Automatic Detection of Object of Interest and Tracking in Active Video

Abstract

We propose a novel method for automatic detection and tracking of Object of Interest (OOI) from actively acquired videos by non-calibrated cameras. The proposed approach benefits from the objectcentered property of Active Video and facilitates selfinitialization in tracking. We first use a color-saliency weighted Probability-of-Boundary (cPoB) map for keypoint filtering and salient region detection. Successive Classif ication and Ref inement (SCR) is used for tracking between two consecutive frames. A strong classifier trained on-the-fly by AdaBoost is utilized for keypoint classification and subsequent Linear Programming solves a maximum similarity problem to reject outliers. Experiments demonstrate the importance of Active Video during the data collection phase and confirm that our new approach can automatically detect and reliably track OOI in videos.

Robust Feedback Zoom Tracking for Digital Video Surveillance

“…It can also run as the base of various applications, including active tracking [31,32], salient recognition [33], speed estimation [34] and automatic driving [35,36]. In this paper, we use a PC with a 2.6-GHz Intel Pentium Dual-Core CPU and 2 GB of memory for observation and control.…”

An automatic method for detecting objects of interest in videos using surprise theory

“…Thus this paper uses the relative differences between these two optima in terms of mean and percentage for evaluation. The objective function can be formulated as shown in (10). W * obtained from (10) is the salient object.…”

“…It indicates that the salient objects can be seen as objects of interest. Although an automatic object detection method [10] has been proposed, it only uses the saliency in terms of spatial context rather than temporal context such that the novelties unfolded at temporal scales cannot be detected. In order to encode the temporal conspicuousness, surprise theory [12], [5] has been developed.…”