Vehicle Identification and Classification System
- 1. Vehicle Identification and Classification System DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING Institute of Engineering and Technology, Lucknow Project Presentation Information Technology Program (A self – financed course) Vishal Polley(1505213053) Shreyas Singh (1505213044) SupervisedBy - Prof. Y. N. Singh Ms. Shipra Gautam
- 2. Contents : • Introduction • Problem Statement • Applications • Vehicle RecognitionProcess • References
- 3. Introduction
- 4. Introduction • The VICS system for identificationand classification of moving vehicles on the road side from the videos is a great importance today. • It is an activeresearch area in IntelligentTransportation Systems (ITS). • Vehicle recognitionhas been an area of recent interest tothe Computer Vision community,no prior research study has been used to build an on- road vehiclerecognition.
- 5. Computer Vision Computervisionis an important field of artificial intelligence where decision about real worldscene having high dimensional data is taken.
- 6. Cont. Applications of Computer Vision
- 8. Problem Statement • The main goal of our project is to implement an efficient method for recognizing vehicles in Indian conditions. There are some challenges in these conditions that makes vehicle recognition much harder. 1. In India, most of the cases traffic system is non lane based. 2. Road conditions are more variedand traffic is unstructured. 3. Vehicles are parked frequently by the sides of the roads. 4. Within same vehicle class there are large variety’s and models. These looks different in size and appearance. It is generally observed in Indian vehicleslike cars and Truck’s. 5. Shapes of the vehicles have a key role in recognition, there is high intra- class variance among Indian vehicles.
- 9. Challenges • Vehicle recognitiontask deals withonly images in outdoor or natural lighting it is known to cause noise related problems. • The other is typical geometry of vehicles. Vehicles chassis are constructed in a significantly greater variety of geometriesas compared to other objects. There are number of dissimilarities in vehicleslike height, number of wheels, body shape and color.
- 10. Sample Images from Indian Vehicle database includes four classes (Truck, Auto, Bus and Car respectively). Images were captured with variancein pose, view and lightning constraints.
- 11. Applications
- 12. Applications • Electronic toll collectionmanagement. • Identification of unauthorized vehicles on roads as a part of vehicle surveillance and traffic data analysis. • License plate localization. • Computerassisted driving. • Methods for reducing road accidents.
- 13. Traffic Management System • The traffic on the roads is increasing day by day. There is dire need of developing an automation system that can effectively manage and control the traffic on roads.
- 15. Vehicle Recognition Process • Vehicle recognitionprocess in Indian scenario has several challenges. To address these challenges features of an individual vehicle from different directions are to be considered. • We are using Bag of features (BOF) and Support vectormachines for vehicle recognition.
- 17. Process • Bag of Features (BOF) works on the principle that every object can be represented by its parts. For example,a Truck contains parts like big- tyres, number plate, cabin etc. Also car contains wheels, number plate and windows, but the basic difference between an Truck and car is observed to be in size and tyres. So, in order to recognize an object it is necessary to first recognize the parts of it and based on the parts identify the object correctly. • Basing on above principle vehicle recognitionprocess is initiatedto recognize parts of the vehicle images by extracting image patches. This can be done by the combination of Harris corner and Sift points because these contain rich local information of the image.
- 18. Cont. • For each patch, descriptors were calculated in the form of vectors. To address the cardinal and ordering problems, clusters are generated by apply K-means algorithm on these descriptors. Each cluster is refereed as word for an image. Thus image is represented as a bag of words or bag of visual words. These wordsare represented as a histogram and referring as histogram of features. Features obtained in the above process are classified by train and test process using SVM.
- 19. Reasons of using SVM • The reason for the select of SVM as a classifier is that, it has some superiority over other approaches. The important points are global minimumsolution, learning and generalization in huge dimensional input spaces, use of kernel function and classification is done by the separating hyper plane at a maximum distance to the closest points in the training set.
- 20. Challenges • Objects in small size • Novel model • Clutter • Poor quality images
- 21. References • R.S Vaddi, L.N.P Boggavarapu, K.R Anne, "ComputerVision based Vehicle Recognitionon Indian Roads", International Journal Of Computer Vision And Signal Processing, 5(1), 8-13(2015) • Baljit Singh Mokha and Satish Kumar, A Review Of Computer Vision System For The Vehicle Identification And Classification From Online And Offline Videos.
- 22. Thank You