A Novel Memory and Time-Efficient ALPR System Based on YOLOv5

Batra, Piyush; Hussain, Imran; Ahad, Mohd Abdul; Casalino, Gabriella; Alam, M. Afshar; Khalique, Aqeel; Hassan, Syed Imtiyaz

doi:10.3390/s22145283

Cited by 13 publications

(3 citation statements)

References 45 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…YOLO-v5 combines these techniques and is now one of the best-performing models in object detection. Especially in small object detection, YOLO-v5 demonstrates desirable applicability and accuracy 16 , 17 . The detection of cracks in WTBs also belongs to the field of small object detection, so in this research paper, the intelligent detection of cracks in WTBs is undertaken based on YOLO-v5.…”

Section: Algorithm Improvementmentioning

confidence: 99%

Wind turbine blades surface crack-detection algorithm based on improved YOLO-v5 model

Yan

Liu

Wei³

et al. 2023

J. Electron. Imag.

View full text Add to dashboard Cite

.The integrity of the blade surface is an essential guarantee for the safe operation of wind turbines. It is crucial to research damage detection of blade surface cracks. Based on the improved YOLOv5 model, D-YOLO-v5 is proposed by improving the loss function, objective classification function, and activation function, extending the application of image processing, artificial intelligence, and pattern recognition to investigate intelligent recognition of cracks on the surface of blades. The blade cracks object detection test was completed by LabelImg image annotation, D-YOLO-v5 training parameters adjustment, test parameters selection, prediction model construction, model training, and model prediction steps. The recognition of cracks under different conditions, such as normal light, dark light, and external interference, is subsequently completed. The values indicated that the object detection model parameters of D-YOLO-v5 were neither over-fitted nor under-fitted. In this case study, the accuracy of the blade surface crack-detection model is 98.62%, the mean average precision value is 49.12%, the recall value is 92.20%, and the recognition speed of a single image is 0.01 s. The simulation concludes that the proposed method can meet the accuracy and real-time requirements of practical engineering.

show abstract

Section: Algorithm Improvementmentioning

confidence: 99%

Wind turbine blades surface crack-detection algorithm based on improved YOLO-v5 model

Yan

Liu

Wei³

et al. 2023

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

“…Also, areas of further improvement of some of the selected CNN-based techniques were suggested. There are several studies that use YOLOv5 5,6 for license plate detection [14][15][16][17][18][19][20] and LPRNet 7 or other OCR techniques 21 for license plate recognition. For example, a recent study published in 2022 proposes a solution for LPR and vehicle re-identification for surveillance systems.…”

Section: Related Workmentioning

confidence: 99%

Simultaneous license plate recognition and face detection application at the edge

Alim

Kavakli

Okcu

et al. 2023

AI and Optical Data Sciences IV

View full text Add to dashboard Cite

Face recognition (FR) and license plate recognition (LPR) are very crucial algorithms for identification of humans and vehicles in several applications such as surveillance, traffic and access-control. The advances in small singleboard computers with high parallel processing power capabilities and the use of low-power Neural Processing Units (NPU) inside embedded System on Chips (SoC), enable real-time face detection (FD) and LPR at the edge. On the other hand, it is still a challenge to run multiple algorithms concurrently with high accuracy and prompt execution (high frame rates) that requires a very efficient software/video analytics algorithm development. Both FR and LPR algorithms need two-stage processing that involve detection and recognition. In this study, we propose a method that enables simultaneous face detection associated with landmark and quality information and LPR at the edge. The FD pipeline detects and tracks the faces, extracts landmarks and quality of faces, to select appropriate faces for recognition and then sends them to face recognition server. LPR algorithm consecutively performs detection and recognition on the embedded platform. Extended YOLO model is utilized for face selection while pruned YOLO and LPRNet models are exploited for license plate detection and license plate reading, respectively. In order to enable real-time performance with high accuracy; optimized AI-models and software architecture are used. As a result of this study, we obtain a high-performance, high-precision and real-time combined face/LPR recognition system which can be very useful for surveillance and security applications.

show abstract

“…El cumplimiento de los objetivos del proyecto se medirá a través del cumplimiento de los indicadores de éxito mostrados en la Tabla 3. Por último, Batra et al (2022) presentan un sistema de reconocimiento automático de matrículas que optimizan el tiempo y memoria mediante el uso de YOLOv5. Su propuesta consta de dos etapas: la detección de matrículas de vehículos mediante el uso de un modelo personalizado con transferencia de conocimiento y la segunda basada en LSTM.…”

Section: Indicadores De éXitounclassified

Sistema de identificación de vehículos estacionados con sobretiempo en zonas comerciales en un distrito de Lima utilizando Yolov5 y OCR

Medina Olano,

Quispe Orellana

View full text Add to dashboard Cite

Las municipalidades del departamento de Lima han implementado estacionamientos vehiculares en áreas comerciales, ofreciendo a los ciudadanos la posibilidad de utilizarlos de forma gratuita durante períodos que varían de dos (02) a tres (03) horas, dependiendo del distrito en cuestión. Esta iniciativa conlleva la necesidad de que las municipalidades cuenten con los recursos humanos y financieros adecuados para supervisar y administrar estos espacios de estacionamiento. Como resultado, en algunos distritos, la viabilidad económica de esta medida se ve comprometida. Este estudio presenta la implementación de un sistema de información diseñado para automatizar la detección de vehículos estacionados durante periodos prolongados en zonas comerciales de un distrito en Lima. Para alcanzar este objetivo, se emplea una combinación eficaz de la tecnología YOLOv5 y el reconocimiento óptico de caracteres (OCR). Este sistema no solo contribuye a la optimización de costos para la entidad, generando una tasa de recuperación de 2.1 por cada sol invertido en un periodo de 4 años, sino que también se respalda en una arquitectura validada por un especialista en Sistemas y TIC. Dicha arquitectura coloca a la alta disponibilidad y seguridad de la información como pilares fundamentales del proyecto. Por último, el sistema logra una notable precisión del 91.43% en el reconocimiento de matrículas de vehículos en comparación con las matrículas reales.

show abstract

A Novel Memory and Time-Efficient ALPR System Based on YOLOv5

Cited by 13 publications

References 45 publications

Wind turbine blades surface crack-detection algorithm based on improved YOLO-v5 model

Wind turbine blades surface crack-detection algorithm based on improved YOLO-v5 model

Simultaneous license plate recognition and face detection application at the edge

Sistema de identificación de vehículos estacionados con sobretiempo en zonas comerciales en un distrito de Lima utilizando Yolov5 y OCR

Contact Info

Product

Resources

About