover, the effective integration of Convolutional Neural Network (CNN) technology with LatLRR remains challenging, particularly after the inclusion of sparse parts. This study utilizes fusion strategies involving weighted average, summation, VGG19, and ResNet50 in various combinations to analyze the fusion performance following the introduction of sparse parts. The research findings show a significant enhancement in fusion performance achieved through the inclusion of sparse parts in the fusion process. The suggested fusion strategy involves employing deep learning techniques for fusing both base parts and sparse parts while utilizing a summation strategy for the fusion of salient parts. The findings improve the performance of LatLRR-based methods and offer valuable insights for enhancement, leading to advancements in the field of image fusion.

BACKGROUND After the soil sample is extracted by organic acid, there are a lot of organic acids and organic matter in the solution. If these remaining materials are not destroyed, the central tube and rectangular tube of the atomizer are easily plugged after they have entered the inductively coupled plasma-optical emission spectrometry (ICP-OES) sampling system. Particles absorbed in the central tube wall and rectangular tube wall will result in poor analytical precision and accuracy, and further affect comprehensive evaluation of soil availability. OBJECTIVES To make the determination of available state in soil sample more stable and accurate, reduce the detection limit of the method, and prevent the sample from contamination and volatilization loss in the pretreatment. METHODS Soil samples were extracted with organic acids (DTPA, oxalic acid-ammonium oxalate, citric acid, etc.), filtered or centrifuged, and the supernatant was absorbed into a high-pressure sealed digestion tank. The supernatant was treated by an electric heating plate and then added with 2mL concentrated nitric acid. The soil samples were heated for at least 3 hours in an oven at 180℃. The effective element contents of copper, zinc, iron, manganese, cadmium, lead, nickel, chromium, molybdenum and silicon were determined by ICP-OES. RESULTS The relative standard deviations in this method were 2.5%-9.8%, the relative errors were -2.1%-5.2%, the recoveries were 90.1%-103.2%, and the detection limits were 0.32μg/kg-0.038mg/kg. Using the method of burning in the high temperature furnace and the open digestion by nitric acid-perchloric acid (sulfuric acid), the recoveries were 89.2%-100.5%, and the detection limits were 0.50μg/kg-0.050mg/kg. CONCLUSIONS The method has stable measurement results, low blank and a short analysis period, and is especially suitable for continuous analysis of batch samples.