Management of Mobile Objects Location for Video Content Filtering

Abstract

The use of mobile devices and the development of geo-positioning technologies make applications that use location-based services very attractive and useful. These applications are composed of sensors that generate various and heterogeneous spatio-temporal data. Exploiting this spatio-temporal data to support video surveillance systems remains a relevant purpose for video content ltering. Since the data processed in such a context are heterogeneous (indoor and outdoor environment, various position types and reference systems, various data format), interoperability and management of these data remains a problem to be solved.In this paper, we de ne an approach that integrates camera location and eld of view metadata, mobile objects trajectories, and metadata from video content analysis algorithms (e.g. detection and movement of mobile objects) to address problems related to processing of huge amount of data (big data) generated by CCTV systems. We propose a new generic trajectory based query in order to handle trajectory segment's heterogeneity for both environments (indoor and outdoor). The proposed data model integrate multi-source metadata and enable to handle interoperability issue of data. Our querying mechanism enable to automatically retrieve video segments that could contain relevant information for the CCTV operator (suspects, trajectories, etc.).We provide an experimental evaluation demonstrating the utility of our approach in a real-world case. Results show that the proposed approach enhances the e ciency of investigators by reducing the search space, as the operator will analyze only the relevant data, therefore he needs less time for video processing (video reviewing).

Spatiotemporal retrieval of dynamic video object trajectories in geographical scenes

“…Deng et al (2010) achieved the analysis and retrieval of the spatiotemporal behavior of dynamic video objects and geospatial information. Kim et al (2014) and Panta, Qodseya, Péninou, and Sedes (2018) achieved dynamic video object retrieval based on the geographical area, direction, keywords, and time by collecting the geospatial information of the cameras. In further research, Deng et al (2012) and Xiu et al (2018) added the trajectory of a dynamic video object into a spatial database.…”

Integration of Multi-Camera Video Moving Objects and GIS

“…Thus, the search work was divided and refined, and the retrieval analysis was processed individually in each camera to obtain the search results. In recent years, some studies have attempted to construct an AOI [45] and trajectory template [46] in geographic space by combining multi-camera fields of view to carry out the spatialization of trajectory retrieval condition description. Although these methods realize the geospatial analysis of the retrieval conditions, the video content of each camera must be retrieved separately due to the lack of spatial-temporal correlation analysis of different camera video object trajectories.…”

Videoların Derin Öğrenme ile Sınıflandırılarak Filtrelenmesi

“…Kapalı devre televizyon kamera sistemleri tarafından üretilen büyük verinin (big data) işlenmesiyle, ilgili sorunları çözmek için kamera konumu ve görüş alanı meta verilerini, mobil nesnelerin yörüngelerini ve video içerik analizi algoritmalarından (örneğin mobil nesnelerin tespiti ve hareketi) meta verileri birleştiren bir yaklaşım tanımlanmıştır. Bu metot ile araştırmacıların insan veya nesne içermeyen kameraların görüntüleri kaldırılarak, arama süresi kısaltılmaktadır (Panta, Qodseya, & Péninou, 2018). Videolar üzerinde duman tespit edilmesi ile ilgili yapılan diğer bir çalışmada transfer öğrenmeden faydalanılmıştır.…”