Field Of Intelligent Transportation Research Articles

Multi-Modal Feature Pyramid Transformer for RGB-Infrared Object Detection

RGB-Infrared multi-modal object detection utilizes diverse and complementary information, showing some advantages in intelligent transportation field. The main challenge of RGB-Infrared object detection is how to fuse the two modalities. The difficulty of fusion is reflected in two aspects: 1) large visual differences between modalities make it difficult to learn effective complementary features, 2) some misaligned RGB-Infrared images increase the difficulty of fusion. To this end, based on feature pyramid commonly used in object detection, we propose Multi-modal Feature Pyramid Transformer (MFPT) to fuse the two modalities. The proposed MFPT learns semantic and modal complementary information to enhance each modal features via intra-modal feature pyramid transformer and inter-modal feature pyramid transformer. The intra-modal feature pyramid transformer enables features to interact across space and scales, improving the semantic representations of features in each modality. The inter-modal feature pyramid transformer conducts feature interaction between modalities, enabling each modality to learn complementary features from other modalities. Meanwhile, the inter-modal feature pyramid transformer can also learn distance independent dependencies between modalities, which are not sensitive to misaligned images. Furthermore, a local attention mechanism is introduced within different windows into MFPT to achieve efficient correlation between regions of different scales or different modalities. Experimental results on two RGB-Infrared detection datasets demonstrate the proposed method is superior to state-of-the-art methods.

Deep Learning and Geometry Flow Vector Using Estimating Vehicle Cuboid Technology in a Monovision Environment.

This study introduces a novel model for accurately estimating the cuboid of a road vehicle using a monovision sensor and road geometry information. By leveraging object detection models and core vectors, the proposed model overcomes the limitations of multi-sensor setups and provides a cost-effective solution. The model demonstrates promising results in accurately estimating cuboids by utilizing the magnitudes of core vectors and considering the average ratio of distances. This research contributes to the field of intelligent transportation by offering a practical and efficient approach to 3D bounding box estimation using monovision sensors. We validated feasibility and applicability are through real-world road images captured by CCTV cameras.

3D pedestrian localization fusing via monocular camera

In the field of intelligent transportation, autonomous driving technologies, especially visual sensing solutions have attracted increasing attention in recent years. There are still some challenges in pedestrian location based on the monocular camera, as the pedestrian is a non-rigid object and its depth information cannot be obtained from the monocular camera easily and accurately. In this paper, a pedestrian location framework based on monocular cameras is proposed. The framework consists of three parts: coarse positioning, auxiliary information generation and information fusion. In the part of coarse positioning, the human skeleton information is obtained from the monocular images and a light-weight feed-forward neural network is used to predict the pedestrian position based on the skeleton information. In the part of auxiliary information generation, pseudo-LiDAR points with pedestrian depth information are generated from the monocular images through an auxiliary network. Finally, the outputs of the above two parts are fused to achieve the pedestrian location. The experimental results on KITTI dataset show that our method has achieved better performance than other methods.

Traffic Sign Detection Based on Improved YOLOv5

<p>As a popular research direction in the field of intelligent transportation, various scholars have widely concerned themselves with traffic sign detection However, there are still some key issues that need to be further solved in order to thoroughly apply related technologies to real scenarios, such as the feature extraction scheme of traffic sign images, and the optimal selection of detection methods. For the purpose of overcoming these difficulties. This paper proposes a YOLO-based traffic sign detection framework. Firstly, a lightweight convolution attention mechanism is embedded into the backbone network to obtain the information of space and channel; Secondly, the multi-scale awareness module is used to replace large convolution with 3×3 convolution superposition to improve the receptive field area of the object in the model and enhance the feature fusion performance of the model; Finally, CIoU is used as the loss function of the bounding box to locate the experimental object with high precision. The experimental results show that on the CCTSDB data set, the MAP of this method reaches 91.0%, which is 3.5% higher than the original YOLOv5. Compared with other mainstream object detection algorithms, it has a certain degree of improvement, which proves the effectiveness of this method.</p> <p> </p>

Hardware Circuit Design of Intelligent Induction Control Classified Garbage Can

This design is based on the STC89C52RC single chip microcomputer and the integration of various multi-function modules to complete the overall system control. It is composed of the core modules of humidity detection, relay drive, metal detection, intelligent alarm, MQ-2 smoke sensor, infrared sensing, ultrasonic detection, etc. We collect specific information through ultrasonic testing, and LCD1602 displays the current status; an infrared sensor and a smoke sensor are used for relevant monitoring; a humidity sensor and metal sensor automatically remind us to classify and put garbage; a relay analog control trash can automatically open and close. The system has the characteristics of ideal performance, low cost, convenient design, simple structure, and intelligence. It has found a feasible solution for the current environmental pollution problem to do garbage classification and treatment. It can play an important role in smart homes, smart campuses, intelligent transportation, telemedicine, and other fields, and will have a broader market prospect and application fields.

English

In the field of vision, applying accurate- time tracking technology in sequence images is of excellent use value to many fields, for example. It has broad prospects for development in alcohol and tobacco, passenger flow statistics, traffic surveillance, etc. In this paper, a Visual tracking simulation is carried out on corresponding detection, extraction, recognition and tracking of the moving target in an image sequence to obtain the moving parameters and trajectory. The tracked moving object performs further processing and analysis accordingly and provides a reliable database for the next more advanced task. Therefore, visual tracking plays an important role in the localization analysis of moving objects in the military, work, scientific research, intelligent transportation and other fields. The computer has undergone four development stages and made a qualitative leap from hardware to software. Stock price fluctuation represents current market trends and corporate development that can be used to determine whether to sell or acquire stocks. A stock market estimate is one of the most complex and vital duties because of the nonlinear or dynamic nature of the market. Therefore, according to the requirements of target tracking in video, a particle filter algorithm is selected to optimize the technology and is addressed for efficient outcomes through simulation. The news, blogs, sentiment analysis, and other media are connected to this relationship between supply and demand. Sentiment analysis stock market forecast focused on the stock market’s autonomous performance.

Dimensionality Reduction and Visualization in Public Management Research from the Perspective of Algorithm Recommendation

With the development of computer technology, algorithm recommendation systems have been widely used in intelligent transportation, urban planning, and other fields. Aiming at the current problems in public management in China, this paper proposes a dimensionality reduction calculation method, and uses the improved particle swarm optimization algorithm to analyze and evaluate the dimensionality reduction process. With the expectation of providing some reference value and ideas for solving practical application problems, a corresponding relationship equation is established with the minimum expected value as the objective function to solve the corresponding optimal solution, the evaluation results of system performance indicators and comprehensive scoring criteria under relevant parameters and constraints are given. The test results show that the visualization effect of the dimensionality reduction visualization model for public management research based on the algorithm recommendation perspective is over 90%.

TRD-YOLO: A Real-Time, High-Performance Small Traffic Sign Detection Algorithm.

Traffic sign detection is an important part of environment-aware technology and has great potential in the field of intelligent transportation. In recent years, deep learning has been widely used in the field of traffic sign detection, achieving excellent performance. Due to the complex traffic environment, recognizing and detecting traffic signs is still a challenging project. In this paper, a model with global feature extraction capabilities and a multi-branch lightweight detection head is proposed to increase the detection accuracy of small traffic signs. First, a global feature extraction module is proposed to enhance the ability of extracting features and capturing the correlation within the features through self-attention mechanism. Second, a new, lightweight parallel decoupled detection head is proposed to suppress redundant features and separate the output of the regression task from the classification task. Finally, we employ a series of data enhancements to enrich the context of the dataset and improve the robustness of the network. We conducted a large number of experiments to verify the effectiveness of the proposed algorithm. The accuracy of the proposed algorithm is 86.3%, the recall is 82.1%, the mAP@0.5 is 86.5% and the mAP@0.5:0.95 is 65.6% in TT100K dataset, while the number of frames transmitted per second is stable at 73, which meets the requirement of real-time detection.

English

Autonomous vehicles in public transport can perform a wide range of real-world tasks such as: moving in factories, in public transport, in search and rescue, etc., thus requiring varying degrees of auto-navigation in response to changes in the environment. This paper presents the predictive model (MPC) for the active suspension system, the vehicle's damping system, combined with Deep Q-network (DQN) algorithm reinforcement learning method applied to control self-driving cars in public transport. Intelligent traffic control system to control movement to avoid fixed obstacles or movable obstacles in the event of external interference, taking into account the comfort of the occupants of the vehicle; taking into account the load, the conveying systems; for the purpose of application in the field of intelligent transportation. The research results, built on Matlab Simulink software, show that autonomous vehicles can safely complete intelligent navigation tasks in an unknown environment and become a real system intelligent with the ability to self-study and adapt well to many different environments and various nonlinear factors.

QE-DAL: A quantum image feature extraction with dense distribution-aware learning framework for object counting and localization

Object counting and localization (OCL) was an essential problem in intelligent transportation fields. The convolutional neural network (CNN)-based models transformed the OCL problems into a regression task. However, the abundant semantic information of the crowd scenes may lead the CNN framework hard to extract adequate features in order to ensure good precision In this work, a Quantum Image Feature Extraction with Dense Distribution-Aware Learning (QE-DAL) framework was proposed to handle this problem. The crowd features were extracted by Quantum layers, which were extracted by encoding, quantum circuits and decode procedures based on the multi-scale architecture. For handling objects, the refined distance compensating operator was adopted to fuse the multi-scale architecture. To relieve the computation burden, a Gaussian distribution estimation mechanism was proposed to initiate and update the bounding sizes of the objects via a point-supervised manner. Finally, the joint loss function, which describes pixel classes, density maps and offset bounding boxes, was built for QE-DAL. The ablation experiment results demonstrated that the effectiveness of the quantum feature extraction architecture and the Gaussian distribution estimation mechanism of QE-DAL was validated to show superior performance than the other state-of-the-art framework. Moreover, the generalization of the QE-DAL was evidenced by the Cross-scene learning evaluation.

Dynamic Synthesis of Three−Point Circle Peripheral Docking Technology Pose

Research on space docking technology was first motivated by the application scenario of space station docking in the aviation field. Due to the maturity of this technology, its application field is expanding to other industries. To benefit the intelligent transportation field, this study uses space docking technology to realize combination and reconstruction between car bodies. Different spatial docking methods and structural characteristics are determined by different application scenarios. The docking of the space station is completed in the suspended state of the body in the outer space environment, which requires advanced technology, is high in hardware cost, and involves a small channel diameter. In this study, the docking of the reconstructed vehicle is completed on the ground; thus, it is low in hardware cost and involves a large channel diameter. Based on the above technical requirements, a three−point circular peripheral docking method is designed for the reconstructed vehicle. A visual positioning system is built, the mapping relationship between the camera coordinate system and the landmark coordinate system rotation matrix and translation vector is established, and the adaptive capture behavior is realized by path planning through the inverse pose solution model. Simulation experiments demonstrate that the active and passive vehicle bodies can achieve compliance capture with small collision force under the two conditions of forward collision and oblique collision, and the recovery coefficient after collision and docking is in the range of (0, 0.01). The acceleration decay process under two working conditions is measured in the crash test of a sample vehicle, which verifies the feasibility of the space reconstruction of the vehicle docking mechanism and the ability of this configuration to achieve tasks, providing a constructive idea for space docking technology with a large channel diameter.

Multiple object tracking with appearance feature prediction and similarity fusion

Object tracking is a crucial research area within the field of intelligent transportation, providing a vital foundation for anomalous behavior analysis and traffic statistics. Although pedestrian detectors have shown impressive results, leading to the advancement of detection-based tracking methods, target association in complex scenarios remains a difficult and less efficient task due to the lack of feature robustness in the presence of partial occlusions. In the proposed tracking method, we extract convolutional features on each entire object and its local blocks, segmented by the superpixel algorithm. Aiming to emphasize the global and local information respectively, the global features for each entire object are extracted from the last layer of the backbone network, while local features are derived from a specific intermediate layer of the backbone network. The association between tracked targets and detected pedestrian candidates relies on fused similarity degrees. Furthermore, we use the transformer’s self-attention mechanism to predict features for the current frame based on the information within past frames, aiming to eliminate the effects of target appearance variations. Additionally, we remove redundant background pixels in the detected rectangles of pedestrian candidates by using a background modeling algorithm. Experimental results demonstrate that the tracker proposed in this paper outperforms other trackers across five publicly available datasets, indicating its effectiveness and potential for further development.

Bl-IEA: A Bit-Level Image Encryption Algorithm for Cognitive Services in Intelligent Transportation Systems

In Intelligent Transportation Systems, images are the main data sources to be analyzed for providing intelligent and precision cognitive services. Therefore, how to protect the privacy of sensitive images in the process of information transmission has become an important research issue, especially in future no non-private data era. In this article, we design the Rearrangement-Arnold Cat Map (R-ACM) to disturb the relationship between adjacent pixels and further propose an efficient Bit-level Image Encryption Algorithm ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{B}{l}$ </tex-math></inline-formula> -IEA) based on R-ACM. Experiments show that the correlation coefficients of two adjacent pixels are 0.0022 in the horizontal direction, -0.0105 in the vertical direction, and -0.0035 in the diagonal direction respectively, which are obviously weaker than that of the original image with high correlations of adjacent pixels. What’s more, the NPCR is 0.996120172, and the UACI is 0.334613406, which indicate that <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{B}{l}$ </tex-math></inline-formula> -IEA has stronger ability to resist different attacks compared with other solutions. Especially, the lower time complexity and only one round permutation make it particularly suitable to be used in the time-limited intelligent transportation field.

Crowd abnormal event detection based on motion entropy and dual support vector data description

Abnormal event detection is a popular research direction in the field of intelligent transportation and public safety. The features that characterize abnormal events are extracted from given video sequence through computer vision technology. Then the abnormal events in the video are automatically detected through the classification model. In order to describe the motion characteristics of events more accurately, a new feature based on motion entropy is proposed in this paper. The entropy value of motion pixels in the video frame is calculated as the input feature of the classification model. Motion entropy is suitable to regard as a feature to distinguish normal events from abnormal events due to the big differences between normal and abnormal events. In addition, an abnormal event detection model based on motion entropy and dual support vector data description (ME-DSVDD) is presented to solve the problem of insufficient sample diversity. The standard data set is tested to analyze the performance of the proposed model. The experimental results show that the proposed method can effectively improve the performance of the abnormal event detection model.

An instant discovery method for companion vehicles based on incremental and parallel calculation

In the field of intelligent transportation, the instant discovery of companions has become a research hotspot. This technique can be applied to traffic management and public security governance. This study provides an incremental and distributed approach for discovering traveling companion instantly and continuously based on a data stream of automatic number plate recognition(ANPR). First, a parallelized incremental mining algorithm is designed and implemented in Spark on the basis of traffic-monitoring streaming data. Second, an adjustable data structure DF-tree is proposed that considers the characteristics of companion vehicles with the original ANPR data stream changing dynamically. On the basis of the DF-tree, the system can discover companions without reconstructing the data tree. In addition, we introduce a time decay mechanism to satisfy the spatio-temporal constraints of companion vehicles discovery. Finally, we realize the real-time discovery of companion vehicles based on large-scale ANPR data. The proposed methods are evaluated with extensive experiments on real datasets. The experimental results show that our proposed DF-tree-based approach is faster than the existing methods for companion discovery and it can detect companion vehicles groups in real time.

A memristor-based RBM circuit implementation and application in license plate image processing

License plate image processing is crucial in the field of intelligent transportation and public safety. Because of the influence of the shooting environment, imaging equipment, and other factors, the quality of the obtained license plate image is usually low, which affects the accuracy of license plate recognition. Image super-resolution reconstruction and image denoising technology not only improve image quality but also help further analysis and processing of the image. In this work, a memristive circuit of the restricted Boltzmann machine (RBM) is designed and applied in license plate image processing. The memristive circuit design mainly contains three modules: a generation module of hidden units, a reconstruction module of visible units, and a regeneration module of hidden units. The training process is transferred from software to on-chip implementation by the memristive circuit implementation. After applying license plate image super-resolution and image denoising, the effectiveness and superiority of the proposed memristive RBM circuit are verified by simulation and comparison results.

Orderly automatic real-time charging scheduling scenario strategy for electric vehicles considering renewable energy consumption

The ORTCS (Orderly Real-time Charging Scheduling) strategy for collaborative optimization of electric vehicles and renewable energy output is proposed, which is considering the flexibility of charge and discharge in the intelligent transportation field. The strategy aims to maximize the consumption of renewable energy as while as minimize the waiting time and expense of car users. An EV (electric vehicle) once entering the charging station and being connected to the power system, the organized planning of charge and discharge is evaluated based on its initial battery SOC (State of Charge), so as to obtain the real-time schedulability level from the whole charging station point of view. According to the dispatching level and the output of renewable energy in the station’s power system, the optimal plan is made for each connecting EV.

A space variable-scale scheduling method for digital vehicle-to-grid platform under distributed electric energy storage

With the widespread application of digital technology in the intelligent transportation field, the vehicle-to-grid (V2G) pattern, which utilizes electric vehicles (EVs) as the distributed storage resources of electric energy, has won increasingly more attention from authorities and decision-makers to promote the sustainable development of regenerative clean energy. This paper aims to study the interaction and integration problem between EVs and grid for the digital V2G platform, so as to support load aggregators making scheduling decisions. According to the variable-scale data analysis theory, a space–time scale space model is established to describe the demand response behavioral feature of EV users, and the lightning-Scale Transformation method (LST) is also proposed. Compared to the original unidirectional scale transformation modes, the LST is capable of adjusting the space and time observation scale collaboratively. A vehicle-to-grid scheduling method based on the lightning-Scale Transformation (V2G-LST) is put forward, in order to make scheduling plans by considering EV users’ behavioral feature and charger resource constraints. We collect the real dataset from 863 Beijing charging stations using the APIs of Amap, as well as the investigation data of the State Grid Corporation of China to verify the efficacy of our proposed method. Comparative experimental results verify that the V2G-LST could obtain the lower dispatch cost and higher EV charger usage rate than the maximum dispatchable quantity first method EVC-MDQ under both charging and discharging scenarios.

Driver identification through vehicular CAN bus data: An ensemble deep learning approach

AbstractDriver identification using in‐vehicle data is receiving considerable attention in the field of intelligent transportation owing to the advances in deep learning (DL). In order to improve accuracy and robustness of identification, this paper proposes an ensemble deep learning framework that integrates a modified one‐dimensional convolutional neural network (M 1‐D CNN) and bidirectional long short‐term memory (BLSTM) to improve the performance and robustness of driver identification using information extracted from vehicular CAN‐bus signals. The M 1‐D CNN architecture is developed by adopting inception blocks, residual connection, and global average pooling to obtain optimal deep‐feature representations of local time series. The BLSTM is used to learn the bidirectional long‐term temporal dependencies. Results of extensive experiments using real driving data show that the proposed ensemble DL model can improve the accuracy and robustness of driver identification. Furthermore, four data augmentation methods, namely up‐sampling, adding noise, data reversal, and random drifting, are used to expand the original training data to improve the performance of the ensemble method. Especially, few‐shot learning is performed using the four data augmentation methods, and it shows excellent potential for driver identification with limited data.

Driver Identification Methods in Electric Vehicles, a Review

Driver identification is very important to realizing customized service for drivers and road traffic safety for electric vehicles and has become a research hotspot in the field of modern automobile development and intelligent transportation. This paper presents a comprehensive review of driver identification methods. The basic process of driver identification task is proposed as four steps, the advantages and disadvantages of different data sources for driver identification are analyzed, driver identification models are divided into three categories, and the characteristics and research progress of driver identification models are summarized, which can provide a reference for further research on driver identification. It is concluded that on-board sensor data in the natural driving state is objective and accurate and could be the main data source for driver identification. Emerging technologies such as big data, artificial intelligence, and the internet of things have contributed to building a deep learning hybrid model with high accuracy and robustness and representing an important gradual development trend of driver identification methods. Developing a driver identification method with high accuracy, real-time performance, and robustness is an important development goal in the future.