Development of the video stream object detection algorithm (VSODA) with tracking
Journal Title: EAI Endorsed Transactions on Energy Web - Year 2019, Vol 6, Issue 22
Abstract
The object tracking is one of the most important task in video analysis. Many methods have been proposed such as TLD (Tracking, Learning, Detection), Meanshift and MIL but they show good accuracy in laboratory cases, not in real ones, where the accuracy is defined as a numerical difference between computed object coordinates and the real ones. One of the reasons is lack of information about tracked object and environment changes. If a method has the prior information about tracked object, then it will be able to perform with higher accuracy. Some of the newest object tracking methods such as GOTURN use trained CNN (convolutional neural network) and have better accuracy because of knowledge about how the tracked object looks like in different situations such as light intensity changes and tracked object’s rotations. If we use only a classification algorithm (classifier) then it can find an object that was in training set with high probability. But if its appearance is changing it will be lost when deviation will be higher than trust limit. Then it is important to have parts of prior and posterior information about tracked object. The prior information is given by detector (CNN) and posterior information – by tracking algorithm (TLD). One of the biggest detector problems is high computational complexity in terms of operations’ number and one of the solutions is to use the classifier in parallel with the tracker. In future work we are going to use different sensors, not only RGB camera, but RGBD camera, which may improve accuracy due to higher amount of information.
Authors and Affiliations
A. Y. Zarnitsyn, A. S. Volkov, A. A. Voycehovsky, B. I. Pyakillya
Keywords
Related Articles
- EP ID EP45419
- DOI http://dx.doi.org/10.4108/eai.22-1-2019.156385
- Views 233
- Downloads 0
Control law synthesis of the wind-driven power-plant with variable geometry
The analysis and synthesis of aerodynamic properties of the wind-driven power-plant (WP) construction with a vertical axis of rotation and useful interference of the stator and the rotor, that exceeds classical type anal...
Extracting Academic Subjects Semantic Relations Using Collocations
The paper presents approach to analyze semantic content of academic subjects and its internal relations using statistically-based techniques for collocation extraction from large electronic educational text corpus. It off...
Multi-Class Queuing Networks Models for Energy Optimization
The increase of energy consumption and the related costs in large data centers has stimulated new researches on techniques to optimize the power consumption of the servers. In this paper we focus on systems that should p...
Methodology for Commercial Buildings Thermal Loads Predictive Models Based on Simulation Performance
Commercial buildings incorporate Building Energy Management Systems (BEMS) to monitor indoor environment conditions as well as controlling Heating Ventilation and Air Conditioning (HVAC) systems. Measurements of temperat...
Role of the SPbPU-FESTO «Synergy» Centre in the Development of Engineering Competences and Skills
Web and Internet technologies for education of university students and for engineering staff (continuing education) on electrical engineering are considered. The Web and Internet technologies form an important part in mo...