Low-level computer vision algorithms have extreme computational requirements. In this
work, we compare two real-time architectures developed using FPGA and GPU devices for …

Video semantic segmentation aims to generate an accurate semantic map for each frame in
a video. For such a task, conducting per-frame image segmentation is generally …

The proposed work presents a highly parallel architecture for motion estimation. Our system
implements the well-known Lucas and Kanade algorithm with the multi-scale extension for …

In experimental solid mechanics optical methods allow for non-contact derivation of full-field
information. In this paper, optical flow based deformation measurement routines are …

Optical flow calculation algorithms are hard to implement on the hardware level in real-time,
due to their complexity and high computational load. Therefore, presented works in the …

The Lucas-Kanade (LK) algorithm is a cost-efficient gradient-based algorithm for real-time
optical flow generation. An excessive external memory access limits the LK algorithm from …

Background subtraction is considered the first processing stage in video surveillance
systems, and consists of determining objects in movement in a scene captured by a static …

This article presents an efficient hardware implementation of the Horn-Schunck algorithm
that can be used in an embedded optical flow sensor. An architecture is proposed, that …

The accurate estimation of optical flow is a problem widely experienced in computer vision
and researchers in this field are devoting their efforts to formulate reliable and robust …

Low-level vision tasks pose an outstanding challenge in terms of computational effort: pixel-
wise operations require high-performance architectures to achieve real-time processing …