Abstract
Blob detection is a common task in vision-based applications. Most existing algorithms are aimed at execution on general purpose computers; while very few can be adapted to the computing restrictions present in embedded platforms. This paper focuses on the design of an algorithm capable of real-time blob detection that minimizes system memory consumption. The proposed algorithm detects objects in one image scan; it is based on a linked-list data structure tree used to label blobs depending on their shape and node information. An example application showing the results of a blob detection co-processor has been built on a low-powered field programmable gate array hardware as a step towards developing a smart video surveillance system. The detection method is intended for general purpose application. As such, several test cases focused on character recognition are also examined. The results obtained present a fair trade-off between accuracy and memory requirements; and prove the validity of the proposed approach for real-time implementation on resource-constrained computing platforms.
Highlights
Consumption of automated image recognition technology has been growing steadily over the past few years [1,2,3]
We have evaluated the results of the proposed blob detection approach in an automated surveillance context, as part of an embedded vision-based architecture that has been implemented on an field programmable gate array (FPGA)
We evaluate its performance with various images that test general detection for use in other applications
Summary
Consumption of automated image recognition technology has been growing steadily over the past few years [1,2,3]. Modern image processing applications must support complex computations on large streams of visual data This technology could be provided by personal computers; power consumption, size and mobility are commonly desired and often forbid the use of such devices in many vision applications. Object detection deals with the extraction and measurement of the objects that are present in the scene This task can be further sub-divided into two operations: background segmentation and blob analysis. In typical EV operations, bottlenecks arise due to high data transfers (image information stored on memory devices), algorithm implementation (serial vs parallel) and hardware resources (CPU vs GPU). We propose the use of a data tree intended for classification of each blob according to its detection history This makes analysis direct, as each class involves a defined set of operations that do not require broad computational overhead.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
