Water monitoring technologies are widely used for contaminants detection in wide variety of water ecology applications such as water treatment plant and water distribution system. A tremendous amount of research has been conducted over the past decades to develop robust and efficient techniques of contaminants detection with minimum operating cost and energy. Recent developments in spectroscopic techniques and biosensor approach have improved the detection sensitivities, quantitatively and qualitatively. The availability of in-situ measurements and multiple detection analyses has expanded the water monitoring applications in various advanced techniques including successful establishment in hand-held sensing devices which improves portability in real-time basis for the detection of contaminant, such as microorganisms, pesticides, heavy metal ions, inorganic and organic components. This paper intends to review the developments in water quality monitoring technologies for the detection of biological and chemical contaminants in accordance with instrumental limitations. Particularly, this review focuses on the most recently developed techniques for water contaminant detection applications. Several recommendations and prospective views on the developments in water quality assessments will also be included.

In the paper we address the applied problem of detecting and recognizing street name plates in urban images by a generic approach to structural object detection and recognition. A structured object is detected using a boosting approach and false positives are filtered using a specific method called the texture transform. In a second step the subregion containing the key information, here the text, is segmented out. Text is in this case characterized as texture and a texton based technique is applied. Finally the texts are recognized by using Dynamic Time Warping on signatures created from the identified regions. The recognition method is general and only requires text in some form, e.g. a list of printed words, but no image models of the plates for learning. Therefore, it can be shown to scale to rather large data sets. Moreover, due to its generality it applies to other cases, such as logo and sign recognition. On the other hand the critical part of the method lies in the detection step. Here it relied on knowledge about the appearance of street signs. However, the boosting approach also applies to other cases as long as the target region is structured in some way. The particular scenario considered deals with urban navigation and map indexing by mobile users, e.g. when the images are acquired by a mobile

Humans looking around in the world can, seemingly without effort, segment out and distinguish different objects in the world. The corresponding capability has largely eluded the efforts of researchers in computer vision. Figure-ground segmention in general needs both context and task to be well-defined, i.e. may not be addressed using information in the visual scene alone. However, 3D cues play a special role: they indicate physical chunks that in turn can be ascribed visually observable 3D properties, such as position, location and motion, and object intrinsic properties such as shape, color and maybe surface and material characteristics. In the paper we will discuss segmentation of the scene into figure and ground and more generally into layers. Cues from stereo and motion will be used together with monocular cues from e.g. colour and texture. The goal is to acquire appearance models of the objects that can be used for subsequent processing, such as recognition. We will consider both moving and static objects, in the latter case assuming that 3D cues are available from either binocular stereo or observer motion. Integrating multiple cues is a key aspect of our approach and two techniques for this will be compared. One is a probabilistic approach where the likelihood of observing the data given a model of each layer is computed followed by a classification of each pixel using Bayes' rule. A second scheme is a voting method, the key difference being that each cue makes an independent decision regarding membership before these decisions are combined using a weighted sum. The advantage of voting in data fusion is that measurements drawn from very different spaces can easily be combined. With probabilistic methods more care must be taken in designing the model of each so that the different cues combine in the desired manner. Experiments on everyday scenes will show the performance of our methods and the type of object appearance models that can be acquire

The 14th Iberoamerican Congress on Pattern Recognition (CIARP 2009, C- gresoIberoAmericanodeReconocimientodePatrones)formedthelatestofanow longseriesofsuccessfulmeetingsarrangedbytherapidlygrowingIber

Classifying materials from their appearance is challenging. Impressive results have been obtained under varying illumination and pose conditions. Still, the effect of scale variations and the possibility to generalise across different material samples are still largely unexplored. This paper (A preliminary version of this work was presented in Hayman et al. [E. Hayman, B. Caputo, M.J. Fritz, J.-O. Eklundh, On the significance of real world conditions for material classification, in: Proceedings of the ECCV, Lecture Notes in Computer Science, vol. 4, Springer, Prague, 2004, pp. 253–266].) addresses these issues, proposing a pure learning approach based on support vector machines. We study the effect of scale variations first on the artificially scaled CUReT database, showing how performance depends on the amount of scale information available during training. Since the CUReT database contains little scale variation and only one sample per material, we introduce a new database containing 10 CUReT materials at different distances, pose and illumination. This database provides scale variations, while allowing to evaluate generalisation capabilities: does training on the CUReT database enable recognition of another piece of sandpaper? Our results demonstrate that this is not yet possible, and that material classification is far from being solved in scenarios of practical interest.

In the paper we address the applied problem of detecting and recognizing street name plates in urban images by a generic approach to structural object detection and recognition. A structured object ...

In this report the authors define and describe the concept of Object-Action Complexes and give some examples. OACs combine the concept of affordance with the computational efficiency of STRIPS. Affordance is the relation between a situation and the action that it allows. OACs are proposed as a framework for representing actions, objects and the learning process that constructs such representations at all levels. Formally, an OAC is defined as a triplet, composed of a unique ID, a predition function that codes the systems belief on how the world (which is defined as a kind of global attribute space) will change after applying the OAC and a statisical measure representing the success of an OAC. The prediction function is thereby a mapping within the global attribute space. The measurement captures the accuracy of this prediction function and describes the reliability of the OAC. Therefore, it can be used for optimal decision making, predicion of the outcome of a certain action and learning.

This paper presents a method for visual object categorization based on encoding the joint textural information in objects and the surrounding background, and requiring no segmentation during recognition. The framework can be used together with various learning techniques and model representations. Here we use this framework with simple probabilistic models and more complex representations obtained using Support Vector Machines. We prove that our approach provides good recognition performance for complex problems for which some of the existing methods have difficulties. Additionally, we introduce a new extensive database containing realistic images of animals in complex natural environments. We assess the database in a set of experiments in which we compare the performance of our approach with a recently proposed method.

In this chapter, we describe methods to be applied on a robot equipped with one or more camera sensors. Our goal is to present representations and models for both three-dimensional (3-D) motion and structure estimation as well as recognition. We do not delve into estimation and inference issues since these are extensively treated in other chapters. The same applies to the fusion with other sensors, which we heavily encourage but do not describe here. In the first part we describe the main methods in 3-D inference from two-dimensional (2-D) images. We are at the point where we could propose a recipe, at least for a small spatial extent. If we are able to track a few visual features in our images, we are able to estimate the selfmotion of the robot as well as its pose with respect to any known landmark. Having solutions for minimal case problems, the obvious way here is to apply random sample consensus. If no known 3-D landmark is given then the trajectory of the camera exhibits drift. From the trajectory of the camera, time windows over several frames are selected and a 3-D dense depth map is obtained through solving the stereo problem. Large-scale reconstructions based on camera only do raise challenges with respect to drift and loop closing. In the second part we deal with recognition as appealed to robotics. The main challenge here is to detect an instance of an object and recognize or categorize it. Since in robotics applications an 23.1 3-D Vision and Visual SLAM .................... 544 23.1.1 Pose Estimation Solution ............... 545 23.1.2 Triangulation ............................... 545 23.1.3 Moving Stereo.............................. 546 23.1.4 Structure from Motion (SfM) ........... 547 23.1.5 Monocular SLAM or Multiple-View SfM .................... 548 23.1.6 Dense Depth Maps from Stereo ...... 549

In this paper, we present a new application of image segmentation algorithms and an adaptation of the im- age segmentation method of Tavakoli et al. to the problem of vegetation segmentation. While the traditional goal of image segmentation is to provide a figure/ground segmenta- tion for object recognition or semantic segmentation to as- sist humans, we propose to use image segmentation in order to boost performance of local invariant feature detectors. In particular, we analyze the performance of MSER feature de- tector and we show that we can prune all features detected on vegetation to gain a 67% speed-up while accuracy of im- age matching does not decrease. The image segmentation method of Tavakoli et al. that we adapt to the problem of vegetation segmentation is based on singular value decom- position (SVD) of local image patches, where the sum of the smaller singular values describes the high frequency part of the patch. The results of the automatic segmentation of veg- etation show that the average overlap between manual and automatic vegetation segmentation is 33% and that the auto- matic procedure for vegetation segmentation can prune 25% of MSER features, resulting in 33% faster image retrieval.

We investigate modeling and recognition of arm manipulation actions of different levels of complexity. To model the process, we are using a combination of discriminative support vector machines and generative hidden Markov models. The experimental evaluation, performed with 10 people, investigates both definition and structure of primitive motions as well as the validity of the modeling approach taken.

In this work, we perform an extensive statistical evaluation for learning and recognition of object manipulation actions. We concentrate on single arm/hand actions but study the problem of modeling and dimensionality reduction for cases where actions are very similar to each other in terms of arm motions. For this purpose, we evaluate a linear and a nonlinear dimensionality reduction techniques: principal component analysis and spatio-temporal isomap. Classification of query sequences is based on different variants of Nearest Neighbor classification. We thoroughly describe and evaluate different parameters that affect the modeling strategies and perform the evaluation with a training set of 20 people.

Attention plays an important role in human processing of sensory information as a mean of focusing resources toward the most important inputs at the moment. It has in particular been shown to be a key component of vision. In vision it has been argued that the attentional processes are crucial for dealing with the complexity of real world scenes. The problem has often been posed in terms of visual search tasks. It has been shown that both the use of prior task and context information - top-down influences - and favoring information that stands out clearly in the visual field - bottom-up influences - can make such search more efficient. In a generic scene analysis situation one presumably has a combination of these influences and a computational model for visual attention should therefore contain a mechanism for their integration. Such models are abundant for human vision, but relatively few attempts have been made to define any that apply to computer vision.In this article we describe a model that performs such a combination in a principled way. The system learns an optimal representation of the influences of task and context and thereby constructs a biased saliency map representing the top-down information. This map is combined with bottom-up saliency maps in a process evolving over time as a function over the input. The system is applied to search tasks in single images as well as in real scenes, in the latter case using an active vision system capable of shifting its gaze. The proposed model is shown to have desired qualities and to go beyond earlier proposed systems.

This paper introduces a fast texture descriptor, the LU-transform. Itis inspired by previous methods, the SVD-transform and Eigen-transform, whichyield measures of image roughness by considering th ...