Abstract The interpretation of remotely sensed images in a spatiotemporal context is becoming a valuable research topic. It helps predicting future trends and behaviors, allowing remotely sensed users to make proactive and knowledgedriven decisions. These decisions are useful for urban sprawl prevention, estimation of changes regarding productivity, and planting status of agricultural products, etc. However, the process of change prediction is... The interpretation of remotely sensed images in a spatiotemporal context is becoming a valuable research topic. It helps predicting future trends and behaviors, allowing remotely sensed users to make proactive and knowledgedriven decisions. These decisions are useful for urban sprawl prevention, estimation of changes regarding productivity, and planting status of agricultural products, etc. However, the process of change prediction is usually characterized by several types of imperfection, such as uncertainty, imprecision, and ignorance. Fusion of several decisions about changes helps improve the change prediction process and decrease the associated imperfections. In this paper, we propose to use an adaptive possibility fusion approach to take into account the reliability of each change decision. This reduces the inuence of unreliable information and thus enhances the relative weight of reliable information. Decisions about changes are obtained by applying previous works and represented as spatiotemporal trees. These trees are combined to obtain more accurate and complete ones. In addition, an uncertainty propagation module is developed to estimate the uncertainty in the output of the knowledge fusion module from the uncertainty in the inputs. This helps us to identify robust conclusions. The proposed approach is validated using SPOT images representing the Saint-Denis region, capital of Reunion Island. Results show good performances of the proposed approach in predicting change for the urban zone in the Saint-Denis region. Read More Read Less

Abstract In many different application fields the amount and importance of spatio-temporal data (i.e., temporally and/ or spatially qualified data) is increasing in last years and users need new solutions for their management. In [4] a framework for modeling spatio-temporal data in relational databases has been proposed. The model is based on the notions of temporal, spatial, and spatio-temporal granularities. Once... In many different application fields the amount and importance of spatio-temporal data (i.e., temporally and/ or spatially qualified data) is increasing in last years and users need new solutions for their management. In [4] a framework for modeling spatio-temporal data in relational databases has been proposed. The model is based on the notions of temporal, spatial, and spatio-temporal granularities. Once data have been modeled, they must be queried through query languages that are also able to exploit their spatio-temporal components. In this paper we propose a spatio-temporal query language, called ST4SQL. The proposed language extends the well-known SQL syntax and the T4SQL temporal query language [8]. The proposed query language deals with different temporal, spatial and spatio-temporal semantics. These semantics allow one to specify how the system must manage temporal and spatial dimensions for evaluating the queries. Moreover, the query language introduces new constructs for grouping data with respect to temporal and spatial dimensions. Both semantics and grouping constructs take into account and exploit data qualified with granularities. Read More Read Less

Abstract In sports events shown on TV or on the Internet, having the names and uniform numbers of the players displayed beside the players on the screen helps viewers to identify the players. Conventional methods of annotating and tracking objects utilize image recognition techniques with highresolution images, so players captured on camera from a long distance are too small for accurate... In sports events shown on TV or on the Internet, having the names and uniform numbers of the players displayed beside the players on the screen helps viewers to identify the players. Conventional methods of annotating and tracking objects utilize image recognition techniques with highresolution images, so players captured on camera from a long distance are too small for accurate recognition. In response to this problem, we propose a method for identifying and tracking moving objects with a combination of wearable acceleration sensors and image recognition techniques. In our method, the method recognizes moving objects by matching the context picked up by the wearable sensors with the context inferred during the image processing. Evaluation results demonstrated the effectiveness of the proposed method. Read More Read Less