SensorCap: Sensor Data Capture

SensorCap is an Android tool that captures sensor data in user-defined configurations. The purpose is to allow researchers and developers to quickly save sensor data for research, testing and prototyping. The sensors are broadly defined to include “motion”, “position” and “environment” device sensors.

An intuitive user interface facilitates tasks such as setting up a sensor, entering capture details and sharing sensor data.… Read more

Benchmark on Activity Recognition based on Wearable Sensors

This page contains the source code and data used in our paper “Human Activity Recognition Based on Wearable Sensor Data: A Standardization of the State-of-the-Art“. In this paper, we implement and evaluate several state-of-the-art approaches, ranging from methods based on handcrafted features to convolutional neural networks. Also, we standardize a large number of datasets, which vary in terms of sampling rate, number of sensors, activities, and subjects.… Read more

OFCM – Optical Flow Co-occurrence Matrices

Source code of the spatiotemporal feature descriptor proposed in the Optical Flow Co-occurrence Matrices: A Novel Spatiotemporal Feature Descriptor (ICPR 2016). Aiming at capturing more information from the optical flow, this work proposes a novel spatiotemporal local feature descriptor called Optical Flow Co-occurrence Matrices (OFCM). The method is based on the extraction of Haralick features from co-occurrence matrices computed using the optical flow information.… Read more

SSAT – Smart Surveillance Annotation Tool

Smart Surveillance Annotation Tool (SSAT), as it own name indicates, is an annotation tool, free and interactive, for the computer vision community. This eases the way researchers and annotation massive video datasets. This tool is still in progress, in the future it will be possible to create and manipulate bounding boxes in the video.

 

Explanatory video

Video extracted from Interactive Dataset, CPR contest on Semantic Description of Human Activities (SDHA)

Proper use

There are a few requirements thats make the SSAT work properly.… Read more

SSIGLib – Smart Surveillance Interest Group Library

The Smart Surveillance Interest Group Library (SSIGLib) is a C/C++ library built to provide a set of functionalities that aid researchers not only on the development of surveillance systems but also on the creation of novel solutions for problems related to video surveillance.

The SSIGLib was designed to provide features for a good scene understanding, scalability, real-time operation, multi-sensor environment, usage of low cost standard components, and communication control.… Read more

Kernel Hierarchical PCA for Person Re-Identification (ICPR 2016)

Source code used in the Kernel Hierarchical PCA for Person Re-Identification (ICPR 2016). In this paper, we tackle the person re-identification problem as a common subspace learning and propose a novel framework, which we named Kernel HPCA, that handles with camera transition and dimensionality reduction.

Kernel HPCA is a nonlinear extension of Hierarchical PCA (HPCA). HPCA is known in chemometrics as a multiblock multivariate model.… Read more

Kernel Partial Least Squares for Person Re-Identification (AVSS 2016)

Source code used in the Kernel Partial Least Squares for Person Re- Identification (AVSS 2016). In this paper, we approach supervised and unsupervised person re-identification (Re-ID) problem in two widely used datasets (VIPER and PRID450S) using Kernel Partial Least Squares.

Regarding supervised Re-ID, we present a common subspace learning method, which we coined Kernel PLS Mode A, and a cross-view discriminative regression model, X-KPLS.… Read more

HOMF Descriptor for Anomalous Pattern Recognition

Source code used in the paper Histograms of Optical Flow Orientation and Magnitude to Detect Anomalous Events in Videos (published on SIBGRAPI 2015). In this paper, we propose the use of magnitude and orientation to describe patterns in crowded scenes. This model describes spatiotemporal regions in the scene to determine if they presents a normal or anomalous pattern.  Our descriptor captures spatiotemporal information from cuboids (regions with spatial and temporal support) and encodes both magnitude and orientation of the optical flow separately into histograms, differently from previous works, which are based only on the orientation.… Read more

CBRA – Color-Based Ranking Aggregation for Person Re-Identification

Source code used in the paper CBRA – Color-Based Ranking Aggregation for Person Re- Identification (ICIP 2015). In this paper, we propose the use of rank aggregation to improve the results, in which we address the person re-identification problem using a Color-based Ranking Aggregation (CBRA) method that explores different feature representations to obtain complementary ranking lists and combine them using the Stuart ranking aggregation method.… Read more

ICB 2015 Appearance-Based Person Re-Identification

This page contains the Software used on the paper presented in ICB 2015 (Appearance-Based Person Re-Identification by Intra-Camera Discriminative Models and Ranking Aggregation). In this work, we used prototypes to indirectly handle with the camera transition problem. Thus, for a given gallery image, we computed the most similar individuals in training set that were captured by the same camera. For each of these individuals, we used its respective image in the opposite camera (prototypes) to learn a appearance model using Partial Least Squares (PLS) in one-against-all (OAA) scheme.… Read more

Smart Surveillance Framework

The Smart Surveillance Framework is a C/C++ library built using the OpenCV and the C++ Standard Template Library to provide a set of functionalities to aid researchers not only on the development of surveillance systems but also on the creation of novel solutions for problems related to video surveillance.

One of its main goals is to provide a set of data structures to describe the scene to allow researches to focus only on their problems of interest  and use these information without creating such infrastructure to every problem that will be tackled, as it is done in the majority of case nowadays.… Read more

PLS NIPALS C++

This library provides a C++ class to execute Partial Least Squares (PLS) NIPALS method for a scalar response variable for both dimension reduction or regression. It provides a class composed of methods to build, load, and store a PLS model, project feature vectors onto the PLS model and retrieve its low dimensional representation.

PLS handles data in high dimensional feature spaces and can be employed as a dimensionality reduction technique.… Read more

Histogram of Shearlet Coefficients (HSC)

This library provides a C++ class called HSC to perform feature extraction using the histogram of shearlet coefficients (HSC), method proposed in the paper A Novel Feature Descriptor Based on the Shearlet Transform (ICIP).

Shearlet transforms provide a general framework for analyzing and representing data with anisotropic information at multiple scales. As a consequence, signal singularities, such as edges, can be precisely detected and located in images.… Read more

PLS Face Identification

This software, called PLS Face Identification (PFI), implements the one-against-all face identification method proposed in [1] and [2] (the second is an extension of the first by adding new feature descriptors). This software allows researchers to compare face identification methods to our method using datasets other than those considered in our papers.

To facilitate its usage, we provide a small data set (a subset of the FERET dataset), inside the directory SampleData in the software package.  … Read more

DetectorPLS

DetectorPLS is an implementation of the paper Human Detection Using Partial Least Squares Analysis.W.R. Schwartz, A. Kembhavi, D. Harwood, L. S. Davis. In proceedings of the ICCV. Kyoto, Japan, 2009 [pdf] [project webpage].

The goal of this implementation is to allow researchers to perform detection using already learned models for applications such as human and face detection and also provide a simple way of learning new object models for detection by providing exemplars of the positive and negative samples.… Read more