Detection thresholds were compared for moving and stationary oscillations with equivalent contrast changes. Motion was more detectable than stationary oscillation, and the difference increased with size of the feature (a Gaussian blob). Phase discriminations between a center and two flanking features were much better for motion than for stationary oscillation. Motion phase discriminations were ...

We believe that the potential of edges in local feature detection has not been fully exploited and therefore propose a detector that starts from single scale edges and produces reliable and interpretable blob-like regions and groups of regions of arbitrary shape. The detector is based on merging local maxima of the distance transform guided by the gradient strength of the surrounding edges. Rep...

We consider the problem of detecting and tracking players on a sports field in a grayscale video sequence from a fixed camera. Motion detection is performed as a separate subsystem, to locate moving objects and pass them to a tracker, and involves background modelling by fast rectangle features and blob detection. A particle filter is utilized for the tracking of objects, by a fast hierarchical...

In this paper, a new approach to real-time people segmentation through processing images captured by an infrared camera is introduced. The approach starts detecting human candidate blobs processed through traditional image thresholding techniques. Afterwards, the blobs are refined with the objective of validating the content of each blob. The question to be solved is if each blob contains one s...

Introduction: While the necessity of replacing voxels with blobs in conventional tomographic reconstruction based upon line-integrals is clear, it is not however well-investigated in plane- integral-based reconstruction. The problem is more challenging in convergent-plane projection reconstruction. In this work, we are aiming at utilizing blobs as alternative to voxels. <stron...

We present a real-time system for motion detection and tracking for autonomous robots with limited computational resources. The system uses an attentional mechanism to combine color and motion blob information, as well as prediction mechanisms to improve the overall system performance. We demonstrate the functionality of the system in several test scenarios and also discuss solutions to various...

A new family of symbolic compression algorithms, such as the ongoing JBIG2 standardization and commercial products, has recently been developed. These techniques are specifically targeted for binary document images. They cluster individual blobs in a document and store the sequence of occurrence of blobs and representative blob templates, hence the name symbolic compression. This paper describe...

We propose a lawn weed detection method modified from our previous work, i.e., Bayesian classifier based method. The proposed method employs features calculated from not only the edge-strength of weed/lawn textures but also color information of RGB. Instead of using Bayesian classifier, we exploit more sophisticated classifier, i.e., supportvector machine, for detecting weeds. After weed detect...