Beruflich Dokumente
Kultur Dokumente
MR.RAGHAVENDRA N S
3RD YEAR, IS&E
RAGHAVENDRANS1998@GMAIL.COM
MR. SUKRUTH R
3RD YEAR, IS&E
VIVEKSUKRUTH@GMAIL.COM
PROJECT GUIDE
DR. SANJAY H A
PROF AND HEAD, IS&E
SANYA.HA@NMIT.AC.IN
INSTITUTION
NITTE MEENAKSHI INSTITUTE OF TECHNOLOGY (NMIT) BANGALORE
PROJECT ABSTRACT
In this project we have worked on the problem of human detection, face detection, face
recognition and tracking an individual. Our project is capable of detecting a human and its face
in a given video and storing Local Binary Pattern Histogram (LBPH) features of the detected
faces. LBPH features are the key points extracted from an image which is used to recognize
and categorize images. Once a human is detected in video, we have tracked that person
assigning him a label. We have used the stored LBPH features of individuals to recognize them
in any other videos. After scanning through various videos our program gives output like-
person labeled as subject1 is seen in video taken by camera1, subject1 is seen in video by
camera2. In this way we have tracked an individual by recognizing him/her in the video taken
by multiple cameras. Our whole work is based on the application of machine learning and
image processing with the help of openCV, an open source computer vision library.
INTRODUCTION
PROBLEM STATEMENT: HUMAN DETECTION AND RECOGNITION
The observation or monitoring of the activity, behavior and other information by a system
which include several Closed Circuit Television (CCTV) cameras for observation and a set of
algorithms to track a person is called Surveillance system. Technology has evolved a lot in the
last few decades, previously there were no security cameras neither in Banks, Railway Station
nor at other places. There were only security guards which protect these areas. Once the
security cameras came into existence, it became easy to find people passing within the range
of CCTV camera by simply searching through the videos recorded. Inventions increases
people’s expectations, although security camera reduces human effort but one has to search
for an individual through entire video which takes a considerable amount of time. So people
thought what if searching task can be accomplished by machine, it would save both human
effort and time. A combination of machine learning with image processing is used to make a
machine learn to recognize a person and track that person in the given footage. Our project is
all about a system which have been designed to track human in the given videos. We have
trained our machine for some people assigning label to each, so that when he/she have
appeared in a video or more than one videos he/she have been recognized by our system
assigning him/her label. In this way a person have been recognized and tracked in a given
videos.
2
Human detection and recognition has lot of Advantages:
The most obvious application of detecting humans in surveillance video is to early detect an
event that is not normal. Detecting sudden changes and motion variations in the points of
interest and recognizing human action could be done by constructing a motion similarity
matrix or adopting a probabilistic method . Methods based on probability statistics use the
minimum change of time and space measure to model the method of probability.
Detecting and counting persons in a dense crowd is challenging due to occlusions. The
proposed system was applied for detecting individual heads in dense crowds of 30 to 40 people
against cluttered backgrounds from a single video frame. However, the performance of their
approach may be challenged by the colour intensities of the heads to be detected.
A person in a visual surveillance system can be identified using face recognition and gait
recognition techniques. The detection and tracking of multiple people in cluttered scenes at
public places is difficult due to a partial or full occlusion problem for either a short or long
period of time. . The wider application of human detection is not only limited to analysis
surveillance videos but also extended to player tracking and identification in sport videos.
3
TECHNIQUES
Human detection in a smart surveillance system aims at making distinctions among moving
objects in a video sequence. The successful interpretations of higher level human motions
greatly rely on the precision of human detection. The detection process occurs in two steps:
object detection and object classification.
4
Non-parametric background model. Sometimes, optimization of parameters for a
specific environment is a difficult task. Thus, a number of researchers introduced non-
parametric background modelling techniques Non-parametric background models
consider the statistical behaviour of image features to segment the foreground from
the background. In a non-parametric model is proposed for background modelling,
where a kernel-based function is employed to represent the colour distribution of each
background pixel. The kernel-based distribution is a generalization of MoG which does
not require parameter estimation. The computational requirement is high for this
method. Kim and Kim proposed a non-parametric method, which was found effective
for background subtraction in dynamic texture scenes (e.g. waving leaves, spouting
fountain and rippling water). They proposed a clustering-based feature, called fuzzy
colour histogram (FCH) to construct the background model by computing the similarity
between local FCH features with an online update procedure. Although the processing
time was high in comparison with the adaptive Gaussian mixture model the false
positive rate of detection is significantly low at high true positive rates.
Temporal differencing. The temporal differencing approach involves three important
modules: block alarm module, background modelling module and object extraction
module. The block alarm module efficiently checked each block for the presence of
either a moving object or background information. This was accomplished using
temporal differencing pixels of the Laplacian distribution model and allowed the
subsequent background modelling module to process only those blocks that were
found to contain background pixels. Next, the background modelling module is
employed in order to generate a high-quality adaptive background model using a
unique two-stage training procedure and a mechanism for recognizing changes in
illumination. As the final step of their process, the proposed object extraction module
computes the binary object detection mask by applying suitable threshold values. This
is accomplished using their proposed threshold training procedure.
.
5
PROJECT FLOW DESIGN
6
SYSTEM REQUIREMENTS:
SOFTWARE REQUIREMENTS
1) Python
2) OpenCV
3) NodeJS
4) Scikit-learn
HARDWARE REQUIREMENTS:
EXPECTED RESULTS:
RESULTS
Several videos containing different actions were taken under varied conditions in terms of
illumination, location, and background. Frame by frame extraction from these videos is
performed. Each frame is firstly labeled in accordance with its semantic content manually.
Each stream of frames belonging to a specified class is bifurcated and kept in a folder
maintaining its sequence. Hence several samples of each action are segmented from the
videos manually. Each sample is a stream of videos belonging to specific action. In the next
step the background or the effect of background is removed from the frame. Two different
strategies are followed for this purpose. With the first method, background is removed by
firstly taking a blank frame which only contains the background and then subtracting this
frame from the one containing a foreground. As a result background will be eliminated.
The other method used for this purpose takes the difference of two successive frames. The
resultant frame will contain just the change that occurred due to motion dynamics. Once
the effect of background has been countered then for all resultant frames a corresponding
feature vector is formed. The feature vector of a frame contains the raw, central, scale, and
rotation invariant moments of the image besides its centroid and eccentricity .
7
PROJECT TIMELINES:
THE PROJECT WOULD TAKE AROUND 3 MONTHS TO COMPLETE WITH ALL THE MODULES
REFERENCES
Ahonen, T., Hadid, A., and Pietikainen, M. Face Recognition with Local
Binary Patterns. Computer Vision - ECCV 2004 (2004), 469481.
https://en.wikipedia.org/wiki/Supportvectormachine/media/F ile :
KernelMachine.s