Abstract
Trains shuttle in semiopen environments, and the surrounding environment plays an important role in the safety of train operation. The weather is one of the factors that affect the surrounding environment of railways. Under haze conditions, railway monitoring and staff vision could be blurred, threatening railway safety. This paper tackles image dehazing for railways. The contributions of this paper for railway video image dehazing are as follows: (1) this paper proposes an end-to-end residual block-based haze removal method that consists of two subnetworks, namely fine-grained and coarse-grained network can directly generate the clean image from input hazy image, called RID-Net (Railway Image Dehazing Network). (2) The combined loss function (per-pixel loss and perceptual loss functions) is proposed to achieve both low-level features and high-level features so to generate the high-quality restored images. (3) We take the full-reference criterion (PSNR&SSIM), object detection, running time, and sensory vision to evaluate the proposed dehazing method. Experimental results on railway synthesized dataset, benchmark indoor dataset, and real-world dataset demonstrate our method has superior performance compared to the state-of-the-art methods.
Highlights
With rapid development of rail transit around the world, the safety of the rail transportation is the essential issue
In order to improve the generalization of the algorithm, the Outdoor Training Set (OTS) of RESIDI [44] is leveraged to be our training set and validation set, the feature of OTS is as RESIDI [44] is leveraged to be our training set and validation set, the feature of OTS is as similar as railway images
The end-to-end residual block-based novel deep learning method was presented for railway image dehazing to enhance the safety of train running
Summary
With rapid development of rail transit around the world, the safety of the rail transportation is the essential issue. In recent years, there have been incidents affecting the running of trains, such as stone on the rails, landslides next to the rails, non-staff entering the railway areas These railway incidents happened on good days, and the driver used emergency braking immediately, reducing economic losses. Some prior-based image dehazing algorithms [5,6,7,8] are prone to distortion, false color, perimeter, and can assist the drivers to predictenvironments, the situation of and railway by on-board and poor generalization, especially in outdoor theenvironment inference speed of most of them monitoring. The overall criterion, object detection performance, running time, and sensory vision to evaluate the proposed scheme of haze removal for railway images using residual CNNs (Convolutional Neural Networks) is dehazing method.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
