An optical flow processor architecture is proposed. It offers accuracy and image-size scalability for video segmentation extraction. The Hierarchical Optical flow Estimation (HOE) algorithm [1] is optimized to provide an appropriate bit-length and iteration number to realize VLSI. The proposed processor architecture provides the following features. First, an algorithm-oriented data-path is intr...

A functional focal-plane implementation of a 2D optical flow system is presented that detects an preserves motion discontinuities. The system is composed of two different network layers of analog computational units arranged in a retinotopical order. The units in the first layer (the optical flow network) estimate the local optical flow field in two visual dimensions, where the strength of thei...

Optical flow algorithms offer a way to estimate motion from a sequence of images. The computation of optical flow plays a key-role in several computer vision applications, including motion detection and segmentation, frame interpolation, three-dimensional scene reconstruction, robot navigation and video compression. In the case of gradient based optical flow implementation, the pre-filtering st...

The computation of optical flow by the differential method imposes additional constraints to the one already imposed in the derivation of the optical flow equation. Consequently, the computation of optical flow using differential methods is computationally expensive especially for devices such as mobile phones, which have low processing power. In this work, we propose an optical flow computatio...

Optical flow as an image processing technique finds its applications in many areas of computer vision. A lot of research has been carried out in order to improve optical flow detection techniques, but this field is not perfect even as of today .Many methods have been proposed to solve the optical flow problem however, instabilities at the boundaries of moving objects are still challenges. There...

This paper presents a hierarchical multi-resolution estimation of optical flow for a vehicle tracking system which can be used in a practical environment. Aiming at accurate estimation of optical flow, we construct a strong feature tracking system based on the Shi-Tomasi approach. As a feature detector, we use a Scale-Invariant Feature Transform (SIFT) algorithm, which not only firmly focuses o...

Even with the recent advances in convolutional neural networks (CNN) in various visual recognition tasks, the state-of-the-art action recognition system still relies on hand crafted motion feature such as optical flow to achieve the best performance. We propose a multitask learning model ActionFlowNet to train a single stream network directly from raw pixels to jointly estimate optical flow whi...

This project presents a method for teaching robot arms optical flow. By extending recent works on depth based, probabilistic robot tracking, a novel real-world optical flow dataset with dense ground truth annotation is generated. A real, robotic dataset boasts the inclusion of phenomena that synthetic datasets cannot model. With this data a generic convolutional neural network is implemented to...

Gradient-based optical flow estimation methods such as LucasKanade method work well for scenes with small displacements but fail when objects move with large displacements. Hierarchical matching-based methods do not suffer from large displacements but are less accurate. By utilizing the high speed imaging capability of CMOS image sensors, the frame rate can be increased to obtain more accurate ...

I present a new focal-plane analog very-large-scale-integrated (aVLSI) sensor that estimates optical flow in two visual dimensions. Its computational architecture consists of a two-layer network of locally connected motion units that collectively estimate the optimal optical flow field. The applied gradient-based optical flow model assumes visual motion to be translational and smooth, and is fo...