Machine vision techniques for motorcycle safety helmet detection

Waranusast, Rattapoom; Bundon, Nannaphat; Timtong, Vasan; Tangnoi, Chainarong; Pattanathaburt, Pattanawadee

doi:10.1109/ivcnz.2013.6726989

Cited by 84 publications

(33 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Experimental evaluation of the proposed approach has been performed on UIUC Image Database for Car Detection. The database consists of 1050 training images with 550 car and 500 non-car images, 170 single-scale test images containing 200 cars at roughly the same scale as in the training images, 108 multi-scale test images containing 139 cars at various scales [11]. The images are in gray-scale in pgm format.…”

Section: Experimental Evaluationmentioning

confidence: 99%

Accident Prevention and Traffic Control by Otsu Method and Haar-Cascade Hand Detector

Suma,

Sunitha,

Avanija

2019

IJEAT

View full text Add to dashboard Cite

The rapid development of economy and continuous improvement of people's purchase ability in every country, purchasing the motor vehicles is increasing rapidly, so as the traffic accidents and accident death rate, which says the road traffic situation in everywhere, is worse day by day. Traffic and Accident control is a complex activity in developing countries shows in increasing number of riders and automobiles every day. The prediction and prevention of traffic accidents is an important part of the traffic safety, the purpose of prediction is to achieve the objective of reducing traffic accidents. The work proposes by using the existing video through the cameras positioned on highways, traffic signal and busy roads that can detect the incidents/events. The system can also be proposed with the ability to read and track the vehicle number helps in searching of vehicles violating the rules by finding the License plate number using Optical Recognition method which finds the alpha numeric character from the segmented image. Counting the vehicles passed through the mentioned place using Haar-cascade hand detector which helps to count the number of vehicles passed through can perform Traffic control system.

show abstract

Section: Experimental Evaluationmentioning

confidence: 99%

Accident Prevention and Traffic Control by Otsu Method and Haar-Cascade Hand Detector

Suma,

Sunitha,

Avanija

2019

IJEAT

View full text Add to dashboard Cite

show abstract

“…Basically helmet detection system involves following steps such as collection of dataset, moving object detection, background subtraction, object classification using neural networks and extraction of licence plate number if the rider is not wearing helmet. Rattapoom Waranusast et al [2] used KNN classifier for moving object extraction and classification.…”

Section: Introductionmentioning

confidence: 99%

Detection of Non-Helmet Riders and Extraction of License Plate Number using Yolo v2 and OCR Method

J.*¹,

Tejas²,

Varshad³

et al. 2019

IJITEE

View full text Add to dashboard Cite

In current situation, we come across various problems in traffic regulations in India which can be solved with different ideas. Riding motorcycle/mopeds without wearing helmet is a traffic violation which has resulted in increase in number of accidents and deaths in India. Existing system monitors the traffic violations primarily through CCTV recordings, where the traffic police have to look into the frame where the traffic violation is happening, zoom into the license plate in case rider is not wearing helmet. But this requires lot of manpower and time as the traffic violations frequently and the number of people using motorcycles is increasing day-by-day. What if there is a system, which would automatically look for traffic violation of not wearing helmet while riding motorcycle/moped and if so, would automatically extract the vehicles’ license plate number. Recent research have successfully done this work based on CNN, R-CNN, LBP, HoG, HaaR features,etc. But these works are limited with respect to efficiency, accuracy or the speed with which object detection and classification is done. In this research work, a Non-Helmet Rider detection system is built which attempts to satisfy the automation of detecting the traffic violation of not wearing helmet and extracting the vehicles’ license plate number. The main principle involved is Object Detection using Deep Learning at three levels. The objects detected are person, motorcycle/moped at first level using YOLOv2, helmet at second level using YOLOv3, License plate at the last level using YOLOv2. Then the license plate registration number is extracted using OCR (Optical Character Recognition). All these techniques are subjected to predefined conditions and constraints, especially the license plate number extraction part. Since, this work takes video as its input, the speed of execution is crucial. We have used above said methodologies to build a holistic system for both helmet detection and license plate number extraction.

show abstract

“…However, it comes with a high risk of accidents. To reduce the involved risk, it is ideal for motorcyclists to use helmet [1][2][3][4][5][6][7][8]. Considering this, the government has made it a punishable offence to ride a motorcycle without the helmet [9].…”

Section: Introductionmentioning

confidence: 99%

Helmet Detection on Two-Wheelers and Number Plate Recognition using Image Processing

2019

IJRTE

View full text Add to dashboard Cite

There has been a sudden increase in motorcycle accidents over the years. The helmet is a safety equipment that protects the motorcyclists, however many riders (i.e. students) don’t use it and the results could be fatal. This paper holds an agenda to propose a system for detection of motorcyclists without helmet. The proposed idea first detects motorcycle riders using surveillance video using background subtraction and object segmentation methods. We have also used techniques that involve human face detection using image processing. This includes face detection using Haar like feature technique and circular Hough transform method that helps in detecting any circular object hence detecting the helmet. This approach works in the near real time mode with significantly low false alarms.

show abstract

Machine vision techniques for motorcycle safety helmet detection

Cited by 84 publications

References 9 publications

Accident Prevention and Traffic Control by Otsu Method and Haar-Cascade Hand Detector

Accident Prevention and Traffic Control by Otsu Method and Haar-Cascade Hand Detector

Detection of Non-Helmet Riders and Extraction of License Plate Number using Yolo v2 and OCR Method

Helmet Detection on Two-Wheelers and Number Plate Recognition using Image Processing

Contact Info

Product

Resources

About