Surveillance Video Synopsis in GIS

Abstract

Surveillance videos contain a considerable amount of data, wherein interesting information to the user is sparsely distributed. Researchers construct video synopsis that contain key information extracted from a surveillance video for efficient browsing and analysis. Geospatial-temporal information of a surveillance video plays an important role in the efficient description of video content. Meanwhile, current approaches of video synopsis lack the introduction and analysis of geospatial-temporal information. Owing to the preceding problems mentioned, this paper proposes an approach called "surveillance video synopsis in GIS". Based on an integration model of video moving objects and GIS, the virtual visual field and the expression model of the moving object are constructed by spatially locating and clustering the trajectory of the moving object. The subgraphs of the moving object are reconstructed frame by frame in a virtual scene. Results show that the approach described in this paper comprehensively analyzed and created fusion expression patterns between video dynamic information and geospatial-temporal information in GIS and reduced the playback time of video content.

Extracting Objects’ Spatial–Temporal Information Based on Surveillance Videos and the Digital Surface Model

“…11 (12) Obtain object tracking results according to Equation (12) and correct them according to the distortion correction model of the camera. Then, the distortion correction results are transferred to the mapping model to obtain the geographical trajectories of the objects.…”

“…The homography matrixbased method is not suitable for large-scale scenes or scenes with complex terrain. In the aspect of fusion, the research is relatively scattered, as it is used for multi-camera object tracking [9], path searching [10], video fragment data management [11], video synopses [12], crowd counting [13], etc. The current real world is in rapid development and change, and how to express and recognize it thoroughly is very important.…”

Real‐time fusion of multiple videos and 3D real scenes based on optimal viewpoint selection

“…With the development of IoT technology and the large‐scale application of sensors (Xu, Du, et al, 2021), real‐time video and image data have grown rapidly, such as urban surveillance videos (Xie et al, 2017; Zhang, Shi, et al, 2021), vehicle‐mounted devices (Kim & Kwon, 2016), panoramic images (Liu et al, 2017), video GIS and Internet social platforms. It can make up for the lack of 3D model data currency and increase the dynamics of 3D scenes to combine real‐time videos with real 3D model data (Milosavljevic et al, 2016; Xie et al, 2019), which is also of great significance for improving the ability to perceive the real world in real time.…”

Multi‐camera video synopsis of a geographic scene based on optimal virtual viewpoint

“…Accordingly, the present research focused on how to effectively select fewer virtual viewpoints in geographic scenes and efficiently observe the video content of multiple cameras, thus providing video synopsis results that can reduce playback time and express the cross‐camera global motion of video objects. Based on our previous work (Xie, Wang, Liu, & Wu, 2017), the present research proposed a four‐part method of multi‐camera video synopsis in a geographic scene based on optimal virtual view selection. First, the camera position and field of view were identified.…”