Surveillance of Vehicle Objects with Aerial Images Using Localization and Posture Based Local Gradient Model

Traffic scenes in road network needs to be monitored in different dimensional perspective to address the issues generated at various time instances. One of the major challenges observed in traffic scenes in road network is to address the vehicle tracking at different dimensional perspective for various time instances. One such application that has received greater significance is the mechanism to develop a full proof vehicle traffic control scheme. Videos fitted on different proposition of the signal junction able to view at respective image positioning and the overall traffic may rise to abnormality. Many studies have been examined for vehicle traffic control scheme. The recently used scheme is model based on simple object recognition and localization of road vehicles based on the position and orientation of vehicle image data. But the drawback of the approach is that if the shape of the vehicle and its pose varies in multiple junction coordination, the model based recognition is an inefficient one. To overcome the issues, in this work we are going to implement surveillance image object recognition and localization using improved local gradient model. The vehicle-object shape recognition and pose recovery in the traffic junction is carried out for varied traffic densities. An experimental evaluation is carried out to estimate the performance of the proposed Surveillance of Vehicle Object Recognition and Localization (SVORL) using improved gradient model in terms of vehicle density, traffic junction points, and computation time and compared with an existing model based on simple object recognition and localization.