Vehicle tire (tyre) detection and text recognition using deep learning

Kazmi, Wajahat; Nabney, Ian T.; Vogiatzis, George; Rose, Peter; Codd, Alexander

doi:10.1109/coase.2019.8842962

Cited by 5 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The system requires the vehicles to be moving under 10 mph, which is suitable for installation at gas stations, parking lots and entry/exit points of motorway toll booths. This is an extension and thorough testing of our earlier work [12]. As an extension, we introduce a fully CNN based proposal generator using low level features (HOG-CNN) and compare it with HOG-MLP from our previous work as well as a well known off-the-shelf proposal generator, the Edge Box [13].…”

Section: Introductionmentioning

confidence: 98%

An Efficient Industrial System for Vehicle Tyre (Tire) Detection and Text Recognition Using Deep Learning

Kazmi

Nabney

Vogiatzis

et al. 2021

IEEE Trans. Intell. Transport. Syst.

Self Cite

View full text Add to dashboard Cite

This paper addresses the challenge of reading low contrast text on tyre sidewall images of vehicles in motion. It presents first of its kind, a full scale industrial system which can read tyre codes when installed along driveways such as at gas stations or parking lots with vehicles driving under 10 mph. Tyre circularity is first detected using a circular Hough transform with dynamic radius detection. The detected tyre arches are then unwarped into rectangular patches. A cascade of convolutional neural network (CNN) classifiers is then applied for text recognition. Firstly, a novel proposal generator for the code localization is introduced by integrating convolutional layers producing HOG-like (Histogram of Oriented Gradients) features into a CNN. The proposals are then filtered using a deep network. After the code is localized, character detection and recognition are carried out using two separate deep CNNs. The results (accuracy, repeatability and efficiency) are impressive and show promise for the intended application.

show abstract

Section: Introductionmentioning

confidence: 98%

An Efficient Industrial System for Vehicle Tyre (Tire) Detection and Text Recognition Using Deep Learning

Kazmi

Nabney

Vogiatzis

et al. 2021

IEEE Trans. Intell. Transport. Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

A Fast Vision-Based Algorithm for Automated Container Pose Measurement System

Zhang,

2024

Lecture Notes in Mechanical Engineering

View full text Add to dashboard Cite

Addressing the current issues of low accuracy in container positioning and posture recognition, as well as long response times during the port automation loading and unloading process, this paper designs a rapid container target recognition and measurement device and method for automated loading and unloading, thereby optimizing the acquisition of key parameters in automated loading and unloading operations. This method combines advanced convolutional neural networks and traditional image processing algorithms to achieve precise detection and tracking of container corner fittings. Furthermore, this paper proposes a high-speed response method for small target measurement, which integrates minimized deep learning network technology and fuzzy image morphology matching algorithms to enhance the accuracy and stability of corner fitting detection. Through experimental verification, this method effectively improves the speed of single detection and reduces the localization error of small targets.

show abstract