Efficient Real-Time Object Detection based on Convolutional Neural Network

Shehab, Mohanad Abd; Al-Gizi, Ammar; Swadi, Salah M.

doi:10.1109/icate49685.2021.9465015

Cited by 6 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hyperparameter optimization is applied to determine the optimal values of hyperparmaters such as optimal learning rate and the number of epoch in order to improve precision and accuracy [29]- [32]. Figure 1 shows neural network-based parking system real-time license plate detection with YOLO.…”

Section: Real-time Neural Network Object Detection With Hyperparamete...mentioning

confidence: 99%

“…YOLOv5 which is based on PyTorch framework provides real-time object detection with high accuracy and speed [6], [7]. As shown in Figure 1 neural network-based parking system real-time license plate detection with YOLO is based on PyTorch framework provides real-time object detection with higher accuracy and speed [5], [7], [29]- [32]. YOLO takes the in a single instance by the framework and divides it into a grid with each grid having a dimension of n by n. Then places bounding box in the residual blocks and then determines the intersection over union (IOU).…”

Section: Real-time Neural Network Object Detection With Hyperparamete...mentioning

confidence: 99%

See 1 more Smart Citation

Neural network-based parking system object detection and predictive modeling

Khatib

Mnaouer²,

Moussa³

et al. 2023

IJ-AI

View full text Add to dashboard Cite

<span lang="EN-US">A neural network-based parking system with real-time license plate detection and vacant space detection using hyper parameter optimization is presented. When number of epochs increased from 30, 50 to 80 and learning rate tuned to 0.001, the validation loss improved to 0.017 and training object loss improved to 0.040. The model mean average precision mAP_0.5 is improved to 0.988 and the precision is improved to 99%. The proposed neural network-based parking system also uses a regularization technique for effective predictive modeling. The proposed modified lasso ridge elastic (LRE) regularization technique provides a 5.21 root mean square error (RMSE) and an R-square of 0.71 with a 4.22 mean absolute error (MAE) indicative of higher accuracy performance compared to other regularization regression models. The advantage of the proposed modified LRE is that it enables effective regularization via modified penalty with the feature selection characteristics of both lasso and ridge.</span>

show abstract

Section: Real-time Neural Network Object Detection With Hyperparamete...mentioning

confidence: 99%