BIKE RIDE SAFETY MANAGEMENT SYSTEM

Abstract : Motorcycle accidents have been rapidly growing through the years in many countries. In India more than 37 million people use two wheelers. Therefore, it is necessary to develop a system for automatic detection of helmet and triples wearing for road safety. Therefore, a custom object detection model is created using a Machine learning based algorithm which can detect Motorcycle riders. On the detection of a Helmetless rider, the License Plate is extracted and the Licence Plate number is recognized using an Optical Character Recognizer. This Application can be implemented in real-time using a Webcam or a CCTV as input.

 EXISTING SYSTEM :

 • Bicycle crushes with automobile vehicles in roads mostly in curved roads and kills thousands of bicyclist with great injuries in every year. This fact indicates the importance of advancement in conventional vehicle systems. • To enable migration to take place from existing urban traffic management systems and equipment. • Major reasons for road accident are failure to look, crossing roads, executing wrong turn, too fast motor vehicles. Besides, tracking the location can increase accessibility of services and it is important for providing high quality services

 DISADVANTAGE :

 • By default we use a soft linear SVM trained with SVM Light (slightly modified to reduce memory usage for problems with large dense descriptor vectors). • To achieve this result, we focused on two problems: localizing objects with a deep network and training a high-capacity model with only a small quantity of annotated detection data. • This issue was too costly (in time) to probe in the past, but becomes practical with Fast R-CNN. To understand the impact of this choice, we implemented post-hoc SVM training with hard negative mining in Fast R-CNN.

 PROPOSED SYSTEM :

 • The proposed methodology for feature extraction using LBP based hybrid descriptor, HOG and Hough transform descriptors. • Whereas absorbed grey level co-occurrence matrix along with LBP for feature extraction. • YOLOv2 and COCO dataset can be worked to detect different types of objects and classify them accordingly. The intended object are motorcycle, motorcyclists, pedestrians and workers. • Exploit colour space transformation and colour feature discrimination for detecting the helmet and triples. GLCM statistical features and Back-Propagation artificial neural network is used to detect helmet and triples more effectively.

 ADVANTAGE :

 • Our detector uses a simpler architecture with a single detection window, but appears to give significantly higher performance on pedestrian images. • This paper is the first to show that a CNN can lead to dramatically higher object detection performance on PASCAL VOC as compared to systems based on simpler HOG-like features. • Fast R-CNN builds on previous work to efficiently classify object proposals using deep convolutional networks. We propose a more efficient training method that takes advantage of feature sharing during training.