• Publications
  • Influence
SIFT Features Tracking for Video Stabilization
TLDR
This paper presents a video stabilization algorithm based on the extraction and tracking of scale invariant feature transform features through video frames that confirms the effectiveness of this feature-based motion estimation algorithm.
Objective estimation of body condition score by modeling cow body shape from digital images.
TLDR
The main objective of this study was to develop a technique that was able to describe the body shape of cows in a reconstructive way and showed that the polynomial model proposed in this study performs better than other state-of-the-art methods in estimating BCS even at the extreme values of BCS scale.
Depth map generation by image classification
TLDR
A novel and fully automatic technique to estimate depth information from a single input image, based on a new image classification technique able to classify digital images as indoor, outdoor with geometric elements or outdoor without geometric elements.
First Quantization Matrix Estimation From Double Compressed JPEG Images
TLDR
A novel algorithm to achieve the reconstruction of the history of an image or a video by exploiting the effects of successive quantizations followed by dequantizations in case of double JPEG compressed images.
A Robust Image Alignment Algorithm for Video Stabilization Purposes
TLDR
A fast and accurate block-based local motion estimator together with a robust alignment algorithm based on voting is proposed for video stabilization purposes and Experimental results confirm the effectiveness of both local and global motion estimators.
3D stereoscopic image pairs by depth-map generation
TLDR
A new unsupervised technique aimed to generate stereoscopic views estimating depth information from a single input image using vanishing lines/points using a few heuristics to generate an approximated depth map is presented.
Leveraging Uncertainty to Rethink Loss Functions and Evaluation Measures for Egocentric Action Anticipation
TLDR
Experiments performed on the EPIC-KITCHENS dataset show that the proposed loss function allows improving the results of both egocentric action anticipation and recognition methods.
Robust Image Alignment for Tampering Detection
TLDR
A robust alignment method which makes use of an image hash component based on the Bag of Features paradigm which encodes the spatial distribution of the image features to deal with highly textured and contrasted tampering patterns is proposed.
Classifying food images represented as Bag of Textons
TLDR
It is pointed out, through a set of experiments, that textures are fundamental to properly recognize different food items and are more accurate than existing (and more complex) approaches in classifying the 61 classes of the Pittsburgh Fast-Food Image Dataset.
...
1
2
3
4
5
...