Figure - available from: Remote Sensing
This content is subject to copyright.
Source publication
Vehicle behavior recognition is an attractive research field which is useful for many computer vision and intelligent traffic analysis tasks. This paper presents an all-in-one behavior recognition framework for moving vehicles based on the latest deep learning techniques. Unlike traditional traffic analysis methods which rely on low-resolution vide...
Similar publications
This contribution discusses the potential of UAV-assisted (unmanned aerial vehicles)
photogrammetry for the study and preservation of mining heritage sites using the example of Roman
gold mining infrastructure in northwestern Spain. The study area represents the largest gold area in
Roman times and comprises 7 mining elements of interest that chara...
Counting livestock is generally done only during major events, such as drenching, shearing or loading, and thus farmers get stock numbers sporadically throughout the year.More accurate and timely stock information would enable farmers to manage their herds better. Additionally, prompt response to any stock in distress is extremely valuable, both in...
This paper gathers the design and implementation of the control system that allows an unmanned Flying-wing to perform a Vertical Take-Off and Landing (VTOL) maneuver using two tilting rotors (Bi-Rotor). Unmanned Aerial Vehicles (UAVs) operating in this configuration are also categorized as Hybrid UAVs due to their ability of having a dual flight en...
This paper proposed the developed of a fixed wings model RC plane. It is an Unmanned Aerial Vehicle
(UAV).The proposed design is capable to fly a drone easily because of strong modeling it can fly using a runway.
In recent research, drones are designed for hand throwing or flying with external pressure. And for flight control
maximum user get NAZA...
![Figure 1. Ultrastick 25e UAV platform [11]](profile/Saban-Ulus/publication/330307408/figure/fig1/AS:713791159402496@1547192482108/Ultrastick-25e-UAV-platform-11_Q320.jpg)
Unmanned aerial vehicles (UAV) are taking more attention in both civilian and army applications in the world. One of the most important thing in UAV applications is to make an autonomous, fast and stable control of a UAV. In this study, one of the fixed wing UAV model (Ultrastick-25e) is analyzed and aerodynamic parameter coefficients of the UAV mo...
Citations
... The cell state updates the cell states from the forget gate, output gate, and input gate. The output gate decides the next hidden state [33,34]. ...
Simple Summary
Research on proteins and their interactions with other proteins yields many new findings that help explain how diseases emerge. However, manual curation of scientific literature delays new discoveries in the field. Artificial intelligence and deep learning techniques have played a significant part in information extraction from textual forms. In this study, we used text mining and artificial intelligence techniques to address the issue of extracting protein–protein interaction networks from the vast amount of scientific research literature. We have created an automated system consisting of three models using deep learning and natural language processing methods. The accuracy of our first model, which employs recurrent neural networks using sentiment analysis, was 95%. Additionally, the accuracy of our second model, which employs the named entity recognition technique in NLP, was effective and achieved an accuracy of 98%. In comparison to the protein interaction network, we discovered by manual curation of more than 30 articles on Autism Spectrum Disorder, that the automated system testing on 6027 abstracts was successful in developing the network of interactions and provided an improved view. Discovering these networks will greatly help physicians and scientists understand how these molecules interact for physiological, pharmacological, and pathological insight.
Abstract
Text mining methods are being developed to assimilate the volume of biomedical textual materials that are continually expanding. Understanding protein–protein interaction (PPI) deficits would assist in explaining the genesis of diseases. In this study, we designed an automated system to extract PPIs from the biomedical literature that uses a deep learning sentence classification model, a pretrained word embedding, and a BiLSTM recurrent neural network with additional layers, a conditional random field (CRF) named entity recognition (NER) model, and shortest-dependency path (SDP) model using the SpaCy library in Python. The automated system ensures that it targets sentences that contain PPIs and not just these proteins mentioned in the framework of disease discovery or other context. Our first model achieved 13% greater precision on the Aimed/BioInfr benchmark corpus than the previous state-of-the-art BiLSTM neural network models. The NER model presented in this study achieved 98% precision on the Aimed/BioInfr corpus over previous models. In order to facilitate the production of an accurate representation of the PPI network, the processes were developed to systematically map the protein interactions in the texts. Overall, evaluating our system through the use of 6027 abstracts pertaining to seven proteins associated with Autism Spectrum Disorder completed the manually curated PPI network for these proteins. When it comes to complicated diseases, these networks would assist in understanding how PPI deficits contribute to disease development while also emphasizing the influence of interactions on protein function and biological processes.
... In order to avoid similar problems, LSTM as a specific RNN network model can solve the problem of a long-term dependence on historical information, so that based on directional selection and reasonable inheritance of current and historical information, it can complete information identification at the current time [33] and feature extraction [34] and information prediction at the next time [35] by comprehensively considering the role of historical input information. The main research content of this paper is based on the vehicle dynamic state information such as lateral acceleration, yaw rate, and tire force in the optimized time-domain length, and the LSTM network is adopted to extract the data features under the input state and predict the calculation to obtain the future sideslip angle of the center of mass. ...
The controller design of vehicle systems depends on accurate reference index input. Considering information fusion and feature extraction based on existing data settings in the time domain, if reasonable input is selected for prediction to obtain accurate information of future state, it is of great significance for control decision-making, system response, and driver’s active intervention. In this paper, the nonlinear dynamic model of the four-wheel steering vehicle system was built, and the Long Short-Term Memory (LSTM) network architecture was established. On this basis, according to the real-time data under different working conditions, the information correction calculation of variable time-domain length was carried out to obtain the real-time state input length. At the same time, the historical state data of coupled road information was adopted to train the LSTM network offline, and the acquired real-time data state satisfying the accuracy was used as the LSTM network input to carry out online prediction of future confidence information. In order to solve the problem of mixed sensitivity of the system, a robust controller for vehicle active steering was designed with the sideslip angle of the centroid of 0, and the predicted results were used as reference inputs for corresponding numerical calculation verification. Finally, according to the calculated results, the robust controller with information prediction can realize the system stability control under coupling conditions on the premise of knowing the vehicle state information in advance, which provides an effective reference for controller response and driver active manipulation.
... b) Approaches based on the deep learning method: Vehicle tracking methods based on deep learning can easily obtain the vehicle trajectory and then analyze vehicle behavior through these trajectories [199], [200]. Wang et al. [201] employed the TrackletNet tracker (TNT) [202] to extract the trajectory of anomalous vehicles and estimate the start time of abnormal behavior, e.g., vehicle accidents and breakdown stopping. ...
A semantic understanding of road traffic can help people understand road traffic flow situations and emergencies more accurately and provide a more accurate basis for anomaly detection and traffic prediction. At present, the overview of computer vision in traffic mainly focuses on the static detection of vehicles and pedestrians. There are few in-depth studies on the semantic understanding of road traffic using visual methods. This paper aims to review recent approaches to the semantic understanding of road traffic using vision sensors to bridge this gap. First, this paper classifies all kinds of traffic monitoring analysis methods from the two perspectives of macro traffic flow and micro road behavior. Next, the techniques for each class of methods are reviewed and discussed in detail. Finally, we analyze the existing traffic monitoring challenges and corresponding solutions.
... In addition to these classic methods, deep learning-based methods have been developed using two-step detectors like deep neural network (DNN) [70], RetinaNet [91], convolutional neural network (CNN) [28,79], Faster R-CNN [66], fully connected neural network (fcNN) [70], or one-step detectors: You only look once (YOLO) [28,70,78,82,87] and single shot multibox detector (SSD) [92]. These studies showed that deep learning-based methods are more effective than traditional computer vision techniques in traffic video analysis [92]. ...
... Regarding the variables that were taken into account for the evaluation of the proposed system, some authors used parameters such as speed [60,64,78,85], traffic density [66,73], vehicle counting [77,92], vehicle trajectory [80,91], and parameters related to the performance of developed method: precision [79], accuracy [81], F1 score [87], correctness, completeness, and quality [84,90]. In the vast majority of studies, there is no difference between the types of vehicles identified, but in some of the them, vehicles are classified in various categories, like cars, buses, trucks, motorbikes, and even pedestrians are detected in several studies. ...
... Zhu et al., 2018a [91] Presenting an all-in-one behaviour recognition framework for moving vehicles based on the latest deep learning techniques. ...
Unmanned aerial vehicles (UAVs) are gaining considerable interest in transportation engineering in order to monitor and analyze traffic. This systematic review surveys the scientific contributions in the application of UAVs for civil engineering, especially those related to traffic monitoring. Following the PRISMA framework, 34 papers were identified in five scientific databases. First, this paper introduces previous works in this field. In addition, the selected papers were analyzed, and some conclusions were drawn to complement the findings. It can be stated that this is still a field in its infancy and that progress in advanced image processing techniques and technologies used in the construction of UAVs will lead to an explosion in the number of applications, which will result in increased benefits for society, reducing unpleasant situations, such as congestion and collisions in major urban centers of the world.
... Most recently, the bidirectional LSTM (BDLSTM) has been developed to extend LSTM from uni-directional to bi-directional by utilizing both past data and future predictions and incorporating both forward and backward propagations. Thus, BDLSTM may yield better performance in theory, although there are limited applications of BDLSTM in transportation research (Cui et al., 2018;Zhu et al., 2018). Cui et al. (2018) propose a novel deep architecture that stacks the bidirectional and unidirectional LSTM to predict traffic speed. ...
... Cui et al. (2018) propose a novel deep architecture that stacks the bidirectional and unidirectional LSTM to predict traffic speed. Zhu et al. (2018) present a behavior recognition framework for moving vehicles using BDLSTM. These studies find that, when compared to other classical and state-of-the-art models, the developed DL method achieves superior predictive performance. ...
... (2) Bidirectional long short-term memory neural network (BDLSTM) Bidirectional long short-term memory neural network (BDLSTM) builds on bidirectional RNN that enables to process time series data in both forward and backward directions with two separate sets of hidden layers (Schuster and Paliwal, 1997). BDLSTM is also regarded as an extension of the standard LSTM by adding hidden layers in the backward direction (Zhu et al., 2018). As shown in Fig. 9, both forward and backward layers are connected to the output layer. ...
Crowd-shipping (CS) is an innovative logistics service that occasional and professional couriers sign up for via an online platform to deliver packages upon requests by senders. Currently the demand and supply of CS is not yet well understood, largely due to the limited real-world data. This study aims to first fill this gap by analyzing the real-world CS data from the city of Atlanta, GA between April 2015 and August 2018. We first present an overview of the real-world CS data in three aspects: (1) the CS pricing scheme; (2) the CS spatial and temporal delivery patterns; and (3) comparison of preferences between the senders’ requests and the couriers’ bids. The analysis finds that the CS service has a clear price advantage over FedEx in the same-day and express service, as well as in the large, extra large, and huge size package delivery. The data analysis also reveals considerable discrepancies between senders’ and couriers’ preferences. We then compare two classes of the state-of-the-art Deep Learning (DL) methods in their ability to predict short-term CS delivery trip production. One class captures only the temporal features, namely the Long Short-term Memory Neural Network (LSTM), the Bidirectional Long Short-term Memory Neural Network (BDLSTM), and the Gated Recurrent Unit (GRU). The other class considers both spatial and temporal features, namely Convolutional Neural Network (CNN), CNN-LSTM, and ConvLSTM. The results show that ConvLSTM has overall the best predictive performance among the six DL methods considered, proving the importance of capturing both the spatial and temporal features of the delivery trip production data, as well as the convolutional nature of the spatial and temporal features in the data.
... Using 50 sets of videos as the test set, the single and dual networks after training are tested, and the performance of the tracking algorithm is evaluated according to the evaluation method. The main evaluation indicators include: (1) Accuracy of the coincidence rate of the merge ratio threshold of 0.5 (denoted as OP0.5); (2) Spatial robustness, that is, the initial frame label is randomly shifted by 10% (denoted as shift10%) and randomly scaled by 10% (Recorded as scale10%); (3) Tracking speed (fps) [8]. An example of test results is shown in figure 4. The test results are shown in table 3. It can be found from table 3 that for single and dual network frameworks, the tracking accuracy and robustness of the tracking algorithm are not much different. ...
Comparing with the advantages and disadvantages of the existing target tracking algorithms based on deep learning, a vehicle tracking algorithm based on Yolov2 and GOTURN algorithm is proposed, which is called YOLOv2-tracker vehicle tracking algorithm. The Algorithm is trained and tested by using the collected training set and test set. The results show that the YOLOv2-tracker vehicle tracking algorithm can achieve higher tracking accuracy and faster tracking speed, and can effectively overcome environmental interference. Further analysis of the test results, the algorithm found that there is “errof” phenomenon, the paper discusses and analyzes the causes of this phenomenon, and put forward a reasonable solution. In addition, a “dynamic save” method is proposed to solve the “lost track” problem.
... Thus, the UAV-ED system has good performance and would benefit the management of pipeline safety. in many fields, including photographic measurements [3], environmental protection [4], search and rescue operations [5], precision agriculture [6-9], infrastructure monitoring [10], and traffic management [11][12][13]. Deep-learning algorithms, which have achieved state-of-the-art performance on a wide range of image processing tasks, are able to interpret the remote-sensing images efficiently. ...
Unmanned aerial vehicle (UAV) remote sensing and deep learning provide a practical approach to object detection. However, most of the current approaches for processing UAV remote-sensing data cannot carry out object detection in real time for emergencies, such as firefighting. This study proposes a new approach for integrating UAV remote sensing and deep learning for the real-time detection of ground objects. Excavators, which usually threaten pipeline safety, are selected as the target object. A widely used deep-learning algorithm, namely You Only Look Once V3, is first used to train the excavator detection model on a workstation and then deployed on an embedded board that is carried by a UAV. The recall rate of the trained excavator detection model is 99.4%, demonstrating that the trained model has a very high accuracy. Then, the UAV for an excavator detection system (UAV-ED) is further constructed for operational application. UAV-ED is composed of a UAV Control Module, a UAV Module, and a Warning Module. A UAV experiment with different scenarios was conducted to evaluate the performance of the UAV-ED. The whole process from the UAV observation of an excavator to the Warning Module (350 km away from the testing area) receiving the detection results only lasted about 1.15 s. Thus, the UAV-ED system has good performance and would benefit the management of pipeline safety.
... Please note that Long Short-Term Memory (LSTM) [41] has been introduced in the deep learning research field (e.g., [42][43][44][45]). Unlike LTMA, LSTM introduces cells and gates to form a "highway" to retain gradient information in a long sequence of a recurrent neural network. ...
Short term memory that records the current population has been an inherent component of Evolutionary Algorithms (EAs). As hardware technologies advance currently, inexpensive memory with massive capacities could become a performance boost to EAs. This paper introduces a Long Term Memory Assistance (LTMA) that records the entire search history of an evolutionary process. With LTMA, individuals already visited (i.e., duplicate solutions) do not need to be re-evaluated, and thus, resources originally designated to fitness evaluations could be reallocated to continue search space exploration or exploitation. Three sets of experiments were conducted to prove the superiority of LTMA. In the first experiment, it was shown that LTMA recorded at least 50 % more duplicate individuals than a short term memory. In the second experiment, ABC and jDElscop were applied to the CEC-2015 benchmark functions. By avoiding fitness re-evaluation, LTMA improved execution time of the most time consuming problems F 03 and F 05 between 7% and 28% and 7% and 16%, respectively. In the third experiment, a hard real-world problem for determining soil models’ parameters, LTMA improved execution time between 26% and 69%. Finally, LTMA was implemented under a generalized and extendable open source system, called EARS. Any EA researcher could apply LTMA to a variety of optimization problems and evolutionary algorithms, either existing or new ones, in a uniform way.
... A UAV is an effective tool to monitor geographical contexts with simple deployment and a low cost [43][44][45][46]. This study employs a UAV to automatically identify and track moving objects, including pedestrians, cyclists, and vehicles at complex traffic intersections, and to simulate the pedestrian movements. ...
For a city to be livable and walkable is the ultimate goal of future cities. However, conflicts among pedestrians, vehicles, and cyclists at traffic intersections are becoming severe in high-density urban transportation areas, especially in China. Correspondingly, the transit time at intersections is becoming prolonged, and pedestrian safety is becoming endangered. Simulating pedestrian movements at complex traffic intersections is necessary to optimize the traffic organization. We propose an unmanned aerial vehicle (UAV)-based method for tracking and simulating pedestrian movements at intersections. Specifically, high-resolution videos acquired by a UAV are used to recognize and position moving targets, including pedestrians, cyclists, and vehicles, using the convolutional neural network. An improved social force-based motion model is proposed, considering the conflicts among pedestrians, cyclists, and vehicles. In addition, maximum likelihood estimation is performed to calibrate an improved social force model. UAV videos of intersections in Shenzhen are analyzed to demonstrate the performance of the presented approach. The results demonstrate that the proposed social force-based motion model can effectively simulate the movement of pedestrians and cyclists at road intersections. The presented approach provides an alternative method to track and simulate pedestrian movements, thus benefitting the organization of pedestrian flow and traffic signals controlling the intersections.
Recognition of abnormal driving behavior is an important application area as it can support driving reliability and improve safety. In the last decade, deep learning methods have been presented through fruitful academic research and industrial applications. State-of-the-art deep learning methods are not commonly used for detection of abnormal driving behavior based on driving parameter information, and are lacking in terms of recognition accuracy. Based on this, a novel data-driven abnormal driving behaviors method is proposed in this paper by combining a convolutional neural network (CNN) and a Bidirectional gated recurrent unit (BiGRU). In this process, real vehicle driving data, including the extreme acceleration and steering position, are analyzed to establish a dataset of driving behaviors recognition firstly. Then, the datasets are inputted into the CNN-BiGRU algorithm to recognize the abnormal driving behavior where CNN captures non-linear relations from long-term trends of sequences and BiGRU extracts features of time series from driving parameters. The experimental results show that the proposed method offers improved accuracy and robustness in recognizing abnormal driving compared with other existing machine learning methods.
