Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Object Tracking System for Traffic Surveillance


Affiliations
1 Goa College of Engineering, Goa University, Goa, India
2 Information Technology, India
     

   Subscribe/Renew Journal


This paper proposes a technique for identifying a moving object in a video clip of stationary background for real time system and discusses one application that is traffic surveillance. We present a framework for detecting some important but unknown knowledge like vehicle identification and traffic flow count. The objective is to monitor activities at traffic intersections for detecting congestions, and then predict the traffic flow which assists in regulating traffic. Dynamic objects detection involves vehicle detection through background foreground segmentation and TLD. Tracking-Learning-Detection (TLD) is novel system for long-term tracking of objects in unconstrained videos and is built on the fly. The system extends TLD with the concept of a generic detector and a validator which is designed for real-time vehicle tracking. The off-line trained detector localizes the structure of vehicle given by vehicle detection and classification algorithm and the online trained validator decides which objects correspond to the tracked subject.

Keywords

Background Registration, Vehicle Tracking, Video Segmentation, Traffic Surveillance.
User
Subscription Login to verify subscription
Notifications
Font Size

Abstract Views: 211

PDF Views: 3




  • Object Tracking System for Traffic Surveillance

Abstract Views: 211  |  PDF Views: 3

Authors

Pooja Shet
Goa College of Engineering, Goa University, Goa, India
Sima Shetgaonkar
Goa College of Engineering, Goa University, Goa, India
Ram Naik
Goa College of Engineering, Goa University, Goa, India
Nilesh Fal Desai
Information Technology, India
Siddhi Naik
Information Technology, India

Abstract


This paper proposes a technique for identifying a moving object in a video clip of stationary background for real time system and discusses one application that is traffic surveillance. We present a framework for detecting some important but unknown knowledge like vehicle identification and traffic flow count. The objective is to monitor activities at traffic intersections for detecting congestions, and then predict the traffic flow which assists in regulating traffic. Dynamic objects detection involves vehicle detection through background foreground segmentation and TLD. Tracking-Learning-Detection (TLD) is novel system for long-term tracking of objects in unconstrained videos and is built on the fly. The system extends TLD with the concept of a generic detector and a validator which is designed for real-time vehicle tracking. The off-line trained detector localizes the structure of vehicle given by vehicle detection and classification algorithm and the online trained validator decides which objects correspond to the tracked subject.

Keywords


Background Registration, Vehicle Tracking, Video Segmentation, Traffic Surveillance.