Light guide plates are essential optical components widely used in a diverse range of applications ranging from medical lighting fixtures to back-lit TV displays. An essential step in the manufacturing of light guide plates is the quality inspection of defects such as scratches, bright/dark spots, and impurities. This is mainly done in industry through manual visual inspection for plate pattern irregularities, which is time-consuming and prone to human error and thus act as a significant barrier to high-throughput production. Advances in deep learning-driven computer vision has led to the exploration of automated visual quality inspection of light guide plates to improve inspection consistency, accuracy, and efficiency. However, given the computational constraints and high-throughput nature of real-world manufacturing environments, the widespread adoption of deep learning-driven visual inspection systems for inspecting light guide plates in real-world manufacturing environments has been greatly limited due to high computational requirements and integration challenges of existing deep learning approaches in research literature. In this work, we introduce a fully-integrated, high-throughput, high-performance deep learning-driven workflow for light guide plate surface visual quality inspection (VQI) tailored for real-world manufacturing environments. To enable automated VQI on the edge computing within the fully-integrated VQI system, a highly compact deep anti-aliased attention condenser neural network (which we name Light-DefectNet) tailored specifically for light guide plate surface defect detection in resource-constrained scenarios was created via machine-driven design exploration with computational and “best-practices” constraints as well as L1 paired classification discrepancy loss. Experiments show that Light-DetectNet achieves a detection accuracy of ∼98.2% on the LGPSDD benchmark while having just 770K parameters (∼33× and ∼6.9× lower than ResNet-50 and EfficientNet-B0, respectively) and ∼93M FLOPs (∼88× and ∼8.4× lower than ResNet-50 and EfficientNet-B0, respectively) and ∼8.8× faster inference speed than EfficientNet-B0 on an embedded ARM processor. As such, the proposed deep learning-driven workflow, integrated with the aforementioned LightDefectNet neural network, is highly suited for high-throughput, high-performance light plate surface VQI within real-world manufacturing environments.

Speed limit violation by vehicles is one of the most frequent reasons for road crashes, which take the lives of many people every year, resulting in an increasing demand for video-based vehicle speed estimation systems. One of the biggest challenges to achieve monocular video-based vehicle speed estimation is the projection displacement difference (PDD) problem, where there is a plane disparity between street-level indicators and above-plane feature points of vehicles, thus resulting in unreliable speed estimates. In this paper, a novel motion plane-based approach for vehicle speed estimation is proposed, which addresses the problem of PDD. In the proposed method, we consider the center of a vehicle license plate as the vehicle reference point and estimate the hypothetical plane (named motion plane), on which license plate moves. Subsequently, the plate position is mapped on the motion plane and the displacement is then calculated, thus mitigating the effects of PPD. To estimate the motion plane, a texture-based shape-from-template technique is used. Unlike existing methods, the proposed method needs neither to apply any indicator nor to use any information about extrinsic parameters of the camera. Furthermore, since all the license plates are approximately located on a flat plane, the motion plane can be estimated by using several extracted 3-D points. Experimental results show that the proposed method performs better than the state-of-the-art vehicle speed estimation methods, illustrating the efficacy of this approach for achieving reliable vehicle speed estimation.

Classification is an important field in machine learning and pattern recognition. Amongst various types of classifiers such as nearest neighbor, neural network and Bayesian classifiers, support vector machine (SVM) is known as a very powerful classifier. One of the advantages of SVM in comparison with the other methods, is its efficient and adjustable generalization capability. The performance of SVM classifier depends on its parameters, specially regularization parameter C, that is usually selected by cross-validation. Despite its generalization, SVM suffers from some limitations such as its considerable low speed training phase. Cross-validation is a very time consuming part of training phase, because for any candidate value of the parameter C, the entire process of training and validating must be repeated completely. In this paper, we propose a novel approach for early stopping of the SVM learning algorithm. The proposed early stopping occurs by integrating the validation part into the optimization part of the SVM training without losing any generality or degrading performance of the classifier. Moreover, this method can be considered in conjunction with the other available accelerator methods since there is not any dependency between our proposed method and the other accelerator ones, thus no redundancy will happen. Our method was tested and verified on various UCI repository datasets and the results indicate that this method speeds up the learning phase of SVM without losing any generality or affecting the final model of classifier.