Air pockets, one kind of concrete surface defects, are often created on formed concrete surfaces during concrete construction. Their existence undermines the desired appearance and visual uniformity of architectural concrete. Therefore, measuring the impact of air pockets on the concrete surface in the form of air pockets is vital in assessing the quality of architectural concrete. Traditionall...

A block–based disparity estimation approach is presented that increases the robustness of the estimator by considering neighbourhood constraints and by estimating hierarchically on a multi–resolutional image pyramid of a stereoscopic image pair. This approach is applied to 3–D reconstruction of moving scenes in the field of 3–D video communications and to landscape and architectural reconstruct...

We present Power Mean Pyramid Scores (PMP), an evaluation metric that extends the Pyramid evaluation scheme for summarization by combining Sentence Content Units (SCU) scores using Power Mean. The Pyramid method generates a summarization score by linearly combining component SCU scores. We find that by combining SCU scores using Power Mean, we can optimize a single parameter, α, leading to sign...

Learning how to extract texture features from noncontrolled environments characterized by distorted images is a still-open task. By using a new rotation-invariant and scale-invariant image descriptor based on steerable pyramid decomposition, and a novel multiclass recognition method based on optimum-path forest, a new texture recognition system is proposed. By combining the discriminating power...

If it is impossible to capture all the image in one scan with the available equipment, a montage can be made from separately scanned pieces. We describe an automatic mosaicing process for document images. The image shifts are found by a correlation technique, using an image pyramid and sequential similarity to reduce computation time. Image placement and overlap is used to reject incorrect solu...

We introduce a low-level image representation using local orientation on a steerable pyramid. Its performance is demonstrated for a purposively progressive image coder which transmits and reconstructs parts of an image guided by their similarity to a given sample image. Like human visual attention, the image is scanned in a most-importantfirst order to gain a maximum of visual information with ...

• Compute particle weights from linear SVM score of extended HOG features [2] • Baseline: Features computed for each particle • Enhancement: Sliding window detector on feature pyramid for fast re-detection after occlusions, failure detection, and to find the best negative training examples in each frame • Particles get SVM score from detector response • Sliding-window-based measurement model is...

A motion estimation algorithm using wavelet approximation as an optical ow model has been developed to estimate accurate dense optical ow from an image sequence. This wavelet motion model is particularly useful in estimating optical ows with large displacement. Traditional pyramid methods which use the coarse-tone image pyramid by image burring in estimating optical ow often produce incorrect r...

The steerable pyramid decomposition is an invertible representation similar to the two-dimensional discrete wavelet transform, but with interesting shiftand rotation-invariance properties. It is slightly overcomplete and amenable to a filter bank implementation via convolution and downand upsampling operations. This paper presents a simple method for designing the FIR filter kernels required to...

A low entropy pyramidal image data structure suited for lossless coding and progressive transmission is proposed in this work. The new coder, called the progressively predictive pyramid (PPP) is based on the well-known Laplacian pyramid. By introducing inter-resolution predictors into the original Laplacian pyramid, we show that the entropy level in the original pyramid can be reduced significa...