We propose an optimized visual tracking algorithm based on the real-time selection of locally and temporally discriminative features. A novel feature selection mechanism is embedded in the Adaptive Color Names [2] (ACT) tracking system that adaptively selects the top-ranked discriminative features for tracking. The Dynamic Feature Selection Tracker (DFST) provides a significant gain in accuracy...

Marker assisted backcrossing has been used effectively to transfer the submergence tolerance gene SUB1 into popular rice varieties, but the approach can be costly. The selection strategy comprising foreground marker and phenotypic selection was investigated as an alternative. The non-significant correlation coefficients between ranking of phenotypic selection and ranking of background marker se...

A new robust method to segment foreground regions from color video sequences using multiple thresholds and morphological processes is proposed. Background models are observed for a long time, and their mean and standard deviation are used for background subtraction. Shadow regions are eliminated using color components, and the final foreground silhouette is extracted by smoothing the boundaries...

Identifying moving objects in a video sequence is a fundamental and critical task in many computer-vision applications. Background subtraction techniques are commonly used to separate foreground moving objects from the background. Most background subtraction techniques assume a single rate of adaptation, which is inadequate for complex scenes such as a traffic intersection where objects are mov...

In this paper, a method to extract moving objects on a pixel base for MPEG-4 “sprite coding” is proposed. Sprite coding is a form of object coding: it uses a unified panoramic background image derived from a sequence having a camera motion, and a foreground object as video object planes (VOP’s). The proposed algorithm utilizes background difference and watershed transformation to extract the fo...

We propose an end-to-end learning framework for foreground object segmentation. Given a single novel image, our approach produces a pixel-level mask for all “object-like” regions—even for object categories never seen during training. We formulate the task as a structured prediction problem of assigning a foreground/background label to each pixel, implemented using a deep fully convolutional net...

A model of auditory scene analysis is proposed, which incorporates an attentional mechanism and is implemented using a network of neural oscillators. The core of the model is a two-layer neural oscillator network which performs stream segregation and selection on the basis of oscillatory correlation. A stream is represented by a sychronised oscillator population, whereas different streams are r...