3-D Compression-Oriented Image Content Correlation Model for Wireless Visual Sensor Networks

Yang, Xiaodong; Wen, Yingyou; Yuan, Duoning; Zhang, Mingyang; Zhao, Hong; Meng, Yunlong

doi:10.1109/jsen.2018.2847332

Cited by 12 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are also other works proposing solutions from other perspectives which could improve the network nodes’ energy efficiency. For example, a clustering based data prediction transmission scheme was proposed in paper [ 16 ]. In this scheme, according to mathematical relationship of the expected seamless coverage ratio and the number of required cluster heads, the initial probability for the nodes to contend for the cluster heads are restrained.…”

Section: Methodsmentioning

confidence: 99%

CS-FCDA: A Compressed Sensing-Based on Fault-Tolerant Data Aggregation in Sensor Networks

Sun

Liu

et al. 2018

Sensors

View full text Add to dashboard Cite

When the nodes in the network are deployed in the target area with an appropriate density, the effective aggregation and transmission of the data gathered in the monitoring area remain to be solved. The existing Compressed Sensing (CS) based on data aggregation schemes are accomplished in a centralized manner and the Sink node achieves the task of data aggregation. However, these existing schemes may suffer from load imbalance and coverage void issues. In order to address these problems, we propose a Compressed Sensing based on Fault-tolerant Correcting Data Aggregation (CS-FCDA) scheme to accurately reconstruct the compressed data. Therefore, the network communication overhead can be greatly reduced while maintaining the quality of the reconstructed data. Meanwhile, we adopt the node clustering mechanism to optimize and balance the network load. It is shown via simulation results, compared with other data aggregation schemes, that the proposed scheme shows obvious improvement in terms of the Fault-tolerant correcting capability and the network energy efficiency of the data reconstruction.

show abstract

Section: Methodsmentioning

confidence: 99%

CS-FCDA: A Compressed Sensing-Based on Fault-Tolerant Data Aggregation in Sensor Networks

Sun

Liu

et al. 2018

Sensors

View full text Add to dashboard Cite

show abstract

“…However, the authors did not consider the construction of a defense barrier. Yang et al [12] introduced the concept of weighted barrier graph (WBG) aiming to model the barrier coverage problem. They demonstrated that the problem of finding the number of visual sensors is equivalent to the problem of constructing the shortest path from the source node to the destination node on the WBG.…”

Section: B Barrier Coverage In Wvsnsmentioning

confidence: 99%

“…As an extension of study [12], Wang et al [13] further proved that the construction of a barrier with k-coverage is equivalent to finding k vertex-disjoint paths with the minimum total length on the WBG. Then, an algorithm based on previous work, called Vertex-Disjoint Path approach, was proposed for solving the problem of k-barrier coverage.…”

Section: B Barrier Coverage In Wvsnsmentioning

confidence: 99%

A Distributed Barrier Coverage Mechanism for Supporting Full View in Wireless Visual Sensor Networks

Chang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Barrier coverage is one of the most important issues in intruder detection applications. Visual sensors can give more accurate information of intruder but also raise the problem of large data volume for information exchange and processing. Constructing a disjoint full-view barrier using minimal number of visual sensors has been the main goal for handling the barrier coverage problem. This paper presents a decentralized FBCA mechanism which consists of Region Partitioning Phase, Grid Excluding Phase, Grid Verification Phase and Full-View Barrier Construction Phase. In Region Partitioning Phase, the given R is partitioned into a set of equal-sized grids, aiming to simplify the construction problem of the full-view barrier. In Grid Excluding Phase, a certain amount of grids is removed, aiming to reduce the computational complexity. In Grid Verification Phase, each visual sensor aims to check if its neighboring grids satisfy the full-view coverage criteria. Finally, the Full-View Barrier Construction Phase aims to construct as many as possible full-view barriers. Experimental study shows that the proposed FBCA outperforms existing work SP, and likely approaches to the optimal solution (MCSPS) in terms of the average success ratio for constructing a full-view barrier.

show abstract

“…The supply of smart devices with high performance and the rapid development of cameras with good quality enabled the general public to easily and freely acquire video data through the high-speed wired and wireless Internet. Such image data include various kinds of video big data such as photos, CCTV videos, black box images of cars, UCC (user created contents), and movies [1][2][3][4][5]. In addition, the acquired image big data are useful in a variety of related practical applications such as robot vision, content-based image retrieval, real-time surveillance, human-computer interaction, face detection, and autonomous driving [6][7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Efficient covering of target areas using a location prediction-based algorithm

Jang

2020

J Supercomput

View full text Add to dashboard Cite

Due to the rapid development of the high-speed wired and wireless Internet, image contents including objects with exposed personal information are being distributed freely, which is a social problem. In this paper, we introduce a method of robustly detecting a target object with facial region exposed from an image that is quickly entered using skin color and a deep learning algorithm and effectively covering the detected target object through prediction. The proposed method in this paper accurately detects the target object containing facial region exposed from the image entered by applying an image adaptive skin color model and a CNN-based deep learning algorithm. Subsequently, the location prediction algorithm is used to quickly track the detected object. A mosaic is overlapped over the target object area to effectively protect the object area where the facial region is exposed. The experimental results show that the proposed approach accurately detects the target object including the facial region exposed from the continuously entered video, and efficiently covers the detected object through mosaic processing while quickly tracking it using a prediction-based tracking algorithm. The tracking-based target covering method proposed in this study is expected to be useful in various practical applications related to pattern recognition and image security, such as content-based image retrieval, real-time surveillance, human-computer interaction, and face detection.

show abstract

3-D Compression-Oriented Image Content Correlation Model for Wireless Visual Sensor Networks

Cited by 12 publications

References 28 publications

CS-FCDA: A Compressed Sensing-Based on Fault-Tolerant Data Aggregation in Sensor Networks

CS-FCDA: A Compressed Sensing-Based on Fault-Tolerant Data Aggregation in Sensor Networks

A Distributed Barrier Coverage Mechanism for Supporting Full View in Wireless Visual Sensor Networks

Efficient covering of target areas using a location prediction-based algorithm

Contact Info

Product

Resources

About