High-level Descriptors Research Articles

Automatic Analysis of the Content of Cell Biological Videos and Database Organization of Their Metadata Descriptors

We present a video content analysis and metadata organizational system for research videos arising from biological microscopy of living cells. Automated procedures are described to determine the position, size, shape and orientation of cells in each video frame. From the temporal changes in the values of these simple metadata parameters, high-level descriptors are derived that describe the semantic content of the video. This content information (specific intrinsic metadata) is of high information value, since it describes the behavior of cells and the timing of events within the video, including changes in environmental conditions experienced by the cells. When such metadata are properly organized in a searchable database, a content-based video query and retrieval system may be developed to locate particular objects, events or behaviors. Moreover, the availability of such semantic contents in the formal and generic format we propose will allow the application of data mining techniques and the amassing of more elaborate knowledge, e.g., species classification depending on behavior, patterns in response to environment changes, etc. The suitability and functionality of the proposed metadata model is demonstrated by the automated analysis of five different types of biological experiments, recording epithelial wound healing, bacterial multiplication, the rotations of tethered bacteria, and the swimming of motile bacteria and of human sperm.

Analysis of respiratory pressure–volume curves in intensive care medicine using inductive machine learning

We present a case study of machine learning and data mining in intensive care medicine. In the study, we compared different methods of measuring pressure–volume curves in artificially ventilated patients suffering from the adult respiratory distress syndrome (ARDS). Our aim was to show that inductive machine learning can be used to gain insights into differences and similarities among these methods. We defined two tasks: the first one was to recognize the measurement method producing a given pressure–volume curve. This was defined as the task of classifying pressure–volume curves (the classes being the measurement methods). The second was to model the curves themselves, that is, to predict the volume given the pressure, the measurement method and the patient data. Clearly, this can be defined as a regression task. For these two tasks, we applied C5.0 and CUBIST, two inductive machine learning tools, respectively. Apart from medical findings regarding the characteristics of the measurement methods, we found some evidence showing the value of an abstract representation for classifying curves: normalization and high-level descriptors from curve fitting played a crucial role in obtaining reasonably accurate models. Another useful feature of algorithms for inductive machine learning is the possibility of incorporating background knowledge. In our study, the incorporation of patient data helped to improve regression results dramatically, which might open the door for the individual respiratory treatment of patients in the future.

Content-based indexing and retrieval of TV news

Effective retrieval and browsing by content of videos is based on the association of high-level information with visual data. Automatic extraction of high-level content descriptors requires to exploit the technical characteristics of video types. This paper comprises a complete system for content-based retrieval and browsing of news reports; the annotation of the video stream is fully automated and is based both on visual features extracted from video shots and on textual strings extracted from captions and audio tracks.

Robot programming by Demonstration (RPD): Supporting the induction by human interaction

Programming by Demonstration (PbD) is a programming method that allows software developers to add new functionalities to a system by simply showing them in the form of few examples. In the robotics domain it has the potential to reduce the amount of time required for programming and also to make programming more “natural”. Just imagine the task of assembling a torch by a manipulator. Wouldn't it be nice to just assemble the torch with one's own hands, watched by video and laser cameras and maybe wearing data gloves, i. e. sensors that provide the data to automatically generate the necessary robot program for the assembly task? And wouldn't it be even nicer to demonstrate the task with few different torches, but achieving an assembly function for all possible variants of them? In order to realize such a PbD environment, at least two major problems have to be solved. First, the sensor data have to be transformed to high-level situation-action descriptors, a task that is not yet solved in general. Second, if a generalization is required, induction algorithms must be applied to the recorded and transformed traces, aiming to find the most general user-intended function from only few examples. In this article we will concentrate only on the second problem. The described experimental environment consists of an industrial robot (PUMA 260b), a 6D teach mouse input device, and some sensors. Various data can be recorded during a demonstration for further processing in the PbD system running on a workstation. The objective is to explore the possibilities of integrating learning and clustering algorithms for automated robot programming. In particular it is investigated how human interaction within system- as well as user-initiated dialogs can support the induction component.

Generalized cones from serial sections

Slices through three-dimensional objects are a common form of data in biomedical research and practice. We report here methods for extracting high-level shape descriptors from slice data. Objects are described as generalized cones and relations between them. The cones used have straight-line spines, elliptical cross sections, and a sweeping rule whereby the lengths of the major and minor axes of the ellipses change linearly and independently. Most smooth elongated objects can be described as compositions of such cone primitives. Two algorithms were developed and tested for extracting cone descriptions from stacks of parallel slices. A local algorithm creates cones from elliptical regions on adjacent slices. A predictive algorithm hypothesises cones from regions on nonadjacent slices and then tests the hypotheses by intelligently requesting intermediate slices. Both algorithms explain complex noneliiptical regions (joints, typically) by using cones impinging upon them as keys to their shapes. Output cone sets are covers, not partitions, of the data. Topological and geometric information is available in the output description. Results of processing a “Y,” a helix, a heart phantom, and a digitized canine heart are discussed.