Parking Space Detection and Path Planning Based on VIDAR

The existing automatic parking algorithms often neglect the unknown obstacles in the parking environment, which causes a hidden danger to the safety of the automatic parking system. Therefore, this paper proposes parking space detection and path planning based on the VIDAR method (vision-IMU-based detection and range method) to solve the problem. In the parking space detection stage, the generalized obstacles are detected based on VIDAR to determine the obstacle areas, and then parking lines are detected by the Hough transform to determine the empty parking space. Compared with the parking detection method based on YOLO v5, the experimental results demonstrate that the proposed method has higher accuracy in complex parking environments with unknown obstacles. In the path planning stage, the path optimization algorithm of the A ∗ algorithm combined with the Bezier curve is used to generate smooth curves, and the environmental information is updated in real time based on VIDAR. The simulation results show that the method can make the vehicle efficiently avoid the obstacles and generate a smooth path in a dynamic parking environment, which can well meet the safety and stationarity of the parking requirements.

New Results on Small and Dim Infrared Target Detection

Real-time small infrared (IR) target detection is critical to the performance of the situational awareness system in high-altitude aircraft. However, current IR target detection systems are generally hardware-unfriendly and have difficulty in achieving a robust performance in datasets with clouds occupying a large proportion of the image background. In this paper, we present new results by using an efficient method that extracts the candidate targets in the pre-processing stage and fuses the local scale, blob-based contrast map and gradient map in the detection stage. We also developed mid-wave infrared (MWIR) and long-wave infrared (LWIR) cameras for data collection experiments and algorithm evaluations. Experimental results using both publicly available datasets and image sequences acquired by our cameras clearly demonstrated that the proposed method achieves high detection accuracy with the mean AUC being at least 22.3% higher than comparable methods, and the computational cost beating the other methods by a large margin.

Truck Driver Fatigue Detection Based on Video Sequences in Open-Pit Mines

Due to complex background interference and weak space–time connection, traditional driver fatigue detection methods perform poorly for open-pit truck drivers. For these issues, this paper presents a driver fatigue detection method based on Libfacedetection and an LRCN. The method consists of three stages: (1) using a face detection module with a tracking method to quickly extract the ROI of the face; (2) extracting and coding the features; (3) combining the coding model to build a spatiotemporal classification network. The innovation of the method is to utilize the spatiotemporal features of the image sequence to build a spatiotemporal classification model suitable for this task. Meanwhile, a tracking method is added to the face detection stage to reduce time expenditure. As a result, the average speed with the tracking method for face detection on video is increased by 74% in comparison with the one without the tracking method. Our best model adopts a DHLSTM and feature-level frame aggregation, which achieves high accuracy of 99.30% on the self-built dataset.

Improved Automatic License Plate Recognition in Jordan Based on Ceiling Analysis

The main challenge of automatic license plate recognition (ALPR) systems is that the overall performance is highly dependent upon the results of each component in the system’s pipeline. This paper proposes an improved ALPR system for the Jordanian license plates. Ceiling analysis is carried out to identify potential enhancements in each processing stage of a previously reported ALPR system. Based on the obtained ceiling analysis results, several enhancements are then suggested to improve the overall performance of the system under study. These improvements are (i) vertical-edge histogram analysis and size estimation of the candidate regions in the detection stage and (ii) de-rotation of the misaligned license plate images in the segmentation unit. These enhancements have resulted in significant improvements in the overall system performance despite a <1% increase in the execution time. The performance of the developed ALPR is assessed experimentally using a dataset of 500 images for parked and moving vehicles. The obtained results are found to be superior to those reported in equivalent systems, with a plate detection accuracy of 94.4%, character segmentation accuracy of 91.9%, and character recognition accuracy of 91.5%.

A Deep Learning Model of Dual-Stage License Plate Recognition Applicable to the Data Processing Industry

Automatic License Plate Recognition (ALPR) is a widely used technology. However, due to the influence of complex environmental factors, recognition accuracy and speed of license plate recognition have been challenged and expected. Aiming to construct a sufficiently robust license plate recognition model, this study adopted multitask learning in the license plate detection stage, used the convolutional neural networks of single-stage detection, RetinaFace, and MobileNet, as approaches to license plate location, and completed the license plate sampling through the calculation of license plate skew correction. In the license plate character recognition stage, the Convolutional Recurrent Neural Network (CRNN) integrated with the loss function of the CTC model was employed as a segmentation-free and highly robust method of license plate character recognition. In this study, after the license plate recognition model, DLPR, trained the PVLP dataset of vehicle images provided by company A in Taiwan’s data processing industry, it performed tests on the PVLP dataset, indicating that its precision was 98.60%, recognition accuracy was 97.56%, and recognition speed was FPS > 21. In addition, according to the tests on the public AOLP dataset of Taiwan’s vehicles, its recognition accuracy was 97.70% and recognition speed was FPS > 62. Therefore, not only can the DLPR model be applied to the license plate recognition of real-time image streams in the future, but also it can assist the data processing industry in enhancing the accuracy of license plate recognition in photos of traffic violations and the performance of traffic service operations.

A Novel Metric-Learning-Based Method for Multi-Instance Textureless Objects’ 6D Pose Estimation

6D pose estimation of objects is essential for intelligent manufacturing. Current methods mainly place emphasis on the single object’s pose estimation, which limit its use in real-world applications. In this paper, we propose a multi-instance framework of 6D pose estimation for textureless objects in an industrial environment. We use a two-stage pipeline for this purpose. In the detection stage, EfficientDet is used to detect target instances from the image. In the pose estimation stage, the cropped images are first interpolated into a fixed size, then fed into a pseudo-siamese graph matching network to calculate dense point correspondences. A modified circle loss is defined to measure the differences of positive and negative correspondences. Experiments on the antenna support demonstrate the effectiveness and advantages of our proposed method.

Graphene Quantum Dots and Cu(I) Liquid Crystal for Advanced Electrochemical Detection of Doxorubicine in Aqueous Solutions

Two paste electrodes based on graphene quantum dots and carbon nanotubes (GRQD/CNT) and one modified with a homoleptic liquid crystalline Cu(I) based coordination complex (Cu/GRQD/CNT) were obtained and morphostructurally and electrochemically characterized in comparison with simple CNT electrode (CNT) for doxorubicine (DOX) detection in aqueous solutions. GRQD/CNT showed the best electroanalytical performance by differential pulse voltammetry technique (DPV). Moreover, applying a preconcentration step prior to detection stage, the lowest limit of detection (1 ng/L) and the highest sensitivity (216,105 µA/mgL−1) in comparison with reported literature data were obtained. Cu/GRQD/CNT showed good results using multiple pulse amperometry technique (MPA) and a favorable shifting of the potential detection to mitigate potential interferences. Both GRQD-based paste electrodes have a great potential for practical utility in DOX determination in water at trace concentration levels, using GRQD/CNT with DPV and in pharmaceuticals formulations using Cu/GRQD/CNT with MPA.

Multi-camera object tracking system

The article proposes a multi-camera tracking system for an object, implemented using computer vision technologies and allowing the video surveillance operator in real time to select an object that will be monitored by the system in future. It will be ready to give out the location of the object at any time. The solution to this problem is divided into three main stages: the detection stage, the tracking stage and the stage of interaction of several cameras. Methods of detection, tracking of objects and the interaction of several cameras have been investigated. To solve the problem of detection, the method of optical flow and the method of removing the background were investigated, to solve the problem of tracking — the method of matching key points and the correlation method, to solve the problem of interaction between several surveillance cameras — the method of the topological graph of a network of cameras. An approach is proposed for constructing a system that uses a combination of the background removal method, the correlation method and the method of the topological graph of a network of cameras. The stages of detection and tracking have been experimentally implemented, that is, the task of tracking an object within the coverage area of one video camera has been solved. The implemented system showed good results: a sufficiently high speed and accuracy with rare losses of the tracked object and with a slight decrease in the frame rate.

A Hybrid Two-Stage CNN-SVM Model for Bone X-Rays Classification and Abnormality Detection

This paper introduces a novel automatic reliable hybrid two-stage method for bone x-rays abnormality detection. For this purpose, 10 different pre-trained convolutional neural networks architectures with different number of layers are examined. The introduced method considers the seven extremity upper bones, namely shoulder, humerus, forearm, elbow, wrist, hand, and finger. The enhanced images are fed into the first stage to classify the bone type into one of the seven bones. Thereafter, the abnormality is detected in the second stage using a specific classifier according to the bone type. Thus, the classification step consists of eight different classifiers: one for the bone classification stage and seven for the abnormality detection stage. Finally, support vector machine layer is examined as a last layer of the classification in the second stage. The best average sensitivity and specificity achieved by the first stage are 95.78% and 99.45%, and 83.25% and 83.25% for the second stage, respectively. All the experiments were carried out using MURA dataset.