Video surveillance using distance maps

Abstract

Human vigilance is limited; hence, automatic motion and distance detection is one of the central issues in video surveillance. Hereby, many aspects are of importance, this paper specially addresses: efficiency, achieving real-time performance, accuracy, and robustness against various noise factors. To obtain fully controlled test environments, an artificial development center for robot navigation is introduced in which several parameters can be set (e.g., number of objects, trajectories and type and amount of noise). In the videos, for each following frame, movement of stationary objects is detected and pixels of moving objects are located from which moving objects are identified in a robust way. An Exact Euclidean Distance Map (E 2 DM) is utilized to determine accurately the distances between moving and stationary objects. Together with the determined distances between moving objects and the detected movement of stationary objects, this provides the input for detecting unwanted situations in the scene. Further, each intelligent object (e.g., a robot), is provided with its E 2 DM, allowing the object to plan its course of action. Timing results are specified for each program block of the processing chain for 20 different setups. So, the current paper presents extensive, experimentally controlled research on real-time, accurate, and robust motion detection for video surveillance, using E 2 DMs, which makes it a unique approach.

Three-dimensional fast exact Euclidean distance (3D-FEED) maps

“…3D-FEED can be employed in a range of settings; e.g., trajectory planning, neuromorphometry 14 , skeletonization, Bouligand-Minkowsky fractal dimension, Watershed algorithms, robot navigation 2 , video surveillance 15 and Voronoi tessellations 12 . Especially for those applications where both speed and precision of the algorithm are of the utmost importance, 3D-FEED is the solution.…”

Distance Transforms: Academics Versus Industry

“…", as it is nowadays considered a standard procedure (cf. [28,69,71]). Lastly, they state that it is required to have "a distance detector for detecting the distance from the reference point to the moving object, from the detected object image and the distance map .…”

“…On the other hand, they are applied within various applications; see for example, [53,69,91]. In the last case, DT are either applied by themselves or as an intermediate method such as: route planning and (robot) navigation [26,28,56,61,70], collision prevention [27], video surveillance [69,71], internal radiation therapy [13], handwriting recognition [62,72], (medical) image segmentation [9][10][11][13][14][15] (see also Fig.…”

“…On the other hand, they are applied within various applications; see for example, [53,69,91]. In the last case, DT are either applied by themselves or as an intermediate method such as: route planning and (robot) navigation [26,28,56,61,70], collision prevention [27], video surveillance [69,71], internal radiation therapy [13], handwriting recognition [62,72], (medical) image segmentation [9][10][11][13][14][15] (see also Fig. (1)), skeletonization [63,73], Voronoi tessellations [30,64], BouligandMinkowsky fractal dimension [74], Watershed algorithms [65], neuromorphometry [73,75], MRI data analysis [76,92], and volume rendering [36,77], to mention but a few.…”

“…These developments also resulted in a further extension of the range of applications (cf. Section 3), including: route planning [70], (robot) navigation [28,56], video surveillance [69,71], handwriting recognition [72], internal radiation therapy [13], image segmentation [10,11] (see also Fig. (1)), skeletonization [73], Bouligand-Minkowsky fractal dimension [74], neuromorphometry [73,75], MRI data analysis [76], and volume rendering [77].…”