Accurate lane detection is an essential function of dynamic traffic perception. Though deep learning (DL) based methods have been widely applied to lane detection tasks, such models rarely achieve sufficient accuracy in low-light weather conditions. To improve the model accuracy in foggy conditions, a new approach was proposed based on monocular depth prediction and an atmospheric scattering model to generate fog artificially. We applied our method to the existing CULane dataset collected in clear weather and generated 107,451 labeled foggy lane images under three different fog densities. The original and generated datasets were then used to train state-of-the-art (SOTA) lane detection networks. The experiments demonstrate that the synthetic dataset can significantly increase the lane detection accuracy of DL-based models in both artificially generated foggy lane images and real foggy scenes. Specifically, the lane detection model performance (F1-measure) was increased from 11.09 to 70.41 under the heaviest foggy conditions. Additionally, this data augmentation method was further applied to another dataset, VIL-100, to test the adaptability of this approach. Similarly, it was found that even when the camera position or level of brightness was changed from one dataset to another, the foggy data augmentation approach is still valid to improve model performance under foggy conditions without degrading accuracy on other weather conditions. Finally, this approach also sheds light on practical applications for other complex scenes such as nighttime and rainy days.

This paper reports an approach to interpolate planar laser-induced fluorescence (PLIF) images of CH₂O between consecutive experimental data by means of computational imaging realized with convolutional neural network (CNN). Such a deep learning based method can achieve higher temporal resolution for 2D visualization of intermediate species in combustion based on high-speed experimental images. The capability of the model was tested for generating 100 kHz PLIF images by interpolating single and multiple PLIF frames into the sequences of experimental images of lower frequencies (50, 33, 25 and 20 kHz). Results show that the prediction indices, including intersection over union (IoU), peak signal to noise ratio (PSNR), structural similarity index (SSIM), and time averaged correlation coefficient at various axial positions could achieve acceptable accuracy. This work sheds light on the utilization of CNN-based models to achieve optical flow computation and image sequence interpolation, also providing an efficient off-line model as an alternative pathway to overcome the experimental challenges of the state-of-the-art ultra-high speed PLIF techniques, e.g., to further increase repetition rate and save data transfer time.

In image-guided surgery (IGS) practice, combining intraoperative 2D X-ray images with preoperative 3D X-ray images from computed tomography (CT) enables the rapid and accurate localization of lesions, which allows for a more minimally invasive and efficient surgery, and also reduces the risk of secondary injuries to nerves and vessels. Conventional optimization-based methods for 2D X-ray and 3D CT matching are limited in speed and precision due to non-convex optimization spaces and a constrained searching range. Recently, deep learning (DL) approaches have demonstrated remarkable proficiency in solving complex nonlinear 2D–3D registration. In this paper, a fast and robust DL-based registration method is proposed that takes an intraoperative 2D X-ray image as input, compares it with the preoperative 3D CT, and outputs their relative pose in x, y, z and pitch, yaw, roll. The method employs a dual-channel Swin transformer feature extractor equipped with attention mechanisms and feature pyramid to facilitate the correlation between features of the 2D X-ray and anatomical pose of CT. Tests on three different regions of interest acquired from open-source datasets show that our method can achieve high pose estimation accuracy (mean rotation and translation error of 0.142° and 0.362 mm, respectively) in a short time (0.02 s). Robustness tests indicate that our proposed method can maintain zero registration failures across varying levels of noise. This generalizable learning-based 2D (X-ray) and 3D (CT) registration algorithm owns promising applications in surgical navigation, targeted radiotherapy, and other clinical operations, with substantial potential for enhancing the accuracy and efficiency of image-guided surgery.

Accurate automatic sleep stage classification from single-channel EEG remains challenging due to the need for effective extraction of multiscale neurophysiological features and modeling of long-range temporal dependencies. This study aims to address these limitations by developing an efficient and compact deep learning architecture tailored for wearable and edge device applications. We propose MultiScaleSleepNet, a hybrid convolutional neural network–bidirectional long short-term memory–transformer architecture that extracts multiscale temporal and spectral features through parallel convolutional branches, followed by sequential modeling using a BiLSTM memory network and transformer-based attention mechanisms. The model obtained an accuracy, macro-averaged F1 score, and kappa coefficient of 88.6%, 0.833, and 0.84 on the Sleep-EDF dataset; 85.6%, 0.811, and 0.80 on the Sleep-EDF Expanded dataset; and 84.6%, 0.745, and 0.79 on the SHHS dataset. Ablation studies indicate that attention mechanisms and spectral fusion consistently improve performance, with the most notable gains observed for stages N1, N3, and rapid eye movement. MultiScaleSleepNet demonstrates competitive performance across multiple benchmark datasets while maintaining a compact size of 1.9 million parameters, suggesting robustness to variations in dataset size and class distribution. The study supports the feasibility of real-time, accurate sleep staging from single-channel EEG using parameter-efficient deep models suitable for portable systems.