MobileNet‐SSD MicroScope using adaptive error correction algorithm: real‐time detection of license plates on mobile devices

Hu, Xun; Li, Hong; Li, Xinrong; Wang, Chiyu

doi:10.1049/iet-its.2019.0380

Cited by 15 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The market size of the power meter device was 10.4 billion US dollars to 2020 and itt increased to 11.8 billion US dollars in 2022. SSD is an object detector device which uses grid cell to detect objects in a particular region of an image [9]. Detecting objects represent the class and location prediction of an object through a particular region.…”

Section: Resultsmentioning

confidence: 99%

Anomaly Diagnosis Method and Condition Assessment of Power Metering Device Based on SSD Algorithm

Jiang,

Wang,

Wang

et al. 2023

SCPE

View full text Add to dashboard Cite

The advancement of anomaly diagnosis methods plays a crucial role in classifying and analyzing data, particularly in distinguishing between normal and abnormal patterns. This study explores the utilization of Support Vector Machine (SVM) techniques to facilitate the selection of pertinent data, thus enhancing the accuracy of anomaly detection. Furthermore, this research delves into the condition assessment process, which offers valuable insights into the real-time state of entities passing through power metering devices. Drawing upon a wealth of secondary data sources, this study employs the SSD algorithm to gain a comprehensive understanding of power metering devices and their interrelated aspects. The SSD algorithm, with its diverse anchor points, is revealed as a powerful tool for quantifying the energy flow passing through the power metering device. This approach not only aids in precise energy measurement but also provides essential insights into the functioning of power metering systems. By combining anomaly diagnosis, SVM techniques, and the SSD algorithm, this study contributes to a deeper comprehension of power metering devices' performance and their capacity to accurately measure energy. These insights have significant implications for improving the overall reliability and efficiency of power metering in various applications.

show abstract

Section: Resultsmentioning

confidence: 99%

Anomaly Diagnosis Method and Condition Assessment of Power Metering Device Based on SSD Algorithm

Jiang,

Wang,

Wang

et al. 2023

SCPE

View full text Add to dashboard Cite

show abstract

“…Facing the problem of blurred underwater images, we designed two sets of target recognition simulation experiments in this paper. The two sets of simulation experiments were conventional underwater images and blurred images, and the compared algorithms were CRSNet [36], DMNet [37], Improved RetinaNet [38], and MobileNet-SSD [39]. The algorithms were evaluated in terms of recognition accuracy (mAP) and recognition time.…”

Section: Methodsmentioning

confidence: 99%

EHDC: enhanced dilated convolution framework for underwater blurred target recognition

Cai

Qin

2022

Robotica

View full text Add to dashboard Cite

The autonomous underwater vehicle (AUV) has a problem with feature loss when recognizing small targets underwater. At present, algorithms usually use multi-scale feature extraction to solve the problem, but this method increases the computational effort of the algorithm. In addition, low underwater light and turbid water result in incomplete information on target features. This paper proposes an enhanced dilated convolution framework (EHDC) for underwater blurred target recognition. Firstly, this paper extracts small target features through hybrid dilated convolution networks, increasing the perceptive field of the algorithm without increasing the computational power of the algorithm. Secondly, the proposed algorithm learns spatial semantic features through an adaptive correlation matrix and compensates for the missing features of the target. Finally, this paper fuses spatial semantic features and visual features for the recognition of small underwater blurred targets. Experiments show that the proposed method improves the recognition accuracy by 1.04% compared to existing methods when recognizing small underwater blurred targets.

show abstract

“…Finally, the 1 × 1 convolution is used again to squeeze the network, so that the input image can be matched with the initial number of channels [36]. The batch normalization [37] and ReLU6 [37,38] are added following each convolution block to reduce the training process of deep neural networks and generalization error [39]. ReLU6 activation is used to discard nonlinear.…”

Section: Ssd-mobilenet-v2mentioning

confidence: 99%

Study on Tracking Real-Time Target Human Using Deep Learning for High Accuracy

Nguyen,

Chu

2023

Journal of Robotics

View full text Add to dashboard Cite

Speed and accuracy are important parts of the human tracking system. To design a system that tracks the target human working well in real time, as well as on mobile devices, a tracking real-time target human system is proposed. First, real-time human detection is performed by the combination of MobileNet-v2 and single-shot multibox detector (SSD). Subsequently, the particle filter algorithm is applied to track the target human. The proposed system is evaluated with the different color shirts and complex background conditions. In addition, the system also works with the support of a depth Kinect-v2 camera to evaluate performance. The experiment result indicates that the proposed system is efficient without the impact of colors, background, and light. Moreover, the system still tracks the human when the human has disappeared or the size of the target has a significant change, and an FPS of 12 (Kinect-v2 camera) and 22 (conventional camera) ensures the system works well in real time.

show abstract

MobileNet‐SSD MicroScope using adaptive error correction algorithm: real‐time detection of license plates on mobile devices

Cited by 15 publications

References 23 publications

Anomaly Diagnosis Method and Condition Assessment of Power Metering Device Based on SSD Algorithm

Anomaly Diagnosis Method and Condition Assessment of Power Metering Device Based on SSD Algorithm

EHDC: enhanced dilated convolution framework for underwater blurred target recognition

Study on Tracking Real-Time Target Human Using Deep Learning for High Accuracy

Contact Info

Product

Resources

About