J. Assfalg

Semantic annotation of sports videos

Taking into consideration the unique qualities of sports videos, we propose a system that semantically annotates them at different layers of semantic significance, using different elements of visual content. We decompose each shot into its visual and graphic content elements and, by combining several different low-level visual primitives, capture the semantic content at a higher level of significance.

Soccer highlights detection and recognition using HMMs

In this paper we report on our experience in the detection and recognition of soccer highlights in videos using hidden Markov models. A first approach relies on camera motion only, whereas a second one also includes information regarding the location of players on the playing field. While the former approach requires less information, the latter has proven to be more precise. Our experimental evaluation yields interesting results.

Content-Based Retrieval of 3-D Objects Using Spin Image Signatures

Retrieval by content of 3D models is becoming more and more important due to the advancements in 3D hardware and software technologies for acquisition, authoring and display of 3D objects, their ever-increasing availability at affordable costs, and the establishments of open standards for 3D data interchange. In this paper, we present a new method, referred to as spin image signatures, that develops on the original spin images approach, with adaptations to support effective retrieval by content. According to the method proposed, a set of spin images is derived for each model, to obtain a view-independent description of its 3D shape and a signature is evaluated for each spin image in the set. Clustering is hence performed on the set of spin image signatures to obtain a compact representation. Experimental results are presented, showing the effectiveness of the spin image signatures method for retrieval, also in comparison with other methods, and its sensitivity to model deformations

CityDev, an interactive multi-agents urban model on the web

In this paper we present CityDev, an interactive multi-agents simulation model of the development of a city. The model is based on agents, goods and markets. Each agent (family, industrial firm, developer, etc.) produces goods by using other goods, and trades the goods on the markets. Each good has a price, and the monetary aspects are included in the simulation. When agents produce goods and interact in the markets, the urban fabric is built and transformed. The computer model (simulator) runs on a 3-D spatial pattern organized in cubic cells. CityDev allows interactive users to get involved in the functioning of the model. In fact, they can manage agents generated by the simulator, as well as new agents created by themselves. Agents managed by users interact with agents managed by the simulator. In addition, an administration board interactively controls the development of the city trough the urban plan, the building of new roads and the location of public facilities. In the present paper the model is described and some results are shown.

Automatic extraction and annotation of soccer video highlights

Broadcasters are demonstrating interest in systems that ease the process of annotation the huge amount of live and archived video materials. Exploitation of such assets is considered a key method for the improvement of production quality, and sport videos are one of the most marketable assets. In particular, in Europe, soccer is one of the most relevant sport types. This paper deals with detection and recognition of soccer highlights, using an approach based on temporal logic models.

Content-based retrieval of 3D models through curvature maps: a CBR approach exploiting media conversion

Multimedia digital libraries are gaining an increasing relevance, and are growing in both number and size. Moreover, advancements in acquisition and authoring technologies have also caused new media types to be added to these libraries. For instance, animations and 3D models have recently come alongside more traditional media such as text, images, audio and video. In particular, even if 3D objects were initially included in multimedia digital libraries in the form of images (i.e., views of the objects), they are now also available in the form of 3D models. These allow to overcome the inherent limitations of an image-based representation of a three-dimensional reality. In this paper we present a novel method for description and retrieval of 3D models that relies on curvature maps: after an initial pre-processing of the model, differential properties of points on the surface of the 3D object are evaluated; the model surface is then deformed into an ellipsoid, and is mapped onto a 2D image retaining curvature information of the original model. Through this media conversion from 3D model to image map, we enable application of analysis, description, and matching techniques which have been originally conceived for the image medium. In particular, the two approaches described in this paper rely on histograms for a coarse but efficient description of tiles of the curvature map, and on weighted walkthroughs for a more precise description of homogeneous regions of the map, taking into account their spatial arrangement and areas. Experimental results reveal that both techniques can be successfully applied to curvature maps. The two approaches have been compared against other solutions presented in literature, and have shown a good retrieval performance (particularly in the case of region-based description).

Curvature maps for 3D CBR

Along with images and videos, 3D models have recently gained increasing attention for a number of reasons: advancements in 3D hardware and software technologies, their ever decreasing prices and increasing availability, affordable 3D authoring tools, and the establishment of open standards for 3D data interchange. In this paper we address the problem of content-based retrieval of 3D models. The solution we present here relies on the description of each model by means a curvature map: after an initial pre-processing of the model, differential properties of points on the surface of the 3D object are evaluated; the model surface is then warped into an ellipsoid, and is mapped onto a 2D image retaining curvature information of the original model. Matching is performed by comparing the 2D map of the query against the 2D maps of the database models. This method has been implemented in a prototype system supporting retrieval by content of 3D objects through a Web interface.

Automatic interpretation of soccer video for highlights extraction and annotation

Broadcasters are demonstrating interest in systems that ease the process of annotation the huge amount of live and archived video materials. Exploitation of such assets is considered a key method for the improvement of production quality, and sport videos are one of the most marketable assets. In particular, in Europe, soccer is one of the most relevant sport types. This paper deals with detection and recognition of soccer highlights, using an approach based on temporal logic models.

Querying by photographs: a VR metaphor for image retrieval

Interaction paradigms based on 3D interfaces and virtual reality offer new possibilities to overcome the limitations of query by example. We present a system that lets users navigate a 3D world where they can take photographs to query a database of images by content. Furthermore, users can interactively customize the virtual world by adding objects to the scene and editing object properties such as colors and textures.

Spin images for retrieval of 3D objects by local and global similarity

The ever increasing availability of 3D models demands for tools supporting their effective and efficient management. Among these tools, those enabling content-based retrieval play a key role. In this paper, we present a novel approach to global and local content-based retrieval of 3D objects that is based on spin images. Spin images are used to derive a view-independent description of both database and query objects. A set of spin images is first created for each object and the parts it is composed of; then, a descriptor is evaluated for each spin image in the set; clustering is performed on the set of image-based descriptors of each object to achieve a compact representation. Experimental results are presented for a test database of about 300 models, showing the effectiveness of retrieval for both object and part similarity.