License plate segmentation and recognition system using deep learning and OpenVINO

Castro-Zunti, Riel; Yépez, Juan; Ko, Seok‐Bum

doi:10.1049/iet-its.2019.0481

Cited by 42 publications

(17 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…YOLO [12] was deployed in [2], [13], but these works maximize accuracy leveraging on high complexity models (>10 GMAC) and making use of powerful GPUs for the inference task. To target embedded implementations, [3] uses SSD [7] coupled to a custom lightweight CNN architecture (∼3M parameters). Likewise, we start from an SSD object detector featuring a MobilenetV2 backbone for LP detection and we optimize it for the deployment on the target system.…”

Section: Related Workmentioning

confidence: 99%

“…Likewise, we start from an SSD object detector featuring a MobilenetV2 backbone for LP detection and we optimize it for the deployment on the target system. Concerning the character recognition task, segmentation-based methods make use of object detectors to detect individual characters [2], [3]. This approach is prone to errors since a single character miss-detection leads to a wrong recognition [14].…”

Section: Related Workmentioning

confidence: 99%

“…To improve performance, NN accelerators can be used. Castro-Zunti et al [3] exploits an Intel Neural Compute Stick 2 (NCS2) to perform LP detection and recognition, processing 300 × 300 images in real-time at 15 FPS. Still, the power required by the NSC2 ranges between 1.5 W and 2 W. To reduce the power consumption, Kendryte K210 exploits a hardwired NN accelerator, but when integrated into a general-purpose AI vision system, e.g.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Low-Power License Plate Detection and Recognition on a RISC-V Multi-Core MCU-Based Vision System

Lamberti

Rusci

Fariselli

et al. 2021

2021 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

In this paper, we present the first (to the best of our knowledge) demonstration of a low-power MCU-based edge device for Automatic License Plate Recognition (ALPR). The design leverages on a 9-core RISC-V processor, GAP8, coupled with a QVGA ultra-low-power greyscale imager. The proposed visual processing pipeline uses a multi-model inference approach based on SSDlite-MobilenetV2 for license plate detection and LPRNet for optical character recognition, reaching a 38.9% mAP score for the first task and a recognition rate of >99.13% for the latter on public datasets. On real-world data, the pipeline recognizes registration numbers when the size of LP crops is as small as 30×5 pixels. Thanks to the applied compression and optimization strategies, the multi-model inference (687 MMAC) achieves a throughput of 1.09 FPS at a power cost of 117 mW when running on GAP8. Our solution is the first MCU-class device embedding such a level of network complexity, resulting to be 73× more energy-efficient w.r.t. precedent mobile-class ALPR system featuring a Raspberry Pi3. The proposed design does not resort to any hardwired acceleration engines, thus retaining full flexibility for future algorithmic improvements.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Low-Power License Plate Detection and Recognition on a RISC-V Multi-Core MCU-Based Vision System

Lamberti

Rusci

Fariselli

et al. 2021

2021 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

show abstract

“…With the advancement of object detection, a character-based workflow that was considered impossible in the past has become a reality. Modified SSD and mask R-CNN were used for character recognition in [53,54], respectively. Since they paid little attention to the license plate standard format, it is hard to achieve multinational license plate recognition based on recognised characters.…”

Section: Most Relevant Workmentioning

confidence: 99%

EDF‐LPR: a new encoder–decoder framework for license plate recognition

Gao

Cai

et al. 2020

IET Intelligent Transport Systems

View full text Add to dashboard Cite

“…The aim of this work is to optimize the kilometer post detection method, so as to improve the assisted positioning technology based on kilometer posts. In recent years, deep learning has achieved good application results in many research fields [18,19], especially for license plate and road sign detection and recognition in the field of autonomous driving [20,21]. At present, the deep learning algorithms that are commonly used in object detection can be divided into two categories-region-and regression-based detection algorithms.…”

Section: Introductionmentioning

confidence: 99%

The Assisted Positioning Technology for High Speed Train Based on Deep Learning

Song

Wen

2020

Applied Sciences

View full text Add to dashboard Cite

In the positioning process of a high-speed train, cumulative error may result in a reduction in the positioning accuracy. The assisted positioning technology based on kilometer posts can be used as an effective method to correct the cumulative error. However, the traditional detection method of kilometer posts is time-consuming and complex, which greatly affects the correction efficiency. Therefore, in this paper, a kilometer post detection model based on deep learning is proposed. Firstly, the Deep Convolutional Generative Adversarial Networks (DCGAN) algorithm is introduced to construct an effective kilometer post data set. This greatly reduces the cost of real data acquisition and provides a prerequisite for the construction of the detection model. Then, by using the existing optimization as a reference and further simplifying the design of the Single Shot multibox Detector (SSD) model according to the specific application scenario of this paper, the kilometer post detection model based on an improved SSD algorithm is established. Finally, from the analysis of the experimental results, we know that the detection model established in this paper ensures both detection accuracy and efficiency. The accuracy of our model reached 98.92%, while the detection time was only 35.43 ms. Thus, our model realizes the rapid and accurate detection of kilometer posts and improves the assisted positioning technology based on kilometer posts by optimizing the detection method.

show abstract

License plate segmentation and recognition system using deep learning and OpenVINO

Cited by 42 publications

References 23 publications

Low-Power License Plate Detection and Recognition on a RISC-V Multi-Core MCU-Based Vision System

Low-Power License Plate Detection and Recognition on a RISC-V Multi-Core MCU-Based Vision System

EDF‐LPR: a new encoder–decoder framework for license plate recognition

The Assisted Positioning Technology for High Speed Train Based on Deep Learning

Contact Info

Product

Resources

About