Analysis of classification algorithms for crop detection using LANDSAT 8 images

Remote sensing - the acquisition of information about an object or phenomenon without making physical contact with the object - is applied in a multitude of different areas, ranging from agriculture, forestry, cartography, hydrology, geology, meteorology, aerial traffic control, among many others. Regarding agriculture, an example of application of this information is regarding crop detection, to monitor existing crops easily and help in the region’s strategic planning. In any of these areas, there is always an ongoing search for better methods that allow us to obtain better results. For over forty years, the Landsat program has utilized satellites to collect spectral information from Earth’s surface, creating a historical archive unmatched in quality, detail, coverage, and length. The most recent one was launched on February 11, 2013, having a number of improvements regarding its predecessors. This project aims to compare classification methods in Portugal’s Ribatejo region, specifically regarding crop detection. The state of the art algorithms will be used in this region and their performance will be analyzed.

Land cover classification of Lago Grande de Curuai floodplain (Amazon, Brazil) using multi-sensor and image fusion techniques

Given the limitations of different types of remote sensing images, automated land-cover classifications of the Amazon várzea may yield poor accuracy indexes. One way to improve accuracy is through the combination of images from different sensors, by either image fusion or multi-sensor classifications. Therefore, the objective of this study was to determine which classification method is more efficient in improving land cover classification accuracies for the Amazon várzea and similar wetland environments - (a) synthetically fused optical and SAR images or (b) multi-sensor classification of paired SAR and optical images. Land cover classifications based on images from a single sensor (Landsat TM or Radarsat-2) are compared with multi-sensor and image fusion classifications. Object-based image analyses (OBIA) and the J.48 data-mining algorithm were used for automated classification, and classification accuracies were assessed using the kappa index of agreement and the recently proposed allocation and quantity disagreement measures. Overall, optical-based classifications had better accuracy than SAR-based classifications. Once both datasets were combined using the multi-sensor approach, there was a 2% decrease in allocation disagreement, as the method was able to overcome part of the limitations present in both images. Accuracy decreased when image fusion methods were used, however. We therefore concluded that the multi-sensor classification method is more appropriate for classifying land cover in the Amazon várzea.

Multi-scale label interaction to improve object detection and segmentation

The project aims at advancing the state of the art in the use of context information for classification of image and video data. The use of context in the classification of images has been showed of great importance to improve the performance of actual object recognition systems. In our project we proposed the concept of Multi-scale Feature Labels as a general and compact method to exploit the local and global context. The feature extraction from the discriminative probability or classification confidence label field is of great novelty. Moreover the use of a multi-scale representation of the feature labels lead to a compact and efficient description of the context. The goal of the project has been also to provide a general-purpose method and prove its suitability in different image/video analysis problem. The two-year project generated 5 journal publications (plus 2 under submission), 10 conference publications (plus 2 under submission) and one patent (plus 1 pending). Of these publications, a relevant number make use of the main result of this project to improve the results in detection and/or segmentation of objects.

Event-related potential analyses via single-subject topographic classification.

Introduction: Responses to external stimuli are typically investigated by averaging peri-stimulus electroencephalography (EEG) epochs in order to derive event-related potentials (ERPs) across the electrode montage, under the assumption that signals that are related to the external stimulus are fixed in time across trials. We demonstrate the applicability of a single-trial model based on patterns of scalp topographies (De Lucia et al, 2007) that can be used for ERP analysis at the single-subject level. The model is able to classify new trials (or groups of trials) with minimal a priori hypotheses, using information derived from a training dataset. The features used for the classification (the topography of responses and their latency) can be neurophysiologically interpreted, because a difference in scalp topography indicates a different configuration of brain generators. An above chance classification accuracy on test datasets implicitly demonstrates the suitability of this model for EEG data. Methods: The data analyzed in this study were acquired from two separate visual evoked potential (VEP) experiments. The first entailed passive presentation of checkerboard stimuli to each of the four visual quadrants (hereafter, "Checkerboard Experiment") (Plomp et al, submitted). The second entailed active discrimination of novel versus repeated line drawings of common objects (hereafter, "Priming Experiment") (Murray et al, 2004). Four subjects per experiment were analyzed, using approx. 200 trials per experimental condition. These trials were randomly separated in training (90%) and testing (10%) datasets in 10 independent shuffles. In order to perform the ERP analysis we estimated the statistical distribution of voltage topographies by a Mixture of Gaussians (MofGs), which reduces our original dataset to a small number of representative voltage topographies. We then evaluated statistically the degree of presence of these template maps across trials and whether and when this was different across experimental conditions. Based on these differences, single-trials or sets of a few single-trials were classified as belonging to one or the other experimental condition. Classification performance was assessed using the Receiver Operating Characteristic (ROC) curve. Results: For the Checkerboard Experiment contrasts entailed left vs. right visual field presentations for upper and lower quadrants, separately. The average posterior probabilities, indicating the presence of the computed template maps in time and across trials revealed significant differences starting at ~60-70 ms post-stimulus. The average ROC curve area across all four subjects was 0.80 and 0.85 for upper and lower quadrants, respectively and was in all cases significantly higher than chance (unpaired t-test, p<0.0001). In the Priming Experiment, we contrasted initial versus repeated presentations of visual object stimuli. Their posterior probabilities revealed significant differences, which started at 250ms post-stimulus onset. The classification accuracy rates with single-trial test data were at chance level. We therefore considered sub-averages based on five single trials. We found that for three out of four subjects' classification rates were significantly above chance level (unpaired t-test, p<0.0001). Conclusions: The main advantage of the present approach is that it is based on topographic features that are readily interpretable along neurophysiologic lines. As these maps were previously normalized by the overall strength of the field potential on the scalp, a change in their presence across trials and between conditions forcibly reflects a change in the underlying generator configurations. The temporal periods of statistical difference between conditions were estimated for each training dataset for ten shuffles of the data. Across the ten shuffles and in both experiments, we observed a high level of consistency in the temporal periods over which the two conditions differed. With this method we are able to analyze ERPs at the single-subject level providing a novel tool to compare normal electrophysiological responses versus single cases that cannot be considered part of any cohort of subjects. This aspect promises to have a strong impact on both basic and clinical research.

Classification and inventory management of abnormal demand items

The main objective of the study is to form a framework that provides tools to recognise and classify items whose demand is not smooth but varies highly on size and/or frequency. The framework will then be combined with two other classification methods in order to form a three-dimensional classification model. Forecasting and inventory control of these abnormal demand items is difficult. Therefore another object of this study is to find out which statistical forecasting method is most suitable for forecasting of abnormal demand items. The accuracy of different methods is measured by comparing the forecast to the actual demand. Moreover, the study also aims at finding proper alternatives to the inventory control of abnormal demand items. The study is quantitative and the methodology is a case study. The research methods consist of theory, numerical data, current state analysis and testing of the framework in case company. The results of the study show that the framework makes it possible to recognise and classify the abnormal demand items. It is also noticed that the inventory performance of abnormal demand items differs significantly from the performance of smoothly demanded items. This makes the recognition of abnormal demand items very important.

A Psychophysical Assessment of Multisensory Processing and Multiple Object Tracking in Autism Spectrum Disorders

Les troubles du spectre autistique (TSA) sont actuellement caractérisés par une triade d'altérations, incluant un dysfonctionnement social, des déficits de communication et des comportements répétitifs. L'intégration simultanée de multiples sens est cruciale dans la vie quotidienne puisqu'elle permet la création d'un percept unifié. De façon similaire, l'allocation d'attention à de multiples stimuli simultanés est critique pour le traitement de l'information environnementale dynamique. Dans l'interaction quotidienne avec l'environnement, le traitement sensoriel et les fonctions attentionnelles sont des composantes de base dans le développement typique (DT). Bien qu'ils ne fassent pas partie des critères diagnostiques actuels, les difficultés dans les fonctions attentionnelles et le traitement sensoriel sont très courants parmi les personnes autistes. Pour cela, la présente thèse évalue ces fonctions dans deux études séparées. La première étude est fondée sur la prémisse que des altérations dans le traitement sensoriel de base pourraient être à l'origine des comportements sensoriels atypiques chez les TSA, tel que proposé par des théories actuelles des TSA. Nous avons conçu une tâche de discrimination de taille intermodale, afin d'investiguer l'intégrité et la trajectoire développementale de l'information visuo-tactile chez les enfants avec un TSA (N = 21, âgés de 6 à18 ans), en comparaison à des enfants à DT, appariés sur l’âge et le QI de performance. Dans une tâche à choix forcé à deux alternatives simultanées, les participants devaient émettre un jugement sur la taille de deux stimuli, basé sur des inputs unisensoriels (visuels ou tactiles) ou multisensoriels (visuo-tactiles). Des seuils différentiels ont évalué la plus petite différence à laquelle les participants ont été capables de faire la discrimination de taille. Les enfants avec un TSA ont montré une performance diminuée et pas d'effet de maturation aussi bien dans les conditions unisensorielles que multisensorielles, comparativement aux participants à DT. Notre première étude étend donc des résultats précédents d'altérations dans le traitement multisensoriel chez les TSA au domaine visuo-tactile. Dans notre deuxième étude, nous avions évalué les capacités de poursuite multiple d’objets dans l’espace (3D-Multiple Object Tracking (3D-MOT)) chez des adultes autistes (N = 15, âgés de 18 à 33 ans), comparés à des participants contrôles appariés sur l'âge et le QI, qui devaient suivre une ou trois cibles en mouvement parmi des distracteurs dans un environnement de réalité virtuelle. Les performances ont été mesurées par des seuils de vitesse, qui évaluent la plus grande vitesse à laquelle des observateurs sont capables de suivre des objets en mouvement. Les individus autistes ont montré des seuils de vitesse réduits dans l'ensemble, peu importe le nombre d'objets à suivre. Ces résultats étendent des résultats antérieurs d'altérations au niveau des mécanismes d'attention en autisme quant à l'allocation simultanée de l'attention envers des endroits multiples. Pris ensemble, les résultats de nos deux études révèlent donc des altérations chez les TSA quant au traitement simultané d'événements multiples, que ce soit dans une modalité ou à travers des modalités, ce qui peut avoir des implications importantes au niveau de la présentation clinique de cette condition.

Object Detection in Images by Components

In this paper we present a component based person detection system that is capable of detecting frontal, rear and near side views of people, and partially occluded persons in cluttered scenes. The framework that is described here for people is easily applied to other objects as well. The motivation for developing a component based approach is two fold: first, to enhance the performance of person detection systems on frontal and rear views of people and second, to develop a framework that directly addresses the problem of detecting people who are partially occluded or whose body parts blend in with the background. The data classification is handled by several support vector machine classifiers arranged in two layers. This architecture is known as Adaptive Combination of Classifiers (ACC). The system performs very well and is capable of detecting people even when all components of a person are not found. The performance of the system is significantly better than a full body person detector designed along similar lines. This suggests that the improved performance is due to the components based approach and the ACC data classification structure.

Validating Co-Training Models for Web Image Classification

Co-training is a semi-supervised learning method that is designed to take advantage of the redundancy that is present when the object to be identified has multiple descriptions. Co-training is known to work well when the multiple descriptions are conditional independent given the class of the object. The presence of multiple descriptions of objects in the form of text, images, audio and video in multimedia applications appears to provide redundancy in the form that may be suitable for co-training. In this paper, we investigate the suitability of utilizing text and image data from the Web for co-training. We perform measurements to find indications of conditional independence in the texts and images obtained from the Web. Our measurements suggest that conditional independence is likely to be present in the data. Our experiments, within a relevance feedback framework to test whether a method that exploits the conditional independence outperforms methods that do not, also indicate that better performance can indeed be obtained by designing algorithms that exploit this form of the redundancy when it is present.

Case study: object and ground point separation on a river bank using airborne based LIDAR data

In the past decade, airborne based LIght Detection And Ranging (LIDAR) has been recognised by both the commercial and public sectors as a reliable and accurate source for land surveying in environmental, engineering and civil applications. Commonly, the first task to investigate LIDAR point clouds is to separate ground and object points. Skewness Balancing has been proven to be an efficient non-parametric unsupervised classification algorithm to address this challenge. Initially developed for moderate terrain, this algorithm needs to be adapted to handle sloped terrain. This paper addresses the difficulty of object and ground point separation in LIDAR data in hilly terrain. A case study on a diverse LIDAR data set in terms of data provider, resolution and LIDAR echo has been carried out. Several sites in urban and rural areas with man-made structure and vegetation in moderate and hilly terrain have been investigated and three categories have been identified. A deeper investigation on an urban scene with a river bank has been selected to extend the existing algorithm. The results show that an iterative use of Skewness Balancing is suitable for sloped terrain.

Application of auto regressive models of wavelet sub-bands for classifying Terahertz pulse measurements

This paper presents an approach for automatic classification of pulsed Terahertz (THz), or T-ray, signals highlighting their potential in biomedical, pharmaceutical and security applications. T-ray classification systems supply a wealth of information about test samples and make possible the discrimination of heterogeneous layers within an object. In this paper, a novel technique involving the use of Auto Regressive (AR) and Auto Regressive Moving Average (ARMA) models on the wavelet transforms of measured T-ray pulse data is presented. Two example applications are examined - the classi. cation of normal human bone (NHB) osteoblasts against human osteosarcoma (HOS) cells and the identification of six different powder samples. A variety of model types and orders are used to generate descriptive features for subsequent classification. Wavelet-based de-noising with soft threshold shrinkage is applied to the measured T-ray signals prior to modeling. For classi. cation, a simple Mahalanobis distance classi. er is used. After feature extraction, classi. cation accuracy for cancerous and normal cell types is 93%, whereas for powders, it is 98%.

Threshold-free object and ground point separation in LIDAR data

Light Detection And Ranging (LIDAR) is an important modality in terrain and land surveying for many environmental, engineering and civil applications. This paper presents the framework for a recently developed unsupervised classification algorithm called Skewness Balancing for object and ground point separation in airborne LIDAR data. The main advantages of the algorithm are threshold-freedom and independence from LIDAR data format and resolution, while preserving object and terrain details. The framework for Skewness Balancing has been built in this contribution with a prediction model in which unknown LIDAR tiles can be categorised as “hilly” or “moderate” terrains. Accuracy assessment of the model is carried out using cross-validation with an overall accuracy of 95%. An extension to the algorithm is developed to address the overclassification issue for hilly terrain. For moderate terrain, the results show that from the classified tiles detached objects (buildings and vegetation) and attached objects (bridges and motorway junctions) are separated from bare earth (ground, roads and yards) which makes Skewness Balancing ideal to be integrated into geographic information system (GIS) software packages.

Video stimuli reduce object-directed imitation accuracy: a novel two-person motion-tracking approach

Imitation is an important form of social behavior, and research has aimed to discover and explain the neural and kinematic aspects of imitation. However, much of this research has featured single participants imitating in response to pre-recorded video stimuli. This is in spite of findings that show reduced neural activation to video vs. real life movement stimuli, particularly in the motor cortex. We investigated the degree to which video stimuli may affect the imitation process using a novel motion tracking paradigm with high spatial and temporal resolution. We recorded 14 positions on the hands, arms, and heads of two individuals in an imitation experiment. One individual freely moved within given parameters (moving balls across a series of pegs) and a second participant imitated. This task was performed with either simple (one ball) or complex (three balls) movement difficulty, and either face-to-face or via a live video projection. After an exploratory analysis, three dependent variables were chosen for examination: 3D grip position, joint angles in the arm, and grip aperture. A cross-correlation and multivariate analysis revealed that object-directed imitation task accuracy (as represented by grip position) was reduced in video compared to face-to-face feedback, and in complex compared to simple difficulty. This was most prevalent in the left-right and forward-back motions, relevant to the imitator sitting face-to-face with the actor or with a live projected video of the same actor. The results suggest that for tasks which require object-directed imitation, video stimuli may not be an ecologically valid way to present task materials. However, no similar effects were found in the joint angle and grip aperture variables, suggesting that there are limits to the influence of video stimuli on imitation. The implications of these results are discussed with regards to previous findings, and with suggestions for future experimentation.

An evaluation of the pedestrian classification in a multi-domain multi-modality setup

The objective of this article is to study the problem of pedestrian classification across different light spectrum domains (visible and far-infrared (FIR)) and modalities (intensity, depth and motion). In recent years, there has been a number of approaches for classifying and detecting pedestrians in both FIR and visible images, but the methods are difficult to compare, because either the datasets are not publicly available or they do not offer a comparison between the two domains. Our two primary contributions are the following: (1) we propose a public dataset, named RIFIR , containing both FIR and visible images collected in an urban environment from a moving vehicle during daytime; and (2) we compare the state-of-the-art features in a multi-modality setup: intensity, depth and flow, in far-infrared over visible domains. The experiments show that features families, intensity self-similarity (ISS), local binary patterns (LBP), local gradient patterns (LGP) and histogram of oriented gradients (HOG), computed from FIR and visible domains are highly complementary, but their relative performance varies across different modalities. In our experiments, the FIR domain has proven superior to the visible one for the task of pedestrian classification, but the overall best results are obtained by a multi-domain multi-modality multi-feature fusion.

Disparity-defined objects moving in depth do not elicit three-dimensional shape constancy

Observers generally fail to recover three-dimensional shape accurately from binocular disparity. Typically, depth is overestimated at near distances and underestimated at far distances [Johnston, E. B. (1991). Systematic distortions of shape from stereopsis. Vision Research, 31, 1351–1360]. A simple prediction from this is that disparity-defined objects should appear to expand in depth when moving towards the observer, and compress in depth when moving away. However, additional information is provided when an object moves from which 3D Euclidean shape can be recovered, be this through the addition of structure from motion information [Richards, W. (1985). Structure from stereo and motion. Journal of the Optical Society of America A, 2, 343–349], or the use of non-generic strategies [Todd, J. T., & Norman, J. F. (2003). The visual perception of 3-D shape from multiple cues: Are observers capable of perceiving metric structure? Perception and Psychophysics, 65, 31–47]. Here, we investigated shape constancy for objects moving in depth. We found that to be perceived as constant in shape, objects needed to contract in depth when moving toward the observer, and expand in depth when moving away, countering the effects of incorrect distance scaling (Johnston, 1991). This is a striking example of the failure of shape con- stancy, but one that is predicted if observers neither accurately estimate object distance in order to recover Euclidean shape, nor are able to base their responses on a simpler processing strategy.

A moving observer in a three-dimensional world

For many tasks, such as retrieving a previously viewed object, an observer must form a representation of the world at one location and use it at another. A world-based 3D reconstruction of the scene built up from visual information would fulfil this requirement, something computer vision now achieves with great speed and accuracy. However, I argue that it is neither easy nor necessary for the brain to do this. I discuss biologically plausible alternatives, including the possibility of avoiding 3D coordinate frames such as ego-centric and world-based representations. For example, the distance, slant and local shape of surfaces dictate the propensity of visual features to move in the image with respect to one another as the observer’s perspective changes (through movement or binocular viewing). Such propensities can be stored without the need for 3D reference frames. The problem of representing a stable scene in the face of continual head and eye movements is an appropriate starting place for understanding the goal of 3D vision, more so, I argue, than the case of a static binocular observer.