Real-time video scene analysis with heterogeneous processors

Blair, Calum Grahame (2014) Real-time video scene analysis with heterogeneous processors. EngD thesis, University of Glasgow.

Full text available as:
[thumbnail of 2014BlairEngD.pdf] PDF
Download (26MB)
[thumbnail of Bank Street Auto video from chapter 6] Multimedia file (Bank Street Auto video from chapter 6)
Download (33MB)
Printed Thesis Information:


Field-Programmable Gate Arrays (FPGAs) and General Purpose Graphics Processing Units (GPUs) allow acceleration and real-time processing of computationally intensive computer vision algorithms. The decision to use either architecture in any application is determined by task-specific priorities such as processing latency, power consumption and algorithm accuracy. This choice is normally made at design time on a heuristic or fixed algorithmic basis; here we propose an alternative method for automatic runtime selection.

In this thesis, we describe our PC-based system architecture containing both platforms; this provides greater flexibility and allows dynamic selection of processing platforms to suit changing scene priorities. Using the Histograms of Oriented Gradients (HOG) algorithm for pedestrian detection, we comprehensively explore algorithm implementation on FPGA, GPU and a combination of both, and show that the effect of data transfer time on overall processing performance is significant. We also characterise performance of each implementation and quantify tradeoffs between power, time and accuracy when moving processing between architectures, then specify the optimal architecture to use when prioritising each of these.

We apply this new knowledge to a real-time surveillance application representative of anomaly detection problems: detecting parked vehicles in videos. Using motion detection and car and pedestrian HOG detectors implemented across multiple architectures to generate detections, we use trajectory clustering and a Bayesian contextual motion algorithm to generate an overall scene anomaly level. This is in turn used to select the architectures to run the compute-intensive detectors for the next frame on, with higher anomalies selecting faster, higher-power implementations. Comparing dynamic context-driven prioritisation of system performance against a fixed mapping of algorithms to architectures shows that our dynamic mapping method is 10% more accurate at detecting events than the power-optimised version, at the cost of 12W higher power consumption.

Item Type: Thesis (EngD)
Qualification Level: Doctoral
Keywords: fpga, gpu, heterogeneous architecture, object detection, computer vision
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Colleges/Schools: College of Science and Engineering
College of Science and Engineering > School of Engineering
Precurrent Departments
Supervisor's Name: Robertson, Dr Neil M
Date of Award: 2014
Depositing User: Dr Calum G Blair
Unique ID: glathesis:2014-5061
Copyright: Copyright of this thesis is held by the author.
Date Deposited: 08 Jul 2014 15:03
Last Modified: 08 Jul 2014 15:05

Actions (login required)

View Item View Item


Downloads per month over past year