Professional Documents
Culture Documents
This Example
In this example, we will be detecting human faces in an image and find out distance
between them, displaying people whose faces are too close to each other.
Original Image
CODE
OPEN CV - a library of programming functions mainly aimed at real-time computer
vision.
ADVANCE VERSION
This method has a lot of disadvantages.
So, now we will detect full person and then calculate the distance between them.
Several governments and Industries in view of COVID 19 situation now wants to ensure that
social distancing is followed or not. This is a human detection system which checks
whether social distancing is followed or not and produces an alert in case it is not followed.
Problem statement:
People can use it for such situations like standing in queue and wants to
detect person after him is atleast 6 feet distance like for ulitmate solution of
coronavirus situation.It makes person notified and user can ask the nearby
person to be at some distance far from him. It also makes the problem
more easier by examining whether you have corona symptoms or not
through self assessment test. It make the authorities to even use in public
areas as it tracks the person from live camera lies at public places to detect
the person in nearby shops standing with some distance apart and stores
the captured images if we have ram available.
The technical methodology of this tool involves three main steps, which are:
Calibration
Detection and
Measurement.
Calibration
Calibration is the first step of the pipeline, which works by computing the transform,
specifically the homography that morphs a perspective view into a bird’s-eye view. In the
above video, we can notice an instance of the birds-eye view at the right corner.
In this process, the simplest calibration method involves selecting four points in the
perspective view and mapping them to the corners of a rectangle in the bird’s-eye view. The
process assumes that every person is standing on the same flat ground plane.
Detection
Detection is the second step of the pipeline that involves applying a pedestrian detector to the
perspective views to draw a bounding box around each pedestrian. For this process, the
company used an open-source pedestrian detection network based on the Faster R-CNN
architecture, non-max suppression (NMS), and various rule-based heuristics. Non-max
suppression (NMS) and various rule-based heuristics have been applied to clean up the output
bounding boxes.
Measurement
This is the third step of the pipeline, where the (x, y) location of the bounding box for each
person has been estimated in the bird’s-eye view. According to the company, the last step is
to compute the bird’s eye view distance between every pair of people and scale the distances
by the scaling factor estimated from calibration. The people whose distance is below the
minimum acceptable distance has been depicted in red, and the rest are coloured as green,
and a line is drawn between the people to emphasize this measure.