China has a vast number of roads. With years of use and damage from severe weather and natural disasters, the service life of China’s roads is gradually being shortened. As a result, various road diseases, such as potholes, peeling, cracks, and more, will appear on the road surface. During the collection of road disease datasets, some exceptional cases are inevitable. For example, in low-illumination conditions or highly dark scenes, the visibility of the surrounding environment is very low, significantly reducing the image acquisition quality. Secondly, when the vehicle-mounted camera passes over uneven ground during the shooting process, the vehicle will experience severe jolts, causing the camera to shake irregularly. When the vehicle speed is unstable, the object motion will cause motion blur due to defocusing, which seriously degrades image quality and hurts subsequent advanced visual tasks such as object detection based on road dataset images. Hence, this study embraces a Retinex-based image optimization approach explicitly tailored to enhance the clarity of low-light, blurred road imagery. It has broad practical application prospects for road disease detection in low-illumination blurred environments.
This paper investigates the problem of long-term forecasting of time series. Previous Transformer-based models use various self-attention mechanisms to find remote dependencies. Autoformer designs a novel decomposition architecture with autocorrelation mechanisms. However, their models are less effective in dealing with long time series. In this paper, we propose a new time series forecasting model, Self-Transformers, based on Non-stationary Transformers. Designed to handle time series data with complex nonlinear trends and seasonality, our model improves forecasting performance and reduces the need for manual feature engineering. We validate the effectiveness of the model by conducting experiments on several benchmark datasets, and the results show that our model achieves significant performance gains on time series forecasting tasks.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.