Scribd
Upload
14 views14 pages

Vehicle Speed Estimation

The project focuses on developing a vision-based system for vehicle counting, speed estimation, and classification using legacy camera footage, aiming to reduce reliance on costly RADAR devices. It employs computer vision techniques and deep learning models to accurately detect and track vehicles, achieving a speed estimation accuracy between 87.01% and 99.38%. Future enhancements may include improved accuracy, efficiency, and the ability to detect abnormal traffic events.

Uploaded by

padmanathan423
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
14 views14 pages

Vehicle Speed Estimation

The project focuses on developing a vision-based system for vehicle counting, speed estimation, and classification using legacy camera footage, aiming to reduce reliance on costly RADAR devices. It employs computer vision techniques and deep learning models to accurately detect and track vehicles, achieving a speed estimation accuracy between 87.01% and 99.38%. Future enhancements may include improved accuracy, efficiency, and the ability to detect abnormal traffic events.

Uploaded by

padmanathan423
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 14

EVALUATION OF THE PROJECT

Speed Estimation and Classiftcation using Legacy Camera System

Name of the Students : 1. k.PADMANATHAN(40620U09008)


2. P.DANUSH(40620U09003)
3.S.ANU(40620U09001)
4. S.VAISHNAVI(40620U09007)
5.K.JANAKI(40620U09007)

Project guide :

Department : Bachelor of Computer Application

Name of the College : SRI ARAVINDAR ARTS AND SCIENCE COLLEGE


Introduction / Problem definition

The Police make use of RADAR device to detect the speed of the vehicle, which should be placed
at a certain distance.
 This requires manpower for focusing the vehicles and also it must be kept in most of the
highways which is expensive.
 Intelligent transportation frameworks have gotten progressively significant in numerous cutting-
edge urban communities as governments depend more on them to empower smart decision making,
and better use of the current foundation.
 To resolve the above problem, we are composing a system to extract traffic data from videos
captured by legacy cameras.
From the extracted data we can detect the vehicles as well classify them (like, Car, Bus etc..,),
speed of the detected vehicles and also keep a count on number of vehicles which passes over the
Camera by using a deep learning model.
Objectives

 The main idea of the project is to develop a vision based pipeline system that for vehicle counting,
speed estimation and vehicle classification.
 It uses computer vision techniques to extract traffic data from videos captured by cameras for
object detectors and transfer-learning to detect vehicles, pedestrians, and cyclists from monocular
videos.
 The main objective of this is to make use of a camera instead of Radar which requires man power
for focusing the vehicles and it must be kept in most of the highways.
 The existing technique which uses Radar is too costly.
 Thus, it is necessary to design a system which is affordable that includes cost effective.
Methodology

Fig . System flow Diagram


Methodology
System flow
Apply object detection to detect vehicle in a video stream.
Compute the bounding box coordinates of all detected vehicles.
Compute Euclidean distance between new bounding boxes and existing bounding box of a
vehicle.
Update bounding box coordinates of existing vehicle.
Compute the speed of vehicle using the distance/time
If any new vehicle detected, register it and assign an ID.
By keeping a track on vehicle ID, extract the new Bounding box coordinates and update.
When a vehicle crosses the threshold fov (field of view) of camera, de-register the vehicle
ID.
Implementation

MODULE 1: SPEED DETECTION METHOD

 MODULE 2: GENRATING ROI

MODULE 3:DETECTING VEHICLES


Implementation

MODULE 1: SPEED DETECTION METHOD

EUCLIDEAN DISTANCE:
def estimateSpeed(location1, location2):
d_pixels = math.sqrt(math.pow(location2[0] -
location1[0], 2) + math.pow(location2[1] -
location1[1], 2))
ppm = 8.8
d_meters = d_pixels / ppm
fps = 18
speed = d_meters * fps * 3.6 #MPH TO KMPH
return speed
Implementation

MODULE 2: GENRATING ROI


Region of interest is an operation widely used in object detection tasks using
convolutional neural networks.

#loading cascade classifier Features xml and initialing


carCascade = cv2.CascadeClassifier('/content/drive/MyDrive/myhaar.xml’)
#converting bgr image to gray image
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
#detecting roi using cascade classifier
cars = carCascade.detectMultiScale(gray, 1.1, 13, 18, (24, 24))
#adding 30 and 40 pixel extra for roi for accuracy
roi = image[y:y+h+30, x:x+w+40]
Implementation

MODULE 3: DETECTING VEHICLES


#giving roi as input to dnn for detecting vehicles
blob = cv2.dnn.blobFromImage(roi, size=(300, 300),ddepth=cv2.CV_8U)
net.setInput(blob, scalefactor=1.0/127.5, mean=[127.5,127.5, 127.5])
#running network forward for prediction
detections = net.forward()
#getting confidence of detected vehicle
confidence = detections[0, 0, i, 2]
#if confidence is greater than 40% accepted else rejected
if confidence > 0.4:
print(‘accept’)
else:
print(‘reject’)
Results
 The accuracy result for speed estimation is satisfied with minimum 87.01% and maximum
99.38%.
 The highest error for speed estimation in this system is speed estimation on high speed vehicle.
 There are still many problems on object detection method which is still be an open problem, for
example : two vehicles are near each other will be detected as one object.
 Problem on object detection process will affect speed estimation accuracy because the centroid
point is depend on object detection result.
Advantages in the project

Advantages

Our proposed pipeline combines object detection and multiple object tracking to count and classify
vehicles from video captured.
Our proposed pipeline also includes a visual classifier module.
A deep learning method is proposed to deal with the problem of vehicle colour recognition.
Potential for Future Work / Scope of Commercialization

 Further requirements and improvements can easily be done since the coding is mainly structured
or modular in nature.
 Changing the existing modules or adding new modules can append improvements.
 Further enhancements can be made to the application, such that the functions are more accurate
and efficient than the present one.
 Our future research work can be extended in several directions. We intend to deploy the proposed
method to daily operations and use the data generated for network operations, traffic flow
monitoring, and also anomaly detection.
 One of our research interests is to detect abnormal events such as pedestrians (or cyclists) on a
freeways, vehicles driving in wrong directions, vehicles driving at abnormal speeds (too fast or
too slow), and traffic accidents.
Snapshots of project
Conclusion

 The proposed project aims to bring out lesser computation and memory and stores vehicles
parameters, estimated speed of the detected vehicles in the database.
 Detection and tracking of the vehicles utilizes parameters such as position, height and width of
vehicle instead of features extraction hence proposed system can be adopted easily in existing
traffic management system.

You might also like