Vehicle Collision Detection Research Articles

Retraction Note: Fuzzy curvilinear path optimization using fuzzy regression analysis for mid vehicle collision detection and avoidance system analyzed on NGSIM I-80 dataset (real-road scenarios)

Retraction Note: Fuzzy curvilinear path optimization using fuzzy regression analysis for mid vehicle collision detection and avoidance system analyzed on NGSIM I-80 dataset (real-road scenarios)

A novel vehicle collision detection system: Integrating audio-visual fusion for enhanced performance

In vehicular accidents, the swift and accurate identification of car crashes is paramount, as it serves as the linchpin for prompt responses from emergency services and search-and-rescue operations. This study introduces an innovative multimodal car crash detection system that capitalizes on audio-visual data sourced from dashboard cameras, thus significantly enhancing the precision of automobile collision detection. In contrast to car crash detection systems relying on single-modal inputs, this research employs advanced multimodal methodologies with a neural network architecture that integrates Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) for car crash detection. This system concurrently leverages audio spectrogram and audio feature data, video RGB, video optical flow, and video differential information, enabling collision recognition through a neural network system, resulting in markedly improved collision detection accuracy. A comprehensive comparative analysis is conducted, benchmarking our system against the most cutting-edge existing car crash detection systems. The system employs a unique fusion approach, allowing it to apply its inference to audio-visual information of varying durations compared to the training set. The empirical findings unequivocally affirm our proposed solution’s substantial enhancement in car crash detection.

Selecting Features That Influence Vehicle Collisions in the Internet of Vehicles Based on a Multi-Objective Hybrid Bi-Directional NSGA-III

The smart platform of generating, collecting, managing and processing dynamic data from different sources in the Internet of Vehicles (IoV) pave the way for a large-scale dataset to be accumulated. The dataset can contain records running into hundreds of thousands and even millions of relevant, irrelevant and redundant features. Therefore, feature selection to select only the significant features for developing vehicle collision detection alarm systems for deployment in the IoV edge is critical. However, previous studies on vehicle collision detection in the IoV have not conducted rigorous feature selection. Limited studies have mainly applied Pearson correlation coefficient (PCC) to select subset features influencing vehicle collision in the domain of IoV. However, PCC can cause relevant features to be discarded if the correlation of the non-linear association is too small, thereby providing incorrect feature ranking, which, in turn, increases the chances of developing a model that will give a poor outcome. To close this gap, this paper proposed a multi-objective, filter-based hybrid non-dominated sorted genetic algorithm III with a gain ratio and bi-directional wrapper for the selection of subset features influencing vehicle collision in the IoV. The proposed approach selected the minimal most significant subset features for developing a vehicle collision detection classifier with maximum accuracy for deployment in the IoV. A comparative study proves that the proposed approach performs better than the compared algorithms across hybrid-, wrapper- and filter-based feature selection methods within the family of the NSGA. Further, a comparative analysis with other evolutionary algorithms proves the superiority of the proposal. This study can help researchers in the future by avoiding the use of large-scale computing resources in acquiring data to develop vehicle collision alert systems in the IoV. This can be achieved since only the subset features discovered in this study are collected, as opposed to collecting large features, thus saving time and resources in the subsequent vehicle collision detection data collection in the IoV.

Collision Prediction of Smart Cities Using Co-simulation

Road traffic has become prominent in everyday living, impacting or disrupting services to people and daily routines. With the rise in automobile manufacturing and the frequency of vehicle crashes, human catastrophes, like fatalities, accidents, impairments, and destruction of property, are surging yearly. Vehicle collision detection has recently gained prominence in decreasing manually operated and autonomous vehicle fatalities. The concept of independent and self-driving cars relies on accurate object recognition, including pedestrians, vehicles, buildings, and other moving objects. Various object-detecting approaches have been proposed to help autonomous vehicles (AVs) achieve consistent, safe driving. Object prediction and detection have noticed numerous algorithmic changes that have improved speed and accuracy. In this study, I used a traffic dataset produced by a CARLA simulator to anticipate collisions using the Yolov7 model. I generated the dataset from a CARLA simulation bench in video sequences, manually annotated the frames, and used the deep learning algorithm Yolov7 to train them. The model predicts the collision a few seconds before it occurs in real-time. I implemented this framework to increase the safety of driving in self-driving vehicles.

Arduino-based vehicle collision detection and warning system

As the number of vehicles increases day by day, accidents are also rapidly increasing. This surge in accidents poses a significant challenge for road safety authorities, necessitating innovative solutions and stricter enforcement of traffic regulations. Addressing the root causes, such as driver education and infrastructure improvements, is crucial to mitigating the escalating risks on our roads. These accidents can occur due to false estimation of nearby vehicles, disturbances in the mind of the driver, or any other reasons that prevent the driver from maintaining focus on driving. Therefore, not only is the accurate estimation of the distance to other surrounding vehicles necessary, but quick actions are also required to avoid any kind of accidents. In addition, advancements in technology, such as the integration of automated driving assistance systems, aim to enhance the precision of distance estimation and mitigate the risk of accidents caused by human errors. As the automotive industry continues to innovate, the intersection of human vigilance and technological support becomes crucial for ensuring road safety. This paper is specifically focused on preventing accidents. The system is designed to measure the distance between the driving car and the front object. If the driver fails to maintain the minimum safety distance from the front object, the system will warn the driver to slow down the speed of the car and avoid a collision. The driver will receive both visual and audio warnings to ensure that a collision does not occur. Additionally, the paper incorporates advanced sensor technologies and real-time data analysis to enhance the accuracy of distance measurements, providing a robust and reliable solution for accident prevention.

Design and Implementation of Vehicle Collision Detection and Alarm System Based on Smartphone

Every year, there are a large number of people died in traffic accidents in our country. If people can get help in time after a traffic accident, the survival rate of the people who are treated can be greatly increased. Therefore, it is very necessary to have a system that can detect traffic accidents and call the police or notify the rescuers in time. According to the survey and analysis, the functions of some similar systems in China are not perfect and most of the cost are high, which cannot be widely promoted in China with a high private car base. Based on the acceleration sequence value obtained by the smartphone accelerometer, this project designs the vehicle collision detection algorithm and realizes the collision detection during the driving process of the vehicle in the android environment. When a collision event is detected, the system can promptly send the collision information to the preset phone number and drive the camera function of the mobile phone, perform instant photo forensics on the scene, and finally send the help information and the accident photo to the preset phone number. The project system can realize the detection and alarm function of automobile collision accidents in time, and provide timely rescue after the collision accident.

Urban Intelligence With Deep Edges

With the increased accuracy available from state of the art deep learning models and new embedded devices at the edge of the network capable of running and updating these models there is potential for urban intelligence at the edge of the network. The physical proximity of these edge devices will allow for intelligent reasoning one hop away from data generation. This will allow a range of modern urban reasoning applications that require reduced latency and jitter such as remote surgery, vehicle collision detection and augmented reality. The traffic flow from IoT devices to the cloud will also be reduced as with the increased accuracy from deep learning models only a subset of the data will need to be reported after a first pass analysis. However, the training time of deep learning models can be long, taking weeks on multiple desktop GPUs for large datasets. In this paper we show how transfer learning can be used to update the last layers of pre-trained models at the edge of the network, dramatically reducing the training time and allowing the model to perform new tasks without data ever having to be sent to the cloud. This will also improve the users’ privacy, which is a key requirement for urban intelligence applications with the introduction of GDPR. We compare our approach to alternative IoT urban intelligence architectures such as cloud-based architectures and deep learning algorithms trained only on local data.

Vehicle Collision Detection During Night Time

”Vehicle collision detection during night time” is an attempt to find an improved solution for vehicle detection problem, during night time. Night time vehicle detection is a challenging area since, the contrast between back ground and foreground is very less due to non uniform lighting, reflections, multiple light sources etc. This algorithm is a blend of night time image enhancement technique and fusion technique for fusing multiple features based on their weight. Image enhancement is an important aspect of the algorithm as it helps in improving the contrast between foreground and back ground as well as improving the lighting, so that it becomes easier to distinguish vehicle and other illuminated objects such as street lights. For improved reliability of the algorithm, set of complementary features - LBP (local binary pattern), HOG (Histogram of Oriented Gradients) and a CNN based feature - are used in the algorithm and are fused together using weighted fusion technique. For classification purpose, individual SVMs are trained for each feature and another SVM is trained for final rank based vehicle detection. Accurate region of interest in computed during detection phase, and is used for vehicle detection by trained SVM classifiers. Tail light detection is used for efficient region proposals. The algorithm is improved by leveraging the region proposals and high accuracy detection of Faster RCNN [10]. The algorithm detects multiple vehicles in single image frame and at possible multiple locations and distances within the frame.

Vehicle Collision Detection Application Through Collision Video Files with Quadtree Algorithms

The improvement of digital image processing technology is increasingly rapid. Image processing has been widely used to maximize the usefulness of the webcam interface or CCTV, which can be used to monitor traffic flow on the street. One of the frequent event occure on the street is a crash (collision). This problem often arises in a collision event is a dispute about the party guilty in the collision. A collision detection application using Quadtree algorithm can solve this problem. This study aims to analyze and design intelligent systems for vehicle collision detection on street through a webcam camera. Using the Quadtree algorithm, a collisions that occur on vehicles can be detected by the regions division method such ash Quadtree algorithm. Using this application the collision possibilities can be describe. Based on the results of the tests conducted, information was obtained that the accuracy of the application of the Quadtree algorithm in the detection of car collisions on the highway was 8: 2 where the value was obtained from the number of collisions detected.

Simulating unmanned aerial vehicle flight control and collision detection

An unmanned aerial vehicle (UAV) is a small, fast aircraft with many useful features. It is widely used in military reconnaissance, aerial photography, searches, and other fields; it also has very good practical-application and development prospects. Since the UAV’s flight orientation is easily changeable, its orientation and flight path are difficult to control, leading to its high damage rate. Therefore, UAV flight-control technology has become the focus of attention. This study focuses on simulating a UAV’s flight and orientation control, and detecting collisions between a UAV and objects in a complex virtual environment. The proportional-integral-derivative control algorithm is used to control the orientation and position of the UAV in a virtual environment. A version of the bounding-box method that combines a grid with a k-dimensional tree is adopted in this paper, to improve the system performance and accelerate the collision-detection process. This provides a practical method for future studies on UAV flight position and orientation control, collision detection, etc.

Offset-based curvilinear path estimation for mid vehicle collision detection and avoidance system using MARS

PurposeThe purpose of this paper is to propose a novel curvilinear path estimation model employing multivariate adaptive regression splines (MARS) for mid vehicle collision avoidance. The two-phase path estimation scheme initially uses the offset (position) value of the front and the mid (host) vehicle to build the crisp model. The resulting crisp model is MARS regressed to deliver a closely aligned actual model in the second phase. This arrangement significantly narrows the gap between the estimated and the true path analyzed using the mean square error (MSE) for different offsets on Next Generation Simulation Interstate 80 (NGSIM I-80) data set. The presented model also covers parallel parking by encompassing the reverse motion of the host vehicle in the path estimation, thereby, making it amicable for real-road scenarios.Design/methodology/approachThe two-phase path estimation scheme initially uses the offset (position) value of the front and the mid (host) vehicle to build the crisp model. The resulting crisp model is MARS regressed to deliver a closely aligned actual model in the second phase.FindingsThis arrangement significantly narrows the gap between the estimated and the true path studied using MSE for different offsets on real (Next Generation Simulation-NGSIM) data. The presented model also covers parallel parking by encompassing the reverse motion of the host vehicle in the path estimation. Thereby, making it amicable for real-road scenarios.Originality/valueThis paper builds a mathematical model that considers the offset and host (mid) vehicles for appropriate path fitting.

RETRACTED ARTICLE: Fuzzy curvilinear path optimization using fuzzy regression analysis for mid vehicle collision detection and avoidance system analyzed on NGSIM I-80 dataset (real-road scenarios)

The majority of the prevailing collision detection and avoidance systems render evasive maneuvers for averting front and rear vehicle collisions. This paper introduces a mid vehicle collision detection and avoidance system with a constraint-free condition that produces mid vehicle maneuvers, particularly when jammed between the front and rear vehicles. Accordingly, three novel path estimation models based on crisp, fuzzy and fuzzy regression logic are blended to formulate a mid (host) vehicle collision detection and avoidance system. At the onset, the crisp model fits an offset-based curvilinear path for the mid vehicle to avoid edge collisions. The realized crisp model is later fuzzified to address more antecedents and accordingly deliver consequents for enhancing path estimation. Finally, the fuzzified model is regressed to obtain a good fitness for real-road conditions. The fused fuzzy regression renders an approximate version of the actual road strategy to obtain collision-free trajectories. This concept is later intrinsically extended to parallel parking in reverse direction. Simulation studies using coefficient of determination $$(R^{2} )$$ and mean square error on the field, real (next generation simulation-NGSIM) dataset reveals the goodness and the path closeness of the proposed system rendered by the novelly blended models tuned at each observation using the optimum h-uncertain factor. Also, relative mean square error analysis with state-of-art CDAS reveals the superiority of MCDAS, thereby making it amicable for real-road scenarios.

Tracking down the Vehicle Collision Detection and Messaging System using GPS and GSM

Tracking down the Vehicle Collision Detection and Messaging System using GPS and GSM

Simplified bionic solutions: a simple bio-inspired vehicle collision detection system

Modern cars are equipped with both active and passive sensor systems that can detect potential collisions. In contrast, locusts avoid collisions solely by responding to certain visual cues that are associated with object looming. In neurophysiological experiments, I investigated the possibility that the ‘collision-detector neurons’ of locusts respond to impending collisions in films recorded with dashboard cameras of fast driving cars. In a complementary modelling approach, I developed a simple algorithm to reproduce the neuronal response that was recorded during object approach.Instead of applying elaborate algorithms that factored in object recognition and optic flow discrimination, I tested the hypothesis that motion detection restricted to a ‘danger zone’, in which frontal collisions on the motorways are most likely, is sufficient to estimate the risk of a collision. Furthermore, I investigated whether local motion vectors, obtained from the differential excitation of simulated direction-selective networks, could be used to predict evasive steering maneuvers and prevent undesired responses to motion artifacts.The results of the study demonstrate that the risk of impending collisions in real traffic scenes is mirrored in the excitation of the collision-detecting neuron (DCMD) of locusts. The modelling approach was able to reproduce this neuronal response even when the vehicle was driving at high speeds and image resolution was low (about 200 × 100 pixels). Furthermore, evasive maneuvers that involved changing the steering direction and steering force could be planned by comparing the differences in the overall excitation levels of the simulated right and left direction-selective networks. Additionally, it was possible to suppress undesired responses of the algorithm to translatory movements, camera shake and ground shadows by evaluating local motion vectors. These estimated collision risk values and evasive steering vectors could be used as input for a driving assistant, converting the first into braking force and the latter into steering responses to avoid collisions. Since many processing steps were computed on the level of pixels and involved elements of direction-selective networks, this algorithm can be implemented in hardware so that parallel computations enhance the processing speed significantly.

Smart Mobile Phone Groups - Based Design and Implementation of Vehicle Accident Self-rescue System

<p class="p1"><span class="s1">Considering the deficiency that the existing automobile accident self-rescue system requires to assemble the specific sensor, GPS and communication module, the author designed a vehicle collision or crash detection and accident self-rescue system based on the smart mobile phone groups. Taking the acceleration signals of physical moments from the smart mobile phones in the accidents car as the input samples and the assembly of acceleration data as the calculating thresholds, the system can not only improve the accuracy rating of the judgments about the accidents, but can also reduce the unusable distress signals due to the damages to individual vehicle-borne device or mobile phone in severe accidents. When the signals exceed the threshold value, the system can draw support from the functions of video, GPS positioning and 3G networking in the mobile phones automatically to call for help from the rescue center. Meanwhile, a prototype system has been implemented on Android platform. The results of the experiments indicate that the system possesses the advantages of high accuracy of collision or crash recognition, low energy consumption and low cost.</span></p>

Traffic collisions early warning aided by small unmanned aerial vehicle companion

Most traffic surveillance systems are based on videos which captured by fixed cameras on bridges, intersections, etc. However, many traffic collisions may occur in many places without such surveillance systems, e.g., in rural highway. Researchers have developed a set of techniques to improve safety on these places, while it is still not enough to reduce collision risk. Based on a novel concept, this paper proposes a traffic collisions early warning scheme aided by small unmanned aerial vehicle (UAV) companion. Basically, it is a vision-based driver assistance system, and the difference in comparison with the available schemes lies in the camera is flying along with the host vehicle. In particular, the system’s framework and the vision-based vehicle collision detection algorithm are proposed. The small UAV works in two switchable modes, i.e., high speed flight or low speed motion. The high speed flight corresponds to the host vehicle moving in highway, while the low speed motion includes hover, vertical takeoff and landing. In addition, as the on-line machine learning is applied, the detection procedure can be implemented in real-time, which is critical in practical applications. Extensive experimental results and examples demonstrate the effectiveness of the proposed method, and its real-time performance outperforms typical tracking methods such as that based on Gaussian mixture model. Moreover, this scheme can be easily extended for some other similar application scenarios.

A Cooperative Strategy for Collision Detection and Prevention for Unmanned Ground Vehicles in Military Applications using WSN based VANET

In the recent years, vehicular Ad Hoc Networks have gained tremendous attention of researchers due to various services they provide and likely to be deployed commercially in coming years. VANET enables vehicles to communicate with each other to avoid any critical situation such as vehicle collision, unseen obstacles etc. Safety applications such as collision warning, highway/rail collision avoidance, obstacle detection and avoidance are one of the driving forces behind the deployment of VANETs. Collision detection and prevention is a critical issue to work at as there is an increased rate of collisions between vehicles in fog during night time or zero visibility situations and rescue operations in inconvenient places such as military battlefield, highways. So any strategy that can detect and prevent such collisions to some extend will be beneficial. In this paper, a simple and cooperative strategy for collision detection and prevention for Unmanned Ground Vehicle (UGV) in military battlefield using WSN based VANET is proposed.

Analytic and Heuristic Methods of Collision Detection for Curve-Moving Vehicle Based on Cooperative Collision Warning System

Analytic and Heuristic Methods of Collision Detection for Curve-Moving Vehicle Based on Cooperative Collision Warning System

Progressive reasoning for real-time intelligent computing

It is argued that the success of real-time intelligent computing hinges on reconciling the unpredictability and vigor of the inference process with the real-time requirement that control system responses must be both appropriate and timely. The use of progressive reasoning, which provides a means of relaxing the demands made on the inference process without violating real-time constraints, is considered. It is a technique that successively refines a solution while making available intermediate, albeit suboptimal, solutions. Factors that influence the successful use of progressive reasoning are examined. A small case study involving autonomous vehicle collision detection and avoidance is presented to illustrate the use of progressive reasoning in a typical automation environment.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>