Railway Obstacle Detection Using Segmented DNN Image Blocks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing railway monitoring systems struggle to rapidly and accurately determine the presence of obstacles on railways, particularly in mountainous areas prone to disasters like rockfalls and landslides, due to the inefficiency of processing entire railway images.
Innovation Solution
A railway disaster monitoring system using a deep learning neural network to process segmented image blocks of railway images, employing a first and second discriminator to verify the presence of foreign matters and differentiate between normal and abnormal states, with additional verification for train passages.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the entire railway image is processed to detect obstacles, then the detection accuracy is improved, but the processing time increases and productivity decreases
Solution Approach 1:
The patent divides the railway image into multiple segmented image blocks and processes them independently through the deep neural network. This segmentation approach reduces the computational burden on each processing unit while maintaining comprehensive coverage of the entire railway scene, thereby improving processing speed without sacrificing detection accuracy
2Measurement precision
If the entire railway image is processed to detect obstacles, then the detection accuracy is improved, but the computational resources required increase
Solution Approach 1:
By segmenting the railway image into multiple smaller blocks and processing them independently, the patent reduces the computational complexity and memory requirements for each processing operation. This approach maintains detection accuracy while significantly reducing the overall computational resource consumption
Solution Approach 2:
The patent processes only the necessary segmented portions of the image through the deep neural network rather than analyzing the entire image at once. This partial processing approach reduces computational resource consumption while still achieving accurate obstacle detection through the systematic analysis of segmented blocks
3Productivity
If segmented image blocks are used for processing, then the processing speed is improved, but the device complexity increases
Solution Approach 1:
The patent implements segmentation of the railway image into multiple blocks, which enables faster parallel processing. While this increases system complexity, the modular nature of the segmentation approach allows for systematic implementation and management of the additional complexity through structured data organization and processing pipelines
Data Source
AI summary
Disclosed is a technique for a railway disaster monitoring system for monitoring a foreign matter on a railway, which includes a camera and an image processing unit that receives a railway image captured by the camera. The image processing unit includes a segmented image acquisition unit that obtains a plurality of segmented images including a rail from the railway image received from the camera and scales the segmented images to obtain segmented image blocks of a predetermined size, and a segmented image determination unit which includes deep neural network (DNN) discriminators trained with deep learning neural networks and inputs the segmented image blocks to the DNN discriminators to determine whether the railway is in a normal state in which there is no foreign matter on the railway except a train passing by. Using the segmented images, a foreign matter on a railway can be rapidly and easily determined using a deep learning neural network even with a small number of resources.