A Survey on Object Detection Methods in Visual Sensor Networks

International Journal of Advanced Smart Sensor Network Systems (IJASSN), Vol 6, No.2, April 2016
DOI:10.5121/ijassn.2016.6201 1
A SURVEY ON OBJECT DETECTION METHODS IN
VISUAL SENSOR NETWORKS
Shamim Yousefi and Samad Najjar Ghabel
Faculty of Electrical and Computer Engineering, University of Tabriz, 29th Bahman
Boulevard, Tabriz, Iran, Islamic Republic of
ABSTRACT
Object detection is one of the major challenges in visual sensor networks (VSNs) which is set up in the
monitoring applications. Many approaches proposed to solve the object detection problem in VSNs,
considering diverse metrics such as reliability, energy consumption, detection accuracy and being real-
time. In this paper, a survey on the object detection methods in visual sensor networks is presented for the
first time. Furthermore, this paper classified the methods precisely. Two main object detection categories
in VSNs that explored in this paper are conventional object detection methods and object detection
approaches with the camera nodes involvement. To be more precise, presented survey promotes an
overview of recent object detection methods' literature with their performance evaluation. Also, this
research is challenging and the object detection issue in the visual sensor networks is open caused by
differences in estimations and performance metrics. Therefore, the survey concludes with open research
challenges.
KEYWORDS
Detection Accuracy, Energy Consumption, Object Detection, Object Recognition, Visual Sensor Networks
1. INTRODUCTION
Recent advances in low-power and resource constraining self-organizing sensor nodes have led to
the development of visual sensor networks (VSNs) [1, 2, 3]. The camera nodes that constitute the
visual sensor networks are able to capture the multimedia data from the monitoring area in the
form of conventional or infrared images and video streaming. Therefore, VSNs can lead to the
development of monitoring and surveillance applications such as traffic control systems [4, 5],
person locator services [6], industrial process control systems, seismic sensing and hazardous
environment exploration [7] automated assistance for the elderly and family monitoring,
biomedical health monitoring [8, 9] and virtual reality [10].
On most of the expressed applications, object detection and recognition are one of the major
challenging issues in the visual sensor networks [11]. Two principal object detection categories in
visual sensor networks that explored in this paper are conventional object detection methods and
object detection approaches with the camera nodes involvement. The conventional object
detection approaches in VSNs used various types of the background subtraction techniques [12]
to recognize the difference between the background and foreground images. In such method, if
the background subtraction result exceeds a pre-determined threshold, the camera node will
detect moving objects within the monitoring area and sends the captured/difference image to the
base station for recognition operations [13, 14]. In visual sensor networks, the data
communication cost is usually much higher than the image processing cost [15]. Therefore, the

2
conventional object detection approaches are not suitable for monitoring and surveillance
applications.
For reducing data transmission cost, some works involves the camera nodes to perform
preprocessing after background subtraction and transmit only the bounding box of the objects to
the network [16]. In these methods, if there are some non-object pixels between the objects in the
foreground image, they are sent to the base station, too. As a result, this type of methods will be
suitable on applications for detecting a single object. Some other works involve the camera nodes
to perform preprocessing tasks, after background subtraction and send only the features or key-
points of the objects to the base station [17, 18, 19]. The overall taxonomy of the object detection
methods in visual sensor networks are shown in Figure 1.
Figure 1: Overall Taxonomy of the Object Detection Methods in VSNs
In the recent papers, various approaches for object detection in visual sensor networks are
presented, but there is a deficiency of well-defined grouping of them based on applications'
requirements. So, this survey presents taxonomy of object detection methods and discusses each
approach under the appropriate category. The rest of the paper is organized as following: Section
2 provides a more detailed survey about the object detection methods in visual sensor networks
and categorizes the approaches. In Section 3, reviewed methods are compared and the paper is
concluded based on VSNs' applications.
2. TAXONOMY OF OBJECT DETECTION APPROACHES IN VSNS
Two main object detection categories in visual sensor networks that are examined in this section
are conventional object detection methods and object detection methods with the camera nodes
involvement. The conventional object detection approaches in VSNs used various types of
background subtraction techniques [12] to recognize the moving objects in the camera node's
field-of-view. In such methods, camera nods send the captured/difference image that include
objects to the base station [13, 14]. While object detection methods with the camera nodes
involvement perform preprocessing tasks after background subtraction and send only the
bounding box of the objects or the useful information of them into the network [16, 17, 18, 19].
2.1. CONVENTIONAL OBJECT DETECTION METHODS
In most of the traditional visual sensor networks' applications, background subtraction techniques
[12] are one of the common approaches to detect the presence of moving objects. These
approaches are based on the difference between the background and foreground images [20]. At
first, each camera node captures a reference image from its field-of view without any moving
objects, which called background image [21]. After saving the background image, the camera
nodes periodically capture the foreground image [22] from its field-of view.

3
In background subtraction approaches for object detection in VSNs, each camera node subtracts
the background and foreground images. If the difference between the background and foreground
images exceeds a pre-determined threshold, the camera node will detect moving objects within its
monitoring area and sends the foreground/difference image to the base station for recognition and
classification operations [13, 14].
2.1.1 OBJECT DETECTION USING THE BACKGROUND SUBTRACTION AND IMAGE
RECONSTRUCTION
In most of the machine vision applications [23], detecting the moving objects in the camera
nodes' field-of view is one of the very important issues. To reduce the energy consumption of the
network, Kenchannavar et al. [13] suggested that the camera nodes must process the captured
image, and then send the useful information to the base station.
As shown in Figure 2, each camera node has a background image and periodically captures the
images from its monitoring area. The moving objects are detected using a background subtraction
technique with some pre-determined threshold values. If the background subtraction result
exceeds the pre-determined threshold value, the camera node will detect moving objects within
the monitoring area and calculates the energy that required for subtraction. Then, the difference
image is sent to the base station using TCP/IP protocol. The foreground image is reconstructed
using the background image, difference image and the median filter [24] at the server and the
energy consumed during reconstruction and transmission is calculated.
Figure 2: Block Diagram for the Camera node and server [13]
The results of authors' implementations show that the visual sensor network's bandwidth [25] in
the cases that the captured images have been processed is efficient as compared to without
processing the images, which in turn increase the network's lifetime [26]. However, in
subtraction/reconstruction approaches, non-object pixels with zero value (black) are injected into
the network, when the background subtraction result is sent to the base station. Therefore, the
transmission energy of the network is increased and its performance will not be acceptable.
Furthermore, background subtraction-based object detection methods are sensitive to
environmental factors like luminance [18].

4
2.1.2 MULTI-OBJECT DETECTION USING THE HAAR-LIKE FEATURES
To accelerate multi-object detection in VSNs with low training data, Vaidehi et al. [14] have been
proposed a method using Haar-like features [27] and Joint-Boosting algorithm [28]. The
foundation of work is that each camera node has a background image and periodically captures
the foreground images from its field-of-view. If the difference between the background and
foreground images exceeds a pre-determined threshold, foreground image is sent to the base
station for extra recognition tasks.
As shown in Figure 3, the foreground images received are treated as the inputs to the multi-object
detection system in the base station. In first step of the multi-object detection approach, the
integral images [29] are defined to compute the Haar-like features fast. The integral image is a
matrix in which its parts include sum of all the pixels in the left-upper part of the foreground
image. The rectangle areas and their Haar-like features are directly obtained in the integral image.
Haar-like features are the input of the decision tree classifiers. In the next step, after a strong
classifier is trained, it can be applied to the foreground image's regions for detecting the
object/non-object sub-window.
Figure 3: Multi-object Detection System Architecture [14]
The simulation results of the author's implementation proved that classifier requires low training
data by using Haar-like features, which in turn accelerate multi-object detection. Furthermore, the
paper shows that detection system recognizes all instances of the objects regardless of their scale
and location. However, further investigation states non-object pixels are injected into the visual
sensor network, when all the foreground image's pixels are sent to the base station. Therefore, the
VSNs' lifetime is decreased and proved inefficiency of the multi-object detection method.
2.2. OBJECT DETECTION METHODS WITH THE CAMERA NODES INVOLVEMENT
It is worth mentioning that calculating the difference between the background and foreground
images are the basis task of all object detection methods in visual sensor networks. However,
analyzing the conventional object detection methods shows using only the background
subtraction techniques increases the network's energy consumption, which in turn decrease the
lifetime of the camera nodes. To reduce data transmission cost in VSNs, some of the existence
approaches involves the camera nodes to perform various preprocessing tasks after background
subtraction and transmit only the useful information such as bounding box, features or key-points
of the objects to the base station [16, 17, 18, 19].

5
2.2.1 EXTRACTING BOUNDING BOX OF THE OBJECTS
To detect objects using minimum hardware and improve the detection costs, Pham et al. [16]
have suggested an efficient approach for extracting the bounding box of the objects in camera
nodes. In bounding box detection method, each stable camera node captures a background image
and converts to gray-scale one. Then, the camera nodes periodically capture foreground images
from own field-of-view and convert to gray-scale ones, too. The moving objects are detected
using a background subtraction technique with some pre-determined threshold values. If the
difference between background and foreground images exceeds the pre-determined threshold, the
result of background subtraction that is a black-and-white image with only values of 0 and 1, will
be treated as the input of the bounding box extraction step. As shown in Figure 4, bounding box
extraction step involves row and column scans to detect whether the number of consecutive
differences is greater than a pre-determined threshold or not (difference threshold for objects'
length and width). During row scans, the first pixel location of the first threshold consecutive
differences and the last pixel location of the last threshold consecutive differences are recorded as
the row edges of bounding box. Similarly, in column scans, the first pixel location of the first
threshold consecutive differences and the last pixel location of the last threshold consecutive
differences have been recorded as the column edges of bounding box. The extracted rows and
columns' edges are used for determining bounding box of the objects in the colored foreground
image.
Figure 4: Extracting the Bounding Box of Objects: (A) Black-and-white Subtraction Result, (B) Rows and
Columns Scan, (C) Bounding Box of the Objects [16]
It is worth mentioning that the noises in the image cause finding some false targets in the most of
the object detection approaches [30]. The results of the authors' implementation show that images'
noises are usually in small groups of consecutive pixels and the approach discards them.
Furthermore, the paper proves that the transmission costs in visual sensor networks are more than
processing ones. So, preprocessing images in the camera nodes and sending only the bounding
box of the objects to the base station increase the network lifetime, significantly. However,
further investigation shows extracting each object's bounding box eliminates non-object pixels in
the overall bounding box and decreases the injected traffic into the VSNs. In other words,
bounding box extraction approach can be suitable for only single object detection. Furthermore,
in the human detection applications, extracting the bounding box of each face [31] and sending it
to the base station is adequate to satisfy the recognition tasks requirements.
To further improvement in visual sensor networks' lifetime, some works have been proposed
various low-complexity face detection methods in camera nodes for detecting the existence faces
in the extracted bounding box. Yousefi et al. [32] have suggested an energy-aware multi-object
method that works based on extracting the bounding box of the objects and Boosting-based face
detection algorithm. The simulation results demonstrated that face detection method injects low
volume of traffic into the network and saves camera nodes energy. However, the complexity of
the Boosting-based face detection algorithm depends on the size of the input boxes and non-
object pixels as the detected objects increases the size of the input boxes, which in turn raise the

6
processing complexity in the camera nodes. In the other hands, face detection methods are
suitable only for the VSNs' applications with the aim of human recognition.
2.2.2 EXTRACTING OBJECTS' FEATURES OR KEY-POINTS
Some object detection approaches in visual sensor networks involve the camera nodes to perform
preprocessing tasks, after background subtraction and sent only the features or key-points of the
objects to the base station [17, 18, 19]. The qualities of the detected objects are accelerated by
using the features or key-points extraction methods, especially in the applications that the
distance between the camera node and objects is changing, continuously. Furthermore, extracting
the features or key-points of the objects and injecting them into the networks decrease the
processing and transmission costs, these in turn improve the performance of the visual sensor
networks.
2.2.2.1 OBJECT DETECTION METHODS BASED OF BINARY ROBUST INVARIANT SCALABLE
KEY-POINTS
To maximize the quality of reconstructed pixel-domain representation under limited resources
such as bandwidth and processing power, some approaches have been suggested that camera
nodes extract the main features required for object recognition using Binary Robust Invariant
Scalable Key-points (BRISK) and send them to the base station for extra recognition analysis.
Object detection approach based on BRISK processes the foreground image to recognize a
number of salient key-points that correspond to very different pixels of the underlying image.
Finally, descriptors detected from the foreground image are matched with a set of descriptors
extracted from a database of reference images. Therefore, a ranked list with the most relevant
results is returned.
To use the BRISK for detecting objects, Redondi et al. [17] have extended Binary Robust
Independent Elementary Features (BRIEF) designing to fix it against scale and rotation
transformations. As shown in Figure 5, the camera nodes are responsible for capturing images,
performing key-point detection tasks and finally, transmitting the descriptors to the base station.
The base station performs object recognition leveraging the descriptors received from the camera
node. The relay nodes only perform information communication and routing tasks.
Figure 5: Architecture of Object Detection by BRISK [17]
Paper's simulation results prove that the processing time depends on the images resolution and the
number of highlight key-points. Furthermore, the paper shows object detection accuracy and data

7
transmission duration is accelerated by using the BRISK to detect the objects. However, using the
local features such as BRISK for object detection in visual sensor networks has not a perfect
performance to predict and formulate the lost data.
To solve the control problem and balance the processing loads in a visual sensor network, some
works have used the temporal correlation in video sequences [19]. The basis of the work is
distributing the processing load by allocating sub-areas of the images to the camera nodes.
Therefore, the threshold and cut-point are estimated for each image, and then the optimal values
of parameters via autoregressive models are predicted. The analytical results of the paper show
that prediction-based methods reach the detection threshold and cut-points in a persuasive
performance. Furthermore, achieving low computational complexity make them a group of
convenient ways to control and balance the processing load on the local feature detection in
VSNs. However, further investigations prove that prediction-based methods will not have an
acceptable performance in visual sensor networks' monitoring and surveillance applications.
2.2.2.2 OBJECT DETECTION METHODS BASED ON ADAPTIVE GAUSSIAN MIXTURE MODEL
To eliminate the influence of environmental factors such as brightness variations, some works
[18] have proposed object detection methods in visual sensor networks based on adaptive
Gaussian mixture model. As shown in Figure 6, the first step of object detection in the camera
nodes is frame reconstruction, which reduces the image size by parting it into blocks with a pre-
determined size. Then, average color value of each image block is computed in a RGB color
space and replaced for the corresponding block. In the second step, background modeling is
performed. The static pixels may only be modeled by a Gaussian member, while other pixels,
which are non-static, should be modeled by multiple Gaussian mixture components. Finally, to
detect whether a pixel matches a component of the Gaussian, sort the Gaussian components, and
then compare them one by one with the corresponding pixel. The pixels are detected as
background pert if matches a component of the Gaussian and foreground one, otherwise.
Figure 6: A. Foreground Image, B. Frame Reconstruction, C. Object Detection in Reconstructed Image and
D. Object Detection in Foreground Image.
Simulation results of the paper show adaptive Gaussian mixture model minimizes the processing
cost and the influence of environmental factors. So, it is suitable for many detection-based
applications in VSNs. However, further investigations prove the faces information is adequate for
detecting the objects, which are humans. Therefore, it is proved transmitting the non-face
information of the humans into the network reduces its lifetime.
3. CONCLUSION AND OPEN ISSUES
In this paper, the importance of object detection and recognition in visual sensor networks was
discussed, which is set up in the monitoring and surveillance applications. Many different
approaches have been proposed to solve the object detection problem in VSNs, considering

8
diverse metrics such as reliability, energy consumption, object detection accuracy and being real-
time. In this paper, a survey on the object detection methods in visual sensor networks is
presented for the first time. Two principal object detection categories in VSNs that explored in
this paper were conventional object detection methods and object detection approaches with the
camera nodes involvement. To be more precise, presented survey promoted an overview of recent
object detection methods' literature with their performance evaluation.
Table 1 illustrates a summary of approaches discussed in this paper utilizing purpose and their
cons and pros. It clearly indicates object detection approaches with the camera nodes involvement
increase the preprocessing and transmission costs partially, which in turn accelerate lifetime of
the camera nodes. Furthermore, table 1 shows that sending the face's information of the objects to
the base station is adequate, when the objects are humans.
One of the important open research issues for object detection-based applications in visual sensor
networks include decreasing the transmission energy of the networks and raising their lifetime.
This purpose is achieved by increasing low cost preprocessing tasks in camera nodes and sending
only the useful information (such as only the faces' information of the humans) to the base
station. Another interesting issue for object detection approaches in visual sensor networks is
energy efficient missing objects recovery, when the camera nodes fail. Therefore, fault tolerant
object detection methods must be designed for VSNs to maximize the detection accuracy with
minimum hardware.
Table 1 Classification of Object Detection Approaches
Methods
Purpose of
Methods
Advantage(s) Disadvantage(s)
Object Detection
using
background
subtraction
techniques [13,
33]
Detecting the
moving object
bandwidth usage
reduction
Influencing of
environmental factors,
High energy consumption
Object detection
using Haar-like
features [14]
Detecting objects
without size
limitation
high-precision
object detection,
speed acceleration
High transmission energy
Extracting the
bounding box of
the objects [16]
High speed object
detection with
minimum hardware
Increasing residual
energy of the
network
Not perfect in reducing
the transmission costs
Extracting the
face's
information of
the objects [32,
34]
increasing
preprocessing tasks
in camera nodes
Decreasing injected
traffic into the
network, Increasing
network' lifetime
high processing and
transmission costs
Object detection
using BRISK
[17, 35]
Maximizing the
quality of pixel-
domain display by
limited resources
Optimizing
processing time,
Increasing
detection accuracy
Inefficiencies in the
prediction of lost
information
Object detection
by adaptive
Gaussian mixture
model [18]
Decreasing costs,
Eliminating
environmental
factors
Reliable object
detection
Sending objects'
information to the base
station instead of faces'
one

9
REFERENCES
[1] Soro, S., Heinzelman, W. "A survey of visual sensor networks." Advances in Multimedia 2009
(2009).
[2] Akyildiz, I.F., Melodia, T. and Chowdhury, K.R. "A survey on wireless multimedia sensor
networks." Computer networks 51.4 (2007): 921-960.
[3] Akyildiz, I.F., Melodia, T. and Chowdury, K.R. "Wireless multimedia sensor networks: A survey."
Wireless Communications, IEEE 14.6 (2007): 32-39.
[4] Tavli, Bulent, et al. "A survey of visual sensor network platforms." Multimedia Tools and
Applications 60.3 (2012): 689-726.
[5] Misra, Satyajayant, Martin Reisslein, and Guoliang Xue. "A survey of multimedia streaming in
wireless sensor networks." Communications Surveys & Tutorials, IEEE 10.4 (2008): 18-39.
[6] Feller, Steven D., et al. "Tracking and imaging humans on heterogeneous infrared sensor arrays for
law enforcement applications." AeroSense 2002. International Society for Optics and Photonics,
2002.
[7] Wener-Allen, G., et al. "Deploying a wireless sensor network on an active volcano, Data-Driven
Applications in Sensor Networks (Special Issue)." IEEE Internet Computing 2 (2006): 18-25.
[8] Gao, Tia, et al. "Vital signs monitoring and patient tracking over a wireless network." Engineering in
Medicine and Biology Society, 2005. IEEE-EMBS 2005. 27th Annual International Conference of
the. IEEE, 2006.
[9] Lorincz, Konrad, et al. "Sensor networks for emergency response: challenges and opportunities."
Pervasive Computing, IEEE 3.4 (2004): 16-23.
[10] Charfi, Youssef, Naoki Wakamiya, and Masayuki Murata. "Challenging issues in visual sensor
networks." Wireless Communications, IEEE 16.2 (2009): 44-49.
[11] Hu, Weiming, et al. "A survey on visual surveillance of object motion and behaviors." Systems,
Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on 34.3 (2004): 334-
352.
[12] Piccardi, Massimo. "Background subtraction techniques: a review." In Systems, man and
cybernetics, 2004 IEEE international conference on, vol. 4, pp. 3099-3104. IEEE, 2004.
[13] Kenchannavar, Harish H., Sushma S. Kudtarkar, and U. P. Kulkarni. "Energy Efficient Data
Processing In Visual Sensor Network." International Journal of CS & IT (2010).
[14] Vaidehi, V., et al. "Multiclass object detection system in imaging sensor network using haar-like
features and joint-boosting algorithm." Recent Trends in Information Technology (ICRTIT), 2011
International Conference on. IEEE, 2011.
[15] Canclini, A., et al. "Object recognition in visual sensor networks based on compression and
transmission of binary local features."
[16] Pham, Duc Minh, and Syed Mahfuzul Aziz. "Object extraction scheme and protocol for energy
efficient image communication over Wireless Sensor Networks." Computer Networks 57.15 (2013):
2949-2960.
[17] Redondi, Alessandro, Luca Baroffio, Antonio Canclini, Matteo Cesana, and M. Tagliasacchi. "A
visual sensor network for object recognition: Testbed realization." In Proc. of International
Conference on Digital Signal Processing (DSP). 2013.
[18] Wang, Yong, Dianhong Wang, and Wu Fang. "Automatic node selection and target tracking in
wireless camera sensor networks." Computers & Electrical Engineering 40, no. 2 (2014): 484-493.
[19] Eriksson, Emil, György Dán, and Viktoria Fodor. "Prediction-based load control and balancing for
feature extraction in visual sensor networks." Acoustics, Speech and Signal Processing (ICASSP),
2014 IEEE International Conference on. IEEE, 2014.
[20] Sobral, Andrews, and Antoine Vacavant. "A comprehensive review of background subtraction
algorithms evaluated with synthetic and real videos."Computer Vision and Image Understanding 122
(2014): 4-21.
[21] Connell, Jonathan H. "Method and apparatus for maintaining a background image model in a
background subtraction system using accumulated motion." U.S. Patent No. 8,630,442. 14 Jan. 2014.
[22] Szwoch, Grzegorz. "Extraction of stable foreground image regions for unattended luggage
detection." Multimedia Tools and Applications (2014): 1-26.
[23] Sonka, Milan, Vaclav Hlavac, and Roger Boyle. Image processing, analysis, and machine vision.
Cengage Learning, 2014.

10
[24] Wang, Zhou, and David Zhang. "Progressive switching median filter for the removal of impulse
noise from highly corrupted images." Circuits and Systems II: Analog and Digital Signal Processing,
IEEE Transactions on 46.1 (1999): 78-80.
[25] Urgaonkar, Bhuvan, and Prashant Shenoy. "Sharc: Managing CPU and network bandwidth in shared
clusters." Parallel and Distributed Systems, IEEE Transactions on 15.1 (2004): 2-17.
[26] Cardei, Mihaela, and Ding-Zhu Du. "Improving wireless sensor network lifetime through power
aware organization." Wireless Networks 11.3 (2005): 333-340.
[27] Mita, Takeshi, Toshimitsu Kaneko, and Osamu Hori. "Joint haar-like features for face detection."
Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on. Vol. 2. IEEE, 2005.
[28] Mita, Takeshi, Toshimitsu Kaneko, and Osamu Hori. "Joint haar-like features for face detection."
Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on. Vol. 2. IEEE, 2005.
[29] Lindsay, J. B., J. M. H. Cockburn, and H. A. J. Russell. "An integral image approach to performing
multi-scale topographic position analysis." Geomorphology (2015).
[30] Netravali, Arun. Digital pictures: representation and compression. Springer Science & Business
Media, 2013.
[31] Wechsler, Harry, et al., eds. Face recognition: From theory to applications. Vol. 163. Springer
Science & Business Media, 2012.
[32] Yousefi, SH., Aghdasi S.H. "Energy Aware Multi-object Detection Method in Visual Sensor
Networks", 5th International Conference on Computer and Knowledge Engineering (ICCKE), 2015.
[33] Tavli, Bulent, et al. "A survey of visual sensor network platforms." Multimedia Tools and
Applications 60.3 (2012): 689-726.
[34] Yildiz, Huseyin Ugur, et al. "Maximizing Wireless Sensor Network lifetime by
communication/computation energy optimization of non-repudiation security service: Node level
versus network level strategies." Ad Hoc Networks 37 (2016): 301-323.
[35] Li, Wei, et al. "Multiple feature points representation in target localization of wireless visual sensor
networks." Journal of Network and Computer Applications 57 (2015): 119-128.
Authors
Shamim Yousefi received the B.S. degree in Information Technology Engineering and
M.S. degree in Computer Engineering (Software) from University of Tabriz, Tabriz, Iran
in 2013 and 2015, respectively. Currently, she is working as a researcher at the Wireless
Ad hoc and Sensor networks research Laboratory (WASL) in University of Tabriz. Her
current interests include light weight methods for object detection and recognition in
visual sensor networks.
Samad Najjar Ghabel is a lecturer at University of Mohaghegh Ardebili, Ardebil, Iran.
He received the B.S. degree in Computer Engineering (Software) from University of
Mohaghegh Ardebili, Ardebil, Iran and M.S. degree in Computer Engineering
(Software) from University of Tabriz, Tabriz, Iran in 2013 and 2015, respectively. His
main interests are Visual sensor networks, Computer Networks, networks security,
developing and modeling software.

A Survey on Object Detection Methods in Visual Sensor Networks

Recommended

More Related Content

What's hot (19)

Similar to A Survey on Object Detection Methods in Visual Sensor Networks (20)

Recently uploaded (20)

A Survey on Object Detection Methods in Visual Sensor Networks