Face detection is necessary for many different applications: face recognition, image database management, etc. In this study, a face detection algorithm is performed on images based on human skin color, and the detected face image is classified based on gender. In this algorithm, three color spaces (RGB, HSV, YCbCr) are used and face detection is performed by combining different thresholds in these three spaces. Outputs of the algorithm are used as feature vectors for the gender classification. The genders in the images are classified with 100% accuracy using the different classification methods.

In this paper, the methodology of detecting rescue messages extracted from social media data is presented. Rescue messages were originated after an earthquake, they are tweets that may also deliver information about position and time. A massive amount of social media data has been extracted after the two earthquake disasters of magnitude of Mw 7.7 and Mw 7.6 occurred on February 6, 2023 in Turkiye. The procedure of manual labelling and automated labelling is presented. For labeling purposes, nine BERT language models, which are based on attention and transformers, were used. The supervised learning methods were applied to assess the precision of the labels and perform classification. Furthermore, the dataset was processed with deep learning methods: Convolutional Neural Networks, Deep Neural Networks, and Long Short-Term Memory. Accuracy of data toward detection of rescue and non-rescue tweets is compared. Keywords are extracted to determine hazard situations and emergency needs toward coordination purposes including spatio-temporal information when provided by tweets. Deep learning and BERT models detect rescue and non-rescue classes assuring a level in 0.8972 and 0.9808 in recall, respectively.

Optimization-based methods are commonly applied in autonomous driving trajectory planners, which transform the continuous-time trajectory planning problem into a finite nonlinear program with constraints imposed at finite collocation points. However, potential violations between adjacent collocation points can occur. To address this issue thoroughly, we propose a safety-guaranteed collision-avoidance model to mitigate collision risks within optimization-based trajectory planners. This model introduces an “embodied footprint”, an enlarged representation of the vehicle’s nominal footprint. If the embodied footprints do not collide with obstacles at finite collocation points, then the ego vehicle’s nominal footprint is guaranteed to be collision-free at any of the infinite moments between adjacent collocation points. According to our theoretical analysis, we define the geometric size of an embodied footprint as a simple function of vehicle velocity and curvature. Particularly, we propose a trajectory optimizer with the embodied footprints that can theoretically set an appropriate number of collocation points prior to the optimization process. We conduct this research to enhance the foundation of optimization-based planners in robotics. Comparative simulations and field tests validate the completeness, solution speed, and solution quality of our proposal.

This paper is focused on the cooperative trajectory planning problem for multiple car-like robots in a cluttered and unstructured environment narrowed by static obstacles. The concerned multi-vehicle trajectory planning (MVTP) problem is challenging because i) the scenario is nonconvex and tiny; ii) the vehicle kinematics is nonconvex; and iii) a feasible homotopy class is unavailable a priori. We propose a two-stage MVTP method: Stage 1 identifies a feasible homotopy class, and Stage 2 quickly finds a local optimum based on the identified homotopy class. Numerical optimal control, adaptive scaling, grouping, and trust region construction strategies are integrated into the proposed planner. Our planner is extensively compared in 100 benchmark cases with the state-of-the-art MVTP methods such as incremental sequential convex programming, numerical optimal control, conflict-based search, priority-based trajectory optimizer, and optimal reciprocal collision avoidance. The simulation results demonstrate our method's superiority in runtime and optimality. Experiments with three car-like robots demonstrate the efficiency of our proposed planner. Source codes are in https://github.com/libai1943/MVTP_benchmark.

In this paper, we propose a computationally efficient method for traffic sign detection. Our methodology uses deep learning networks introduced for semantic image segmentation and classification of region of interests generated by image segmentation. The region of interests are detected by segmenting the road scene image dataset and hypothesis tests are applied to accept or reject the probability of being a traffic sign in the detected region of interest. For hypothesis tests, color feature, and the location of the traffic sign with respect to the segmented road information is used. The main contribution of our method is the introduction of hypothesis tests that mutually couple two deep learning networks trained by well-known datasets publicly available for benchmarking purposes. To test and evaluate our traffic sign detection system, we use the German traffic sign detection benchmark dataset with a large set of traffic signs and during its training, The cityscapes dataset offering labeled urban scenes is also leveraged by the traffic sign detection system. Our experimental results illustrate the effectiveness performance metrics are reached at 90.81%, 94.76% and 92.74% in precision, recall and F-measure, respectively. The runtime cost is around 0.4[Formula: see text]s for an image on an ordinary laptop computer.

This paper is focused on planning fast, accurate, and optimal trajectories for autonomous parking. Nominally, this task should be described as an optimal control problem (OCP), wherein the collision-avoidance constraints guarantee travel safety and the kinematic constraints guarantee tracking accuracy. The dimension of the nominal OCP is high because it requires the vehicle to avoid collision with each obstacle at every moment throughout the entire parking process. With a coarse trajectory guiding a homotopic route, the intractably scaled collision-avoidance constraints are replaced by within-corridor constraints, whose scale is small and independent from the environment complexity. Constructing such a corridor sacrifices partial free spaces, which may cause loss of optimality or even feasibility. To address this issue, our proposed method reconstructs the corridor in an iterative framework, where a lightweight OCP with only box constraints is quickly solved in each iteration. The proposed planner, together with several prevalent optimization-based planners are tested under 115 simulation cases w.r.t. the success rate and computational time. Real-world indoor experiments are conducted as well.

Autonomous intersection management (AIM) refers to planning the trajectories for multiple connected and automated vehicles (CAVs) when they traverse an unsignalized intersection cooperatively. As an extension of the conventional AIM, lane-free AIM allows the CAVs to adjust their velocities and paths flexibly within the intersection. Nominally, one needs to formulate a centralized optimal control problem (OCP) to describe the concerned lane-free AIM scheme, but solving such an intractably scaled problem is challenging. This work proposes a batch-processing framework, which divides the traffic flow into batches. The cooperative trajectories within one batch are planned by numerically solving a small-scale OCP; all the batches are managed via a reservation-based method following the first-come-first-serve policy. The proposed batch-processing framework aims to run as fast as a reservation-based method at the macro level while taking care of the cooperative driving quality at the micro level. The proposed method is validated via simulation and preliminary experiments.

Driver Monitoring Systems play a crucial role at detecting driver’s distraction to assure perception and reaction when driver is loaded by secondary activities, and specifically making transition of control authority from automated driving system to driver in conditional automation (SAE Level L3). Activities such as using cell phone, operating radio, drinking, talking to a passenger are an instance preventing the driver percepting the road scene and, degrading perception and reaction of the driver to possible hazards. In this paper, a new approach is presented to detect driver activity using deep learning based driver image classification and driver pose estimation. Driver pose information is obtained using a pre-trained deep network and it is used in a machine learning based classifier, in this case, a Random Forest. Then, results of two predictive models, deep learning based image classifier and Random Forest classifier leveraged by pose estimation, are combined and activity detection is performed using this fusion mechanism. The effectiveness of the presented driver activity recognition system is investigated using a publicly available dataset and multi-class activity detection test accuracy is found to be 0.9703.

A solution for a tractor-trailer vehicle's generic maneuver planning task can be introduced by an optimal control problem (OCP). However, the curse of dimensionality is excited along with the OCP solution due to the collision-avoidance constraints in a large scale. The collision-avoidance conditions are weakened by simply constructing a corridor along a homotopically guiding route such that the vehicle's maneuvers are safely separated from obstacles. This approach is motivated by the safe flight corridor (SFC) applied for path planning of unmanned aerial vehicle (UAV). But SFC cannot be applied directly to the ground vehicle cases because a tractor-trailer vehicle cannot be modeled as a mass point in a narrow environment. An extension of the SFC is proposed, which requires different bodies of a multi-body vehicle to stay in different safe travel corridors. In this way, a reduced-scale OCP is formulated, and the problem scale becomes irrelevant to the environmental complexity. Simulation results illustrate that near-optimal maneuvers can be derived within less CPU time.

Vehicular Ad-Hoc Network is an emerging technology and research area since it promises fast and lossless communication among vehicular nodes. Vehicular to Everything (V2X) communication targets data sharing between the vulnerable road users and cars with mobile network assistance in the near future. Despite the nature of vehicular mobility and density, V2X requires transmitting massive data over a long range and being lossless. LTE becomes the main infrastructure for V2X and called Cellular V2X (C-V2X), but it is still a developing technology necessitating further research efforts. In this study, the literature review is conducted to elaborate the LTE characteristics and its performance. To evaluate and test the LTE deployment in a VANET, an NS3 simulator coupled with a SUMO simulator is built to enable scalable simulation of various traffic scenarios. A set of physical channel configuration parameters is evaluated to maximize the performance of a fast and lossless ad-hoc communication in road traffic. Performance related parameters are listed and explained in the proposed system scheme. This study contributes to the geo-based resource selection algorithm along with comparative simulation studies. Performance results are compared with respect to the Semi Persistent Scheduling scheme. Our evaluation and test study illustrates that according to the calculated packet reception rates, the resource selection algorithm plays a crucial role. In addition, previous public simulation studies conducted to seek the performance of C-V2X are utilized to develop an NS-3 based open source C-V2X simulation environment.

Deployment of SAE Level 3+ automated vehicles faces validation and certification challenges due to uncertainty and state space size of the operating domain. We propose a validation and testing methodology that aims to minimize unknown unknowns through minimization of scenarios that have not been accounted for, and scenarios that have not been identified due to modeling deficiencies. The methodology utilizes simulators with different levels of fidelity for residual risk handling, functional hierarchies for simplification of complex navigation tasks, and the Backtracking Process Algorithm to identify scenarios of risk significance. The methodology is demonstrated on a scenario with an intersection preceded by a traffic light. Through use of the testing flowchart, we were able to identify and remedy scenarios leading to undesirable events.

Trajectory planning for a tractor-trailer vehicle is challenging because the vehicle kinematics consists of underactuated and nonholonomic constraints that are highly coupled. Prevalent sampling-based or search-based planners suitable for rigid-body vehicles are not capable of handling the tractor-trailer vehicle cases. This work aims to deal with generic n-trailer cases in the tiny environments. To this end, an optimal control problem is formulated, which is beneficial in being accurate, straightforward, and unified. An adaptively homotopic warm-starting approach is proposed to facilitate the numerical solution process of the formulated optimal control problem. Compared with the existing sequential warm starting strategies, our proposal can adaptively define the subproblems with the purpose of making the gaps between adjacent subproblems “pleasant” for the solver. Unification and efficiency of the proposed adaptively homotopic warm-starting approach have been investigated in several extremely tiny scenarios. Our planner finds solutions that other existing planners cannot. Online planning opportunities are briefly discussed as well.

In this study, we elaborate the procedure of designing a supervisory controller for the Autonomous Transit on Demand Vehicle (ATODV) system. Reinforcement learning is implemented to reduce the mean waiting time of the passengers, and a cost function is introduced to penalize the energy consumption of the electric vehicles. A stochastic simulation environment for an ATODV pilot project is coded in the Python environment to train the autonomous cart decision process as agents with artificial intelligence. Passenger group behavior, get-on and get-off times, destinations are modeled as random variables. A single Deep Q-Learning Network is trained subject to multi-agent settings. The ATODV system's independent decision making for the carts to reduce the passenger's waiting time while constraining the energy consumption and empty vehicle motion is evaluated.

In this paper, multiple-object vehicle tracking system by affinity matching using min-cost linear cost assignment is proposed. This tracking system is targeted to scene recordings acquired from cameras mounted on a moving ego vehicle. Vehicle tracking on the road scene and images acquired from moving ego vehicle’s camera amplifies the problem of greater bounding box geometry change in comparison with other low speed tracking applications such as traditional pedestrian tracking. This perturbation occurs in many tracking scenarios such as when a high speed object is approaching from an opposing lane. Since autonomous driving algorithms need to use the processing resources in an efficient manner even while satisfying the requirements of computationally complex tasks like localization, object detection, occupancy grid update, sensor-fusion and trajectory planning, our study is particularly focused on the development and benchmarking of an computationally lightweight online multiple object tracking model. To test and evaluate our model, we use KITTI Object Tracking - Car Benchmark dataset and our model statistical metric values are comparably higher; our model outperforms the state-of-the-art methods on ML and MT and places second on MOTA and MOTP metric evaluations, and processing time is 6 to 20 times faster compared to other methods.

In this paper we present the procedure of fusing a monocular camera based vehicle tracking and IEEE 802.11p Vehicle-to-Vehicle communication enabled position, velocity and time sharing. Toward a monocular camera-based detection and tracking, Haar-like features of a vehicle are trained, median flow tracking algorithm is applied, pixel based relative distance and relative speed is estimated. In order to improve reliability and availability of tracking system, IEEE 802.11p radio modem is added. Then, we implement Particle Filter algorithm in order to fuse the information provided by these two sensors subject to different characteristics. We evaluate the tracking system by the real road data collected on highway. Sensor fusion results along different road scenarios are presented. We present the state-of-the-art low cost sensor fusion, our application setup and elaborate some experimental results.

This study presents the runtime behaviour‐based classification procedure for Windows malware. Runtime behaviours are extracted with a particular focus on the determination of a malicious sequence of application programming interface (API) calls in addition to the file, network and registry activities. Mining and searching n‐gram over API call sequences is introduced to discover episodes representing behaviour‐based features of a malware. Voting Experts algorithm is used to extract malicious API patterns over API calls. The classification model is built by applying online machine learning algorithms and compared with the baseline classifiers. The model is trained and tested with a fairly large set of 17,400 malware samples belonging to 60 distinct families and 532 benign samples. The malware classification accuracy is reached at 98%.

This paper addresses identification of risk level of the driver from the statistical analysis of sharp maneuvering tasks ensuing with the human being who is controlling the technical system. In particular, risk level is predicted by processing offline time stamped and geographically referenced driving maneuver information occured due to exceeding a given threshold acceleration in both longitudinal and lateral direction and a speed limit given as the static attribute of the road map data. A data set in terms of vehicle numbers and time period is analyzed and driving activites are fused using Dempster-Shafer theory to assess risk level related to vehicle driving performance. The level in accident making prediction accuracy is reached at 82%.

Global Navigation Satellite Systems (GNSS) are widely used in vehicle navigation applications. GNSS mostly suffer from atmospheric conditions and urban buildings. Due to urban buildings, GNSS signals are blocked and it is likely that the number of available satellites is insufficient to compute position fix. Classical integrity concepts do not regard local cases which appears a likely case in the vehicle navigation domain. Recent studies discuss about local integrity concept to overcome this problem in urban locations. However technical applicability using feasible resources is low. In this paper, we present a local integrity heat map that indicates possible urban canyons and estimate positioning error given the location and time of the measurement. Local integrity heat map is designed as a digital map attribute which will be used as other sensor information at the time of position sensor fusion to enhance localization and map matching. Real world field tests show that local integrity heat map is a good indicator of position fix error.

This tutorial paper highlights possible issues related to the integrity and authentication of the GNSS position in road applications. In fact, the Global Navigation Satellite System (GNSS) community is already aware of the conceptual and practical problems related to the availability of the position integrity (i.e. position confidence, protection level) and authentication in urban scenarios. However, these issues seem not to be widely known in the Intelligent Transportation Systems (ITS) domain. These limitations need to be carefully considered and addressed in the perspective of deploying reliable and robust systems based on positioning information.

This paper presents an assisted system for vehicle localization and map-matching by utilizing Vehicle ad-hoc Networks (VANETs). Fusion of the GNSS and odometer measurement is augmented by ranging distance. Ranging is computed by exchanging the data packets between the vehicular nodes equipped with Dedicated Short Range Communication (DSRC) modem and GNSS receiver. Time-of-Arrival (ToA) of exchanged data packet between the two vehicular nodes is converted in distance. Map matching enhances accuracy of localization while projecting the result of multilateration created by numerous ranging queries. Realistic simulations are conducted to test the performance of the algorithm. Test results show bounded and acceptable particle filter positioning results. The scenario of GPS outages and low number of vehicles collaborating for positioning are simulated. Tracking performance of the particle filter is illustrated. Algorithm helps dead reckoning when GPS data is not available temporarily. A simple GPS receiver is fused with odometer data during tests. Particularly, expensive sensors are not used to achieve better price/performance towards commercial usage.

This paper presents a high performance and robust system for traffic sign recognition with digital map fusion. The proposed system is enhanced by fusion of different sensors and recognition is improved. Traffic sign is detected by a monochrome camera added by a reflective surface detector whereas recognition is achieved by a template matching algorithm. Digital Maps used in this work are standard navigable data. For localization the GPS receiver and the odometer of the test vehicle is used with the developed particle filter based map-matching algorithm. Tests are accomplished in rural and urban areas of metropolitan city for both day and night conditions. Especially, success rate at night scenes is comparably higher when compared to existing approaches and technologies. The system is unique since it is not limited to certain sign types, can be used in day and night conditions. The proposed system can be easily adapted to real world applications since it utilizes low cost and industrially available digital map content and sensors.

ABSTRACT Nowadays, cyber‐world is being enriched by a large variety of digital information technology‐based services. An increasing rate of remote and mobile usage leads to a remarkable dependency on information security. Analysis and detection of malicious software or so‐called malware is a challenging task due to the introduction of advanced obfuscation techniques by malware authors. In this study, we mainly concentrate on anti‐virtual machine evasion techniques to provide secure and reproducible environments for malware analysis and its implementation issues. Malwares are identified on the basis of their behaviors by taking precautions related to the anti‐virtual machine detection techniques. The dynamic malware analyzer tool is deployed to execute anti‐virtual machine‐aware malware samples in VMware environment. Dynamic malware analyzer monitors system resources such as connections, processes, windows registry, and file operations. Success ratio of detection is tested by using public malware sets with an accuracy of 92%. The effectiveness and success of the behavior‐based malware analyzer tool is exploited and current state of the art of malware detection schemes is presented. Copyright © 2013 John Wiley & Sons, Ltd.

One of the most challenging factors in the development of autonomous vehicles and advanced driver assistance systems is the imitation of an expert driver system which is the observer and interpreter of the technical system in the related driving scenario. In this paper, a multimodal adaptive driver assistance system is presented. The main goal is to determine the human driver's attention and authority level by decoupling the driver's vehicle control in the longitudinal and lateral direction in order to trigger timely warnings according to his/her driving intents and driving skills with respect to the possible driving situation and hazard scenarios. The presented driver assistance system considers the driver's driving performance metric sampled during the longitudinal and lateral vehicle control tasks as well as the processed information about the surrounding traffic environment consisting of the interactions with the other vehicles and the road situations. Experiments on a simulator are performed and the presented metric is calculated for the evaluation of the human driver's driving performance with respect to adaptive cruising and obstacle avoidance maneuvering tasks.

This paper presents a novel algorithm for vehicle localization and map-matching using particle filter with the help of digital maps. Probability of being on a certain area of digital map according to vehicle speed is used in conjunction with routing information to augment likelihood function in weight calculation step of particle filter. Real life tests were conducted on different regions of Istanbul to test the performance of the algorithm. Test results show dramatic increase in correctness of map-matching and position correction. Algorithm also helps dead reckoning when GPS data is not available temporarily. A simple GPS receiver is fused with odometer data during tests. Expensive sensors are not used to achieve better price/performance for commercial usage.

Before the deployment of any vehicular communication system, security and privacy issues have to be resolved. In this paper, for achieving secure and privacy preserving communications, an easily implementable PKI-based protocol is proposed. Security requirements for vehicular communications are defined and a detailed definition of the scheme, which uses shared asymmetric keys and PKI techniques to provide anonymous and secure communications, is given. Furthermore, the proposed protocol is evaluated against the defined security requirements. Providing privacy and security, the proposed scheme does not introduce any complexity and computational overheads.