Controlling background subtraction algorithms for robust object detection

Abstract

This paper presents a controller for background subtraction algorithms to detect mobile objects in videos. The controller has two main tasks.The first task is to guide the background subtraction algorithm to update its background representation. To realize this task, the controller has to solve two important problems: removing ghosts (background regions misclassified as object of interest) and managing stationary objects. The controller detects ghosts based on object borders. To manage stationary objects, the controller cooperates with the tracking task to detect faster stationary objects without storing various background layers which are difficult to maintain.The second task is to initialize the parameter values of background subtraction algorithms to adapt to the current conditions of the scene. These parameter values enable the background subtraction algorithms to be as much sensitive as possible and to be consistent with the feedback of classification and tracking task.

Evaluation of a monitoring system for event recognition of older people

“…It extracts foreground objects in the current frame using an extension of the Gaussian Mixture Model algorithm for background subtraction proposed by Nghiem et al [12]. Object tracking is performed by a multi-feature algorithm proposed by Chau et al [13] using features such as 2D size, 3D displacement, color histogram, and dominant color.…”

Accuracy and reliability of the RGB-D camera for measuring walking speed on a treadmill

“…People detection is performed at each frame using a background subtraction algorithm proposed by Nghiem et al [22]. A multifeature algorithm, such as 2D size, 3D displacement, color histogram and dominant color, proposed by Chau et al [23] is used for tracking.…”

Recognizing Gestures by Learning Local Motion Signatures of HOG Descriptors

“…People detection is performed by background subtraction to determine moving regions followed by a morphological dilation [25]. Then a people classifier is applied to determine bounding boxes around single individuals.…”