No abstract

No abstract

No abstract

b this paper, w describe a technique to hate volumes using a volumetric skdeton. The skdeton is computed born the actual volum~b=ed on a reversible thinning procedure u~ing the distance transfom Polygons are never computed, and the entire procremains in the volume domain. The skeletal points =e connected and arranged in a 'skeletontree", which can be used for artictiation in an animation program. The ti volume object is regrown Corn the trf omed skdetti points. Since the skdeton is an intuitive mechanism for animation, the animator deforms the skeleton and causes corre~onding deformations in the volume object. The volumetric skdeton can *O be used for volume morphing, automatic path navigation, volume smoothing and compresGon/decimation.

Situational awareness applications require a highly detailed geospatial visualization covering a large geographic area. Conventional polygon based terrain modeling would exceed the capacity of current computer rendering. Terrain visualization techniques for a situational awareness application are described in this case study. Visualizing large amounts of terrain data has been achieved using very large texture maps. Sun shading is applied to the terrain texture map to enhance perception of relief features. Perception of submarine positions has been enhanced using a translucent, textured water surface. Each visualization technique is illustrated in the accompanying video tape. Keywords: Terrain Visualization, Situational Awareness, DTED, Digital Maps lntroducti,onSituational awareness visualization applications require the representation of large geographic areas and thousands of military units. The extent of the area of interest (playbox) is typically one million square miles. Observers want to see the highest resolution data available and be able to navigate through the model at interactive rates. The geo-spatial information &splayed consists of elevation data, a variety of maps, and high resolution imagery. The size of the playbox and the amount of data present a considerable demand on both the terrain model and the visualization software. A Joint Forces operation simultaneously involves ground, sea, and air forces. Military units must be displayed in the context of terrain, on the sea, under the sea, and in the air. Collateral maps and images also aid in understanding the movement and placement of units.The Joint Operations Visualization Environment (JOVE) [5] has been developed to assist top level military decision makers. JOVE uses three rear projected displays driven from an SGI Onyx2 Infinite Reality (IR) computer. Interaction is provided through a joystick and speech interface. JOVE also allows accurate navigation through the model over a range of viewer positions. A typical scene from the situational awareness application is shown in Video Sequence 1. This case study describes techniques used for realistic modeling and navigation of geo-spatial data in JOVE. Section 2 presents an outline of our model and its components. Section 3 describes visualization of elevation data. Section 4 describes techniques to improve perception of sea and under sea vessels. Section 5 discusses the visualization of maps and overhead imagery. The Earth ModelOur model starts with a sphere representing the Earth. The entire world is portrayed because:1. Units can move out of the playbox.2. Far-ranging units, such as aircraft, could be stationed anywhere around the world. Satellite imagery [I] of the Earth is texture-mapped onto the geometric model. The cloudless imagery portrays the world at 4 kilometer resolution. Lines of latitude and longitude are drawn over the imagery at 10 degree intervals. The sphere geometry is modeled to use polygons efficiently and also to avoid thin triangles near the poles. The highest polyg...

In this paper, we describe a method to detect collisions between volumetric objects. A hierarchy of bounding spheres is computed from a volumetric object based on the distance transform. Multiple levels of bounding approximations to the volumetric object are automatically computed. The computation of bounding spheres is based on the shape of the object. Only those spheres which are essential to the description of the shape at a certain level of detail are included. This results in a tighter fitting bounding volume compared to existing methods for collision detection. Because of the tighter fit, we are able to use fewer spheres for collision testing at each level, thus decreasing computation time. Since our method is based on the shape of the object, the hierarchical spheres are determined for the first frame and can then animate along with the volumetric object.

No abstract

Video analytics technology has matured and found application in a variety of fields over the past decade. This chapter discusses the current state-ofthe-art, and describes challenges for future video analytics implementations. Current applications and markets for video analytics are described in the context of a processing pipeline. Application-specific challenges are described with potential solutions to those challenges. This chapter also lists some implementation considerations for embedded video analytics and concludes with future and emerging applications of video analytics. IntroductionVideo analytics is an industry term for the automated extraction of information from video for a variety of purposes. It is a combination of imaging, computer vision, pattern analysis, and machine intelligence applied to real-world problems. Its utility spans several industry segments including video surveillance, retail, and transportation. Video analytics is distinct from machine vision or machine inspection and is similar to automotive vision. Some applications of analytics include the detection of suspicious objects and activities for offering better security, in license plate recognition and traffic analysis for intelligent transportation systems, and in customer counting and queue management for retail applications.The past decade has seen the maturation of algorithms and the adoption of analytics solutions in these markets. Analytics has progressed from research labs, with algorithms running on powerful workstations and PCs to current real-time embedded implementations on consumer-grade embedded processors. At the same time, the range of applications for analytics has also grown, with current trends indicating