Embedded GPU-accelerated combinatorial kalman filter for lane tracking system | |
| Author | Attanayake, Sachini |
| Call Number | AIT Caps. Proj. no.EL-15-10 |
| Subject(s) | Tracking (Engineering) Kalman filtering |
| Note | A capstone project report submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Engineering Electronic Engineering, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Caps. Proj. ; no. EL-15-10 |
| Abstract | Road safety is an important fact in automobile industry. Each year countless deaths and injuries occur by road accidents. Autonomous driving and driver assistance systems can help to reduce this huge number of human fatalities considerably. Road lane detection and tracking systems plays a vital role in such systems. Such systems have noise and need a filter to remove the noise. A Kalman tracker is often quite robust in such environments with noise. A combinatorial Kalman filter differs from common Kalman filter as it takes one or more input at a stage and outputs more estimates, in a way that all the combinations are considered. It needs tremendous amount computational power and hardware resources as the variables associated keeps growing in size in each iterative loops. It needs to account one or more inputs at a given time and outputs estimates. This way all the combinations are included. In this paper the author utilizes GPU accelerating combinatorial Kalman filter for road tracking system. Its observed that combinatorial Kalman filter can be accelerated on embedded GPU where CPU systems seems not so convenient for huge amount of computational load associated with combinatorial Kalman filter. |
| Year | 2015 |
| Corresponding Series Added Entry | Asian Institute of Technology. Caps. Proj. ; no. EL-15-10 |
| Type | Project |
| School | School of Engineering and Technology (SET) |
| Department | Bachelor Degree |
| Academic Program/FoS | Electronic Engineering (EL) |
| Chairperson(s) | Mongkol Ekpanyapong; |
| Examination Committee(s) | Dailey, Matthew;Manukid Parnichkun; |
| Degree | Capstone Project (B.Sc.)-Asian Institute of Technology, 2015 |