YOLO Based Recognition Method for Automatic License Plate Recognition

Riaz, Waqar; Azeem, Abdullah; Gao, Chenqiang; Zhou, Yiming; Saifullah, -; Khalid, Waqas

doi:10.1109/aeeca49918.2020.9213506

Cited by 19 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Video prediction is one of the possible ways of learning from unlabeled data [11][12][13]. For this reason, most current advanced models [14][15][16] extract the optical flow from contiguous video frames, and then use LSTM (Long Short-Term Memory networks), RNN (Recurrent Neural Networks) or feedforward networks to ingest sequences [17][18][19][20]. Regarding pre-processed optical flow, it is observed that it provides no motion information for models.…”

Section: Introductionmentioning

confidence: 99%

Traffic Anomaly Prediction System Using Predictive Network

et al. 2022

View full text Add to dashboard Cite

Anomaly anticipation in traffic scenarios is one of the primary challenges in action recognition. It is believed that greater accuracy can be obtained by the use of semantic details and motion information along with the input frames. Most state-of-the art models extract semantic details and pre-defined optical flow from RGB frames and combine them using deep neural networks. Many previous models failed to extract motion information from pre-processed optical flow. Our study shows that optical flow provides better detection of objects in video streaming, which is an essential feature in further accident prediction. Additional to this issue, we propose a model that utilizes the recurrent neural network which instantaneously propagates predictive coding errors across layers and time steps. By assessing over time the representations from the pre-trained action recognition model from a given video, the use of pre-processed optical flows as input is redundant. Based on the final predictive score, we show the effectiveness of our proposed model on three different types of anomaly classes as Speeding Vehicle, Vehicle Accident, and Close Merging Vehicle from the state-of-the-art KITTI, D2City and HTA datasets.

show abstract

Section: Introductionmentioning

confidence: 99%

Traffic Anomaly Prediction System Using Predictive Network

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Penelitian (Yolo-v et al 2020) mengimplementasikan pendeteksian ANPR menggunakan Algoritme YOLO v3 dapat disimpulkan bahwa pendeteksian ANPR pada plat nomor kendaraan secara real time mengg unakan algoritme YOLO v3 berhasil dan jika terdapat pengendara yang melakukan pelanggaran pada lampu lalu lintas maka sistem tersebut dapat memberikan peringatan kepada petugas terdekat. Penelitian (Riaz et al 2020) terkait teknologi ANPR dan OCR untuk mendeteksi beberapa plat nomor kendaraan pada citra mobil menunjukkan bahwa pendeteksian plat nomor kendaraan pada citra yang memiliki resolusi rendah berhasil dengan algoritme YOLO v3 dan YOLO v4. Algoritme YOLO v4 memiliki nilai mAP yang lebih tinggi serta proses pendeteksian yang lebih cepat dibandingkan dengan algoritme YOLO v3.…”

Section: Pendahuluanunclassified

YOLO V5 for Vehicle Plate Detection in DKI Jakarta

Reezky Illmawati,

Hustinawati

2023

JIKA

View full text Add to dashboard Cite

The odd-even rule on vehicle number plates in DKI Jakarta aims to reduce congestion that occurs in DKI Jakarta. The application of these regulations is constrained by the limitations of the manual supervision function by officers. This problem can be overcome by implementing intelligence in the form of detecting number plate objects with the YOLO v5 algorithm and the character extraction process with Optical Character Recognition technology using Tesseract OCR. Object detection technology will detect objects in the form of vehicle plates. The OCR method can extract the characters on the number plate, the extraction results can be processed into parameter categorization so that the program can distinguish between vehicles that violate the rules and do not violate the rules automatically and more effectively and minimize errors. Based on this research, the average percentage of objects detected in each video is 92.38%, and the average confidence value obtained in object detection is between 75.55%. The success rate of the character extraction process on number plates is 95.45%, and the average proportion according to the detected number plate category is 97.2%. The implementation of the YOLO Algorithm has succeeded in detecting license plates with odd and even categories on videos that can provide signs and save violations of vehicles that violate the odd and even rules.

show abstract

“…Extensive experimental testing validates the effectiveness and efficiency of their approach in real-world working environments. In another related work [18], authors experienced the use of temporal redundancy in license plate detection. The results of their method reached an overall recognition rate of 86% and achieved an outstanding accuracy of 99% for four-letter plates.…”

Section: Temporal Redundancymentioning

confidence: 99%

Improving License Plate Identification in Morocco: Intelligent Region Segmentation Approach, Multi-Font and Multi-Condition Training

Laoula¹,

Midaoui²,

Youssfi³

et al. 2023

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

The exponential growth in the number of automobiles over the past few decades has created a pressing need for a robust license plate identification system that can perform effectively under various conditions. In Morocco, as in other regions, local authorities, public organizations, and private companies require a reliable License Plate Recognition (LPR) system that takes into account all plates specifications (HWP, VWP, DP, YP, and WWP) and multiple fonts used. This research paper introduces an intelligent LPR system implemented using the Yolov5 and Detectron2 frameworks, which have been trained on a customized dataset comprising multiple fonts (such as CRE, HSRP, FE-S, etc.) and accounting for different circumstances such as illumination, climate, and lighting conditions. The proposed model incorporates an intelligent region segmentation approach that adapts to the plate's type, thereby enhancing recognition accuracy and overcoming conventional issues related to plate separators. With the use of image preprocessing and temporal redundancy optimization, the model achieves a precision of 97,181% when handling problematic plates, including those with specific illumination patterns, separators, degradations, and other challenges, with little advantage to Yolov5 over Detecton2.

show abstract

YOLO Based Recognition Method for Automatic License Plate Recognition

Cited by 19 publications

References 12 publications

Traffic Anomaly Prediction System Using Predictive Network

Traffic Anomaly Prediction System Using Predictive Network

YOLO V5 for Vehicle Plate Detection in DKI Jakarta

Improving License Plate Identification in Morocco: Intelligent Region Segmentation Approach, Multi-Font and Multi-Condition Training

Contact Info

Product

Resources

About