Energy efficient surveillance system using WVSN with reweighted sampling in modified fast Haar wavelet transform domain

2022 18th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)

2022

Nowadays, to improve animal well-being in livestock farming applications, a wireless video sensor network (WVSN) can be deployed for surveillance and livestock monitoring to early detect injury or Asiatic hornets attacks [1]. They are composed of small embedded video and camera motes that capture video frames periodically and send them to a specific node called a sink. Sending all the captured images to the sink consumes a lot of energy on every sensor and may cause a bottleneck at the sink level. Energy consumption and bandwidth limitation are two important challenges in WVSNs because of the limited energy of nodes and the medium scarcity.In this work, we exploit the Spatio-temporal correlation between neighboring nodes to reduce the number of captured frames. For that purpose, Synchronization with Frame Rate Adaptation SFRA algorithm is introduced where overlapping nodes capture frames in a synchronized fashion every N − 1 period, where N is the number of overlapping sensor nodes. The results show more than 90% data reduction, surpassing other techniques in the literature at the level of the number of sensed frames by 20% at least.

Section: Related Workmentioning

confidence: 99%

Spatio-Temporal Data Reduction Technique in WVSN for Smart Agriculture

Koteich

Salim²,

2022 18th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)

2022

“…In this section, we discuss some previous works regarding data reduction in WSN and in WVSN in particular. A lot of techniques based on scheduling [6], [3], in-trusion location and clustering [13,4], compressive sensing [16], data similarity [10], [11], and frame rate adaptation [15,7] exist for data reduction and for energyefficiency. The authors in [13] used the kinematics functions to predict the next location of the intrusion in the area of interest in order to increase the frame rate adaptation of the targeted nodes.…”

Section: Related Workmentioning

confidence: 99%

“…In this paper, the proposed method reduces the number of frames sent from each node to the coordinator by using the L2-norm distance to measure the similarity. It is a way less heavy to be implemented at the sensor node unlike other techniques that use the colour-edge and pixel similarities as in [10], [15], [7]. As explained in section 1.3 it is a less complex technique regarding the execution time comparison with other approaches for the same purpose of data reduction.…”

Section: Related Workmentioning

confidence: 99%

Image Similarity Based Data Reduction Technique in Wireless Video Sensor Networks for Smart Agriculture

Salim

Advanced Information Networking and Applications

2021

Nowadays, to improve animal well being in livestock farming or beekeeping application, a wireless video sensor network (WVSN) can be deployed to early detect injury or Asiatic hornets attacks. WVSN represents a low-cost monitoring solution compared to other technologies such as the closed circuit television technology (CCTV). WVSNs are composed of low-power resource-constrained video sensor nodes (motes). These nodes capture frames from videos at a given frequency (frame rate) and wirelessly send them to the sink. The big amount of data transferred from the nodes to the sink consumes a lot of energy on the sensor node, which represents a major challenge for energy-limited nodes. In this paper, we introduce two complementary mechanisms to reduce the overall number of frames sent to the sink. First, the Transmission Data Reduction algorithm (TDR) run on the sensor node leverages the similarity degree of consecutive images. Second, the Inter-Nodes Similarity algorithm (INS) exploits the spatio-temporal correlation between neighbouring nodes in order reduce the number of captured frames. The results show a 95% data reduction, surpassing other techniques in the literature by 30% at least.

“…Several research work for energy reduction has been proposed to decrease data redundancy: Scheduling methods [4]- [6], [9], [13], Data aggregation [18], Geometrical criteria [14]- [16], prediction techniques [8], frame rate adaptation [1], [2], [7], [10], [11]. In Akkaya et al [17], a GPS module is used to control the cameras and to determine which camera should be activated based on the sensor's location.…”

Section: Related Workmentioning

confidence: 99%

Data Reduction and Frame Rate Adaptation in WVSN

Koteich¹,

Salim

2021 17th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)

2021

Wireless Video Sensor Networks (WVSNs) are becoming one of the most used technologies for surveillance and livestock monitoring. They are composed of small embedded video and camera motes that capture video frames periodically and send them to a specific node called a sink. Sending all the captured images to the sink consumes a lot of energy on every sensor and may cause a bottleneck at the sink level. Energy consumption and bandwidth limitation are two important challenges in WVSNs because of the limited energy of nodes and the medium scarcity. The first one is related to the sensing and transmission modules of the sensor node. The higher the frame rate and the number of frames sent, the more energy is consumed. The second one is related to the transmission module of the sensor node, the greater the number of frames sent on the network the more bandwidth is used. In this paper, FRABID, a joint data reduction, and frame rate adaptation on sensing and transmission phases mechanism is introduced. This approach reduces the number of sensed frames based on a similarity method. The aim is to adapt the number of sensed frames based on the degree of difference between two consecutive sensed frames in each period. This adaptation technique maintains the accuracy of the video while capturing frames holding new information. This approach is validated through simulations using real data-sets from video sensors [3]. The results show that the amount of sensed data is reduced by more than 70% compared to a recent algorithm in [2], while guaranteeing the detection of all the critical events at the sensor node level.