Deep Learning Enabled Object Detection and Tracking Model for Big Data Environment

Kumar, Kirthi; Lydia, E. Laxmi; Dutta, Ashit Kumar; Velmurugan, S.; Ramasamy, Gobi; Pustokhina, Irina V.; Pustokhin, Denis A.

doi:10.32604/cmc.2022.028570

Cited by 2 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many advancements in parking systems using computer vision [35] [1] , RFID tags [27] [5], deep learning [35] [1] and Blockchain-IoT integration [31] [36] [6] [30] [22] have mitigated many parking issues namely time saving, management of parking places and traffic congestion alleviation. Hence, there is still a need to improve these systems.…”

Section: Discussionmentioning

confidence: 99%

“…Hence, there is still a need to improve these systems. The listed works rely on IoT devices integrated along with RFID tags [27] [5], Ultrasonic sensors [22] or cameras [35] [1] to authenticate a car in a parking slot through its plate. Their solutions may be susceptible to security issues or cyber-attacks during car authentication on parking entry due to their limited built-in security features.…”

Section: Discussionmentioning

confidence: 99%

“…In citeICCC2016, the authors propose an architecture which brings IoT gadget including sensors and microcontrollers along with TCP/IP protocol for exchanging parking data. More recently, the use of IoT devices and sensors is also found in [35]. The authors propose a system based on a Raspberry-Pi that activates a servo motor to take a picture of the car's plate.…”

Section: A Smart Parking Systems Based On Iotmentioning

confidence: 99%

See 2 more Smart Citations

PufParkChain: Secure and Smart Parking Based on PUF Authentication and Lightweight Blockchain

Turki,

Dammak,

Alshahrani

2024

IEEE Access

View full text Add to dashboard Cite

Smart Parking Systems have emerged as a transformative solution to address the growing challenges associated with urbanization and increasing vehicular traffic. Such system integrates sensors, cameras, and other IoT connected devices to monitor parking spaces in real time. However, there are many security vulnerabilities in existing solutions, especially when it comes to car authentication at parking entry points. IoT sensors my be susceptible to Cyber-attacks and fraudulent activities, such as car theft, can exploit these vulnerabilities due to limited built-in security features. The reliability of authentication systems, based on IoT sensors can also be compromised by factors such as extreme weather conditions and physical damage. The cyber-physical solution we propose relies on Physical Unclonable Functions (PUFs) for identification and authentication in IoT devices to mitigate these challenges. The use of PUFs enhances the reliability and security of smart parking systems against unauthorized access and fraud. Furthermore, to ensure the integrity and confidentiality of the data within the smart parking ecosystem and to improve authentication process, we propose the implementation of a tailored blockchain framework. This framework incorporates lightweight local blockchains dedicated to individual parking slots, complemented by a central blockchain that manages data at the city level. The experimental results demonstrate the feasibility of the PUF computation process, showcasing an acceptable runtime for practical implementation. In the experimental results, we evaluated the SRAM used for the PUF implementation process and demonstrated its stability (intra HD equals to 2.25

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: A Smart Parking Systems Based On Iotmentioning

confidence: 99%

See 1 more Smart Citation

PufParkChain: Secure and Smart Parking Based on PUF Authentication and Lightweight Blockchain

Turki,

Dammak,

Alshahrani

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…At present, intelligent transportation systems have been developed to decrease the volume of traffic in metropolitan cities, decrease the rate of injuries and accidents, and deaths, minimize fuel consumption, decrease environmental pollution, etc [1]. Such systems used diverse technologies (including deep learning (DL), IoT, data mining, image processing, neural networks (NN), and machine learning (ML) for different applications [2].…”

Section: Introductionmentioning

confidence: 99%

Leveraging Marine Predators Algorithm with Deep Learning Object Detection for Accurate and Efficient Detection of Pedestrians

Gogineni

Bhuyan

Lydia³

2023

Preprint

View full text Add to dashboard Cite

Pedestrian detection using object detection and deep learning has been found to be effective method for identifying pedestrians in video frames or images accurately. It is more commonly used in many real-time applications, such as security observing systems, autonomous driving systems, and robotics. The combination of deep learning techniques and object detection algorithms allows efficient and robust detection of pedestrians in several real-time scenarios. But it is necessary to improve the detection efficacy for complex environments such as cases with worse visibility due to weather or daytime, crowd scenes, and rare pose samples. Continuous improvement and research in DL algorithms, dataset collection, and training models contribute to accelerating the robustness and accuracy of pedestrian detection systems. Therefore, this study designs a new marine predator algorithm with deep learning-based pedestrian detection and classification (MPADLB-PDC) technique. The objective of the MPADLB-PDC approach lies in the accurate recognition and classification of pedestrians. To achieve this, the MPADLB-PDC technique involves two major processes, namely object detection and classification. In the first stage, the MPADLBPDC technique uses an improved YOLOv7 object detector for the recognition of the objects in the frame. Next, in the second stage, the ensemble classifier comprises three classifiers such as deep feed-forward neural network (DFFNN), extreme learning machine (ELM), and long short-term memory (LSTM). To improve the recognition performance of the ensemble classifier, the MPA is used to optimally select the parameters related to it. The simulation outcome of the MPADLB-PDC system was validated on the pedestrian database, and the outcome can be studied interms of various aspects. The simulation values validated the better outcome of the MPADLB-PDC system compared to other approaches.

show abstract

Deep Learning Enabled Object Detection and Tracking Model for Big Data Environment

Cited by 2 publications

References 13 publications

PufParkChain: Secure and Smart Parking Based on PUF Authentication and Lightweight Blockchain

PufParkChain: Secure and Smart Parking Based on PUF Authentication and Lightweight Blockchain

Leveraging Marine Predators Algorithm with Deep Learning Object Detection for Accurate and Efficient Detection of Pedestrians

Contact Info

Product

Resources

About