Smart Car: An IoT Based Accident Detection System

Arif, Shaik; Bowen, Natalie; Bole, Jennifer; Kunzi, Gary; Bruce, David; Abdelgawad, Ahmed; Yelamarthi, Kumar

doi:10.1109/gciot.2018.8620131

Cited by 51 publications

(15 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shaik et al developed a vehicular sensor in [160] that utilizes GSM communications to notify ambulances and healthcare workers of accidents, with results showing notifications were immediately sent to the appropriate destinations. This demonstrates EC-GSM is an appropriate solution for accident or fault monitoring in areas where LTE is unavailable, however we still recommend LTE-based networks if available due to their lower latency.…”

Section: Transportmentioning

confidence: 99%

Low-Power Wide-Area Networks: Design Goals, Architecture, Suitability to Use Cases and Research Challenges

et al. 2020

View full text Add to dashboard Cite

Previous survey articles on Low-Powered Wide-Area Networks (LPWANs) lack a systematic analysis of the design goals of LPWAN and the design decisions adopted by various commercially available and emerging LPWAN technologies, and no study has analysed how their design decisions impact their ability to meet design goals. Assessing a technology's ability to meet design goals is essential in determining suitable technologies for a given application. To address these gaps, we have analysed six prominent design goals and identified the design decisions used to meet each goal in the eight LPWAN technologies, ranging from technical consideration to business model, and determined which specific technique in a design decision will help meet each goal to the greatest extent. System architecture and specifications are presented for those LPWAN solutions, and their ability to meet each design goal is evaluated. We outline seventeen use cases across twelve domains that require large low power network infrastructure and prioritise each design goal's importance to those applications as Low, Moderate, or High. Using these priorities and each technology's suitability for meeting design goals, we suggest appropriate LPWAN technologies for each use case. Finally, a number of research challenges are presented for current and future technologies. INDEX TERMS Low power wide area network (LPWAN), Internet of Things (IoT), design goals, MAC layer, channel access, long range, scalability, data rate, licensed and unlicensed band, operational lifetime.

show abstract

Section: Transportmentioning

confidence: 99%

Low-Power Wide-Area Networks: Design Goals, Architecture, Suitability to Use Cases and Research Challenges

et al. 2020

View full text Add to dashboard Cite

show abstract

“…From the cloud, an alert message will be sent to the person whoever has done the subscriptions to that car's system. Through the GPS co-ordinates, ambulance will be able to reach that spot easily and the signal will indicate the harshness of the accident [14].…”

Section: Literature Reviewmentioning

confidence: 99%

An IoT-Based Support System for Cars in Case of Critical Health Emergency

2021

View full text Add to dashboard Cite

In this technologically advancing world, a huge interest has been seen from the Automobile industry toward IoT applications, due to factors such as concern about the safety of the passengers, to satisfy customers' usability, and ultimately to offer cheaper but effective products which should maximize profit. The healthcare industry is more interested in how the IoT technology can lead to speedy and accurate treatment and how fast they could reach the neediest. This paper initially describes the practicability of equipping a vehicle with modern technology that can help patients to locate the nearest appropriate hospital by uploading their diagnosis into that system. Secondly, to reach the destination (i.e., Hospital) as soon as possible with the help of traffic police. For critical health issues such as Cardiac Arrest, Pregnancy (Labor pain), rapidly bleeding, snakebite, respiratory issues, gunshot fire and badly wounded, etc., where patient needs immediate medical assistance but unfortunately many of the times they could not make it due to traffic jams. While rushing to the hospital in case of medical emergency, it is risky to both communicate and locate the hospital at the same time while driving, so we have developed a system to establish a private network which will communicate via Cloud Thingspeak to the Hospital about our arrival. Also, the system will send patients' basic details, GPS location to them so that they'll get ready with their medical support. We will send vehicle information and GPS coordinates to the Traffic control room to get help in clearing the way for the patient's vehicle till the Hospital.

show abstract

“…For ease of presentation, we regard the first grid as example to explain the training steps of YOLO-CA. The center of car accident region falls into the grid cell (7,5), so this cell is responsible for detecting this car accident in the whole training process. Then the cell (7, 5) will predict three bounding boxes, and each boxes includes six parameters: x, y, w, h, CS, p. The (x, y) is the center point of the bounding box, and the (w, h) is the ratio of width and height of the bounding box to the whole image.…”

Section: ) Network Designmentioning

confidence: 99%

“…Especially, because that the multi-scale feature fusion is used in YOLO-CA, the loss is the sum of conditions under S = 13 and S = 26. In additionally, the loss of each batch of images is defined as (7). Loss_img k (7) where the b in ( 7) is the size of batch.…”

Section: ) Network Designmentioning

confidence: 99%

See 1 more Smart Citation

An Automatic Car Accident Detection Method Based on Cooperative Vehicle Infrastructure Systems

et al. 2019

View full text Add to dashboard Cite

Car accidents cause a large number of deaths and disabilities every day, a certain proportion of which result from untimely treatment and secondary accidents. To some extent, automatic car accident detection can shorten response time of rescue agencies and vehicles around accidents to improve rescue efficiency and traffic safety level. In this paper, we proposed an automatic car accident detection method based on Cooperative Vehicle Infrastructure Systems (CVIS) and machine vision. First of all, a novel image dataset CAD-CVIS is established to improve accuracy of accident detection based on intelligent roadside devices in CVIS. Especially, CAD-CVIS is consisted of various kinds of accident types, weather conditions and accident location, which can improve self-adaptability of accident detection methods among different traffic situations. Secondly, we develop a deep neural network model YOLO-CA based on CAD-CVIS and deep learning algorithms to detect accident. In the model, we utilize Multi-Scale Feature Fusion (MSFF) and loss function with dynamic weights to enhance performance of detecting small objects. Finally, our experiment study evaluates performance of YOLO-CA for detecting car accidents, and the results show that our proposed method can detect car accident in 0.0461 seconds (21.6FPS) with 90.02% average precision (AP). In additionally, we compare YOLO-CA with other object detection models, and the results demonstrate the comprehensive performance improvement on the accuracy and real-time over other models.INDEX TERMS Car accident detection, CVIS, machine vision, deep learning.

show abstract

Smart Car: An IoT Based Accident Detection System

Cited by 51 publications

References 8 publications

Low-Power Wide-Area Networks: Design Goals, Architecture, Suitability to Use Cases and Research Challenges

Low-Power Wide-Area Networks: Design Goals, Architecture, Suitability to Use Cases and Research Challenges

An IoT-Based Support System for Cars in Case of Critical Health Emergency

An Automatic Car Accident Detection Method Based on Cooperative Vehicle Infrastructure Systems

Contact Info

Product

Resources

About