FasteNet: A Fast Railway Fastener Detector

TL;DR

FasteNet is a high-speed, fully convolutional neural network designed for fastener detection in railway images, achieving real-time performance and high accuracy by directly predicting saliency maps without bounding boxes.

Contribution

The paper introduces FasteNet, a novel saliency map-based detection method that operates at 110 FPS and improves fastener detection accuracy in railway images.

Findings

Runs at 110 FPS on Nvidia GTX 1080

Capable of detecting an average of 14 fasteners per image

Achieves high confidence detection without bounding boxes

Abstract

In this work, a novel high-speed railway fastener detector is introduced. This fully convolutional network, dubbed FasteNet, foregoes the notion of bounding boxes and performs detection directly on a predicted saliency map. Fastenet uses transposed convolutions and skip connections, the effective receptive field of the network is 1.5$\times$ larger than the average size of a fastener, enabling the network to make predictions with high confidence, without sacrificing output resolution. In addition, due to the saliency map approach, the network is able to vote for the presence of a fastener up to 30 times per fastener, boosting prediction accuracy. Fastenet is capable of running at 110 FPS on an Nvidia GTX 1080, while taking in inputs of 1600$\times$512 with an average of 14 fasteners per image. Our source is open here: https://github.com/jjshoots/DL\_FasteNet.git