Project DetailsThe goal of this work is to build an algorithm that analyse spatial parameters using simple and inexpensive sensors and a limited calculation cost. The current method of identifying objects in a given space and extracting its active properties requires a large number of advanced sensors and expensive processing power. We suggest the option of reducing the computing power and the number of sensors used while maintaining the output quality.
The proposed solution is based on a visual system inspired by flying insects and the algorithm is implemented using signal processing tools.
We reviewed several possible solutions, creating a generic interface for simulating visual systems using fewer sensors and creating a dataset of varied captured movements that will be used as input for the algorithm.
The results of this project demonstrate the feasibility of the algorithm. An infrastructure for further research was created as well as documentation of a fundamental database.
A motion-direction-detection model was implemented for the acquired sequence of images. The results obtained from the model were analyzed and a generic software interface was created, that could be used to test and put together different versions of additional models.
