Railway Security System Design by Image Processing and Deep Learning Unmanned Aerial Vehicle

EYLENCE, Muzaffer; YÜCEL>, Mehmet; Özmen, Mustafa; Aksoy, Bekir

doi:10.46810/tdfd.1112957

Cited by 2 publications

(2 citation statements)

References 21 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The drawbacks of cloud computing necessitated the need for an edge computing model that is faster than cloud computing and can route tasks intelligently to meet quality of service. Edge computing has been a popular choice in recent times to reduce network transmission delays [28]- [30] since it is more tolerant of poor network connectivity [31], [32].…”

Section: Edge Computing Paradigm and Transport Industrymentioning

confidence: 99%

IoT and Edge Computing Technologies as Security Option for Train Service in Nigeria

Jiya,

Akinyemi,

Nwocha

2023

J. Inf. Syst. Informatics

View full text Add to dashboard Cite

The revival of rail transport service in Nigeria in recent years came at a critical moment of insecurity in Nigeria, it promised not only to serve as an alternative to overloaded vehicles on the roads but was also thought to be a safer means of transportation. Due to kidnapping on many roads, both high and low-class Nigerians patronized rail transport. However, train attacks and terrorism are major challenges that have impacted the sector negatively. Though the government has tried to improve surveillance along train routes, however, the result has not been impressive. The current level of insecurity in Nigeria is beyond the use of traditional surveillance and monitoring systems. It requires the adoption of technology to fight attacks and to monitor the health of train facilities. While the insecurity challenges that have overwhelmed the security forces will not permit the assignment of more personnel to the rail tracks that stretch several kilometres across the country, the incorporation of IoT and edge computing can be an optimal solution to the challenges of constant security problems. Among the trending technologies, IoT is a viable option that the country can adopt to improve security in the sector. It will increase the confidence of passengers and improve revenue and growth in rail transport.

show abstract

Section: Edge Computing Paradigm and Transport Industrymentioning

confidence: 99%

IoT and Edge Computing Technologies as Security Option for Train Service in Nigeria

Jiya,

Akinyemi,

Nwocha

2023

J. Inf. Syst. Informatics

View full text Add to dashboard Cite

show abstract

“…In a study based on a single-stage target detection algorithm, Ding et al [26] and Eylence et al [27] used the YOLOv5 model for foreign object detection, respectively, with good results; Some researchers have combined basic target detection algorithms with attention mechanisms for detection [28], [29], [3], [30].…”

Section: Related Work a The Detection Of Foreign Bodiesmentioning

confidence: 99%

EBSE-YOLO: High Precision Recognition Algorithm for Small Target Foreign Object Detection

Wang,

Chang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

For the complex background along the electrified railroad, there are problems such as missed detection and false detection of invasive small target foreign objects. A high-precision recognition algorithm for small target foreign object detection is proposed. A channel attention mechanism ECA-Net is added to the backbone network of YOLOv5s so that the network can focus more on small target objects; borrowing from the network structure of weighted bidirectional feature pyramid network (BiFPN), the backbone network is fused with Neck by adding an edge to achieve cross-level feature fusion; the SPD-Conv module is used to replace the seventh layer convolutional kernel to increase the detail information extraction; using EIOU loss function to shorten the actual difference in width and height between the a priori frame and the real frame, The experimental results show that the improved algorithm increases the mAP value by 3.35 percentage points with little growth in computational volume, and the highest mAP value reaches 97.96%. The detection accuracy is greatly improved with a small loss of time cost, and the demand for small target foreign body detection in complex environments is achieved.

show abstract

Railway Security System Design by Image Processing and Deep Learning Unmanned Aerial Vehicle

Cited by 2 publications

References 21 publications

IoT and Edge Computing Technologies as Security Option for Train Service in Nigeria

IoT and Edge Computing Technologies as Security Option for Train Service in Nigeria

EBSE-YOLO: High Precision Recognition Algorithm for Small Target Foreign Object Detection

Contact Info

Product

Resources

About