In this technical note, we derive a closed-form expression for the affine transformation mapping local image patches between two calibrated views. We show that the transformation is a function of the relative camera pose, the image coordinates, and the local surface normal.
This document describes an image and video dataset of driving views captured in all weather and illumination conditions. The data set has been submitted to CDVL.
State-of-the-art motor vehicles are able to break for pedestrians in an emergency. We investigate what it would take to issue an early warning to the driver so he/she has time to react. We have identified that predicting the intention of a pedestrian reliably by position is a particularly hard challenge. This paper describes an early pedestrian warning demonstration system.
We propose and discuss the summarization of superpixel-type image tiles/patches using mean and covariance information. We refer to the resulting objects as covapixels.
Given an grayscale digital image, and a positive integer $n$, how well can we store the image at a compression ratio of $n:1$? In this paper we address the above question in extreme cases when $n>>50$ using "$\mathbf{V}$-variable image compression".
In this work, we present preliminary results demonstrating the ability to recover a significant amount of information about secret model inputs given only very limited access to model outputs and the ability evaluate the model on additive perturbations to the input.
Multi-camera tracking is quite different from single camera tracking, and it faces new technology and system architecture challenges. By analyzing the corresponding characteristics and disadvantages of the existing algorithms, problems in multi-camera tracking are summarized and some new directions for future work are also generalized.
We study the problem of multicut segmentation. We introduce modified versions of the Semi-PlanarCC based on bounding Lagrange multipliers. We apply our work to natural image segmentation.
Human eye can see and read what is written or displayed either in natural handwriting or in printed format. The same work in case the machine does is called handwriting recognition. Handwriting recognition can be broken down into two categories: off-line and on-line. ...
This paper presents a kernel formulation of the recently introduced diff-hash algorithm for the construction of similarity-sensitive hash functions. Our kernel diff-hash algorithm that shows superior performance on the problem of image feature descriptor matching.
This paper reviews Kunchenko's polynomials using as template matching method to recognize template in one-dimensional input signal. Kunchenko's polynomials method is compared with classical methods - cross-correlation and sum of squared differences according to numerical statistical example.