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

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

doi:10.1109/tits.2020.2967316

Cited by 24 publications

(14 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Havel started to suffer from gradient dispersion issues when convolutional neural networks used the ReLU activation function. When the input voltage of the ReLU function is less than 0, truncation occurs, so the weight difference still disappears [19].…”

Section: Methodsmentioning

confidence: 99%

Intelligent Detection of Vehicle Driving Safety Based on Deep Learning

Wang¹

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

With the continuous increase in the number of cars, traffic safety problems are also becoming more and more serious, whether the driver wears a seat belt to protect the driver’s personal safety so that the problem can be solved in the event of a traffic accident. The author puts forward the research status of deep learning and convolutional neural network, as well as its theory and technology, and conducts in-depth analysis and research, a small target detection algorithm Deconv-SSD based on transposed convolution is proposed, driver area localization algorithm Squeeze-YOLO is based on lightweight model, and driver seat belt detection algorithm is based on semantic segmentation. Deconv-SSD achieves fast vehicle detection through depthwise separable convolution and fusion of multiresolution feature maps and then utilizes the salient features of the front windshield; through the method of lightweight feature extraction and the Squeeze-YOLO algorithm, the rapid positioning of the driver area is realized. Fast segmentation of seat belts is based on semantic segmentation algorithm and pruning technology in the positioning area, and by judging the maximum connected domain area after segmentation, the driver’s seat belt detection is realized. Experiments and data analysis are carried out on the proposed algorithm. When the image resolution is consistent with the feature extraction model, the average accuracy of Deconv-SSD is compared with the original SSD algorithm in the PASCALVOC public dataset, from 77.2% to 79.6%. In the self-made seat belt detection dataset, Squeeze-YOLO can reach 73 FPS when the average accuracy is 99.96%, the semantic segmentation algorithm accelerated by pruning achieves an accuracy of 94.87% at a speed of 305 FPS, and the validity of the experiment is verified.

show abstract

Section: Methodsmentioning

confidence: 99%

Intelligent Detection of Vehicle Driving Safety Based on Deep Learning

Wang¹

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Previous state-of-the-art studies often miss these details [1,2], for example, the hardware and software (HW / SW), the programming language, or the dependencies required by text spotting methods. When working in industrial projects that require real-time performance, these aspects are essential for effective and successful application of any method [19]. Due to the relevance of aspects such as machine time or production costs in industrial applications, it is necessary to optimise the HW/SW to carry out a particular task.…”

Section: Introductionmentioning

confidence: 99%

A survey on methods, datasets and implementations for scene text spotting

Blanco‐Medina

Fidalgo

Alegre

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

Text Spotting is the union of the tasks of detection and transcription of the text that is present in images. Due to the various problems often found when retrieving text, such as orientation, aspect ratio, vertical text or multiple languages in the same image, this can be a challenging task. In this paper, the most recent methods and publications in this field are analysed and compared. Apart from presenting features already seen in other surveys, such as their architectures and performance on different datasets, novel perspectives for comparison are also included, such as the hardware, software, backbone architectures, main problems to solve, or programming languages of the algorithms. The review highlights information often omitted in other studies, providing a better understanding of the current state of research in Text Spotting, from 2016 to 2022, current problems and future trends, as well as establishing a baseline for future methods development, comparison of results and serving as guideline for choosing the most appropriate method to solve a particular problem.

show abstract

“…Image recognition is the main method of this technology. One group of researchers used the camera to catch image information and a computer to execute an image recognition algorithm [14]. Optics sensors are key, but they are costly.…”

Section: Introductionmentioning

confidence: 99%

Estimation of Tire Mileage and Wear Using Measurement Data

et al. 2021

View full text Add to dashboard Cite

Tire mileage and wear provide important information for vehicle applications. There are more and more studies discussing intelligent tires, but few focus on the role of tire mileage and wear. The conventional tire pressure monitoring system (TPMS) is one of the intelligent tire applications, but there has been no significant advancement in recent years in this regard. In order to increase the additional functions of intelligent tire applications, we propose a method that estimates the mileage and wear information of tires. The proposed method uses a three-axis sensor and a Hall sensor to implement the function. The proposed method also has a low power design to reduce the power consumption of the Hall sensor. The experimental results show the trend of tire wear status, rendering this method effective. This method also requires more accurate mileage information to support tire wear estimation. This experiment found that the correct rate of the proposed mileage estimation method is 99.4% and provides sufficient and correct mileage information for tire wear methods. If this method is used in autonomous vehicle applications, the autonomous control strategy algorithm has more conditions to plan the control strategy. The strategy system processes more meticulous control that increases the safety of autonomous vehicles.

show abstract

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

Cited by 24 publications

References 19 publications

Intelligent Detection of Vehicle Driving Safety Based on Deep Learning

Intelligent Detection of Vehicle Driving Safety Based on Deep Learning

A survey on methods, datasets and implementations for scene text spotting

Estimation of Tire Mileage and Wear Using Measurement Data

Contact Info

Product

Resources

About