Copyright © 2014 by Intelligent Systems Laboratory, Computer Science Department, Technion - Israel Institute of Technology, Haifa 3200003, Israel. All rights reserved

Color Invariants for Person Re-Identification

Color Invariants for Person Re-IdentificationBy: Igor Kviatkovsky

We revisit the problem of specific object recognition using color distributions. In some applications - such as specific person identification - it is highly likely that the color distributions will be multimodal and hence contain a special structure. Although the color distribution changes under different lighting conditions, some aspects of its structure turn out to be invariants. We refer to this structure as an intra-distribution structure, and show that it is invariant under a wide range of imaging conditions while being discriminative enough to be practical. Our signature uses shape context descriptors to represent the intra-distribution structure. Assuming the widely used diagonal model, we validate that our signature is invariant under certain illumination changes. Experimentally, we use color information as the only cue to obtain good recognition performance on publicly available databases covering both indoors and outdoors conditions. Combining our approach with the complementary covariance descriptor, we demonstrate results exceeding the state of the art performance on the challenging VIPeR database.

Read more ...

Probabilistic Local Variation

Probabilistic Local VariationBy: Michael Baltaxe and Prof. Michael Lindenbaum

The goal of image oversegmentation is to divide an image into several pieces or "segments", such that each segment is part of an object present in the scene. Contrary to image segmentation algorithms, an oversegmentation algorithm is allowed to output more segments than the number of objects that appear in the image. Oversegmentation is a very common preprocessing step for several common computer vision tasks. In this work we study image oversegmentation and develop new algorithms.

Read more ...

Navigation Performance Enhancement Using Online Mosaicking

Navigation Performance Enhancement Using Online MosaickingBy: Vadim Indelman

The current research focuses on VAN in unknown environments. It is assumed that the platform is equipped with a standard inertial navigation system and a single camera only. The camera-captured images are associated with navigation data and stored in a repository, which represents a mapping of the observed environment. The repository can be also used for constructing mosaic images. Consequently, the camera-captured images are used both for mapping and for navigation aiding. In contrast to SLAM, the mapping (i. e., mosaic construction and repository refinement), is performed in a background process, thereby considerably reducing the computational load.

Read more ...

Building A Non-Euclidean Roadmap From A Small Set Of Images

Building A Non-Euclidean Roadmap From A Small Set Of ImagesBy: Silvina Rybnikov

This work addresses the problem of robotic navigation using natural visual features.

The system receives a set of target locations represented by images taken from those locations. The robot autonomously explores the environment, locates the targets, and builds a graph of the paths between them. The graph allows fast homing from any location in the environment to any target location. 


Read more ...

Active Tracking And Pursuit Under Different Levels Of Occlusions: A Two Layers Approach

Active Tracking And Pursuit Under Different Levels Of Occlusions: A Two Layers ApproachBy: Tomer Baum, Idan Izhaki, Ehud Rivlin, Gadi Katzir

We present an algorithm for a real-time, robust, vision-based active tracking and pursuit. The algorithm was designed to overcome problems emergent from active vision based pursuit, such as target occlusion. The algorithm offers to overcome an occlusion by two levels of reactions, we term layers. The purpose of the first layer is to cope with short term or medium term occlusions, i.e. occlusions where a known method such as Mean-Shift combined with a Kalman filter fails. For the first layer we designed the Hybrid filter for Active Pursuit (HAP). For long term occlusions we use the second layer. This layer is a decision algorithm following a learning procedure, and based on game theory related reinforcement.

Read more ...