Research
Video Based Vehicle Detection and Tracking Using Image Processing and Deep Learning Using Customised Dataset (Final Academic Thesis 2021,yet to be published in gernal )
Abstract:
In today’s world, the intelligent transportation system plays a crucial role in the field of traffic management to provide an efficient and reliable transportation system. One of the applications of the intelligent transportation system is to detect and track vehicles accurately. Smart detection and tracking systems require the collection of processed data from respective procedures for the regulation of classifying. In this regard, surveillance cameras have been installed in monitoring and control of traffic in the last few years. Image processing algorithms have been widely developed to monitor the motion of vehicles, humans, or any other objects. Video processing of traffic data obtained through prerecorded video is an instance of applications for advanced cautioning or data extraction for real-time analysis of vehicles. However, the traditional vehicle systems may be declined and not recognized well due to the vehicles being occluded by other vehicles or by background obstacles such as road signals, trees, weather conditions and the performance of these systems depend on a good traffic image analysis approaches to detect, track and classify the vehicles. Here we have studied and analyzed previous works done on this area, identified the research scope, understand the process, methods used, and finally, propose a model that might help us in vehicle detection and tracking with great accuracy.
Local Vehicle Detection using machine learning - Hog + SVM (Project based research 2021)
Abstract: Vehicle detection is a very essential application for driver assistance system and autonomous self guided vehicles . In Bangladesh, there are various kinds of local vehicles like- rickshaw, CNG, leguna which we can see everyday on the road .For this project, a new high definition local vehicle dataset, containing 25,000 images is made on perspective of Bangladesh .This research work propose a video based vehicle detection. Experimental results using video collected from real world scenarios are provided, showing that the proposed method possesses accuracy and it can detect vehicle targets successfully in real life environment. The focus of the paper is to solve the problem of feature extraction and classification for detecting local vehicles . Thus, we propose using Histogram of Oriented Gradient(HOG) for feature extraction and Support Vector Machine(SVMs) for vehicle detection .The goal of this study is to identify the local vehicles individually and find the accuracy. We have also discussed general challenges and future work scopes and plans.