No abstract

Steerable cameras that can be controlled via a network, to retrieve telemetries of interest have become popular. In this paper, we develop a framework called AcTrak , to automate a camera’s motion to appropriately switch between (a) zoom ins on existing targets in a scene to track their activities, and, (b) zoom out to search for new targets arriving to the area of interest. Specifically, we seek to achieve a good trade-off between the two tasks, i.e., we want to ensure that new targets are observed by the camera before they leave the scene, while also zooming in on existing targets frequently enough to monitor their activities. There exist prior control algorithms for steering cameras to optimize certain objectives; however, to the best of our knowledge, none have considered this problem, and do not perform well when target activity tracking is required. AcTrak  automatically controls the camera’s PTZ configurations using reinforcement learning (RL), to select the best camera position given the current state. Via simulations using real datasets, we show that AcTrak  detects newly arriving targets 30% faster than a non-adaptive baseline and rarely misses targets, unlike the baseline which can miss up to 5% of the targets. We also implement AcTrak  to control a real camera and demonstrate that in comparison with the baseline, it acquires about 2 × more high resolution images of targets.

No abstract

No abstract

In this paper we study the problem of tag identification in multi-reader RFID systems. In particular, we propose a novel solution to the reader-to-reader collisions and tag collisions in multi-reader systems, using the concept of bit tracking [1]. Towards this objective, we propose the multi-reader RFID tag identification using bit tracking (MRTI-BT) algorithm which allows concurrent tag identification, by neighboring RFID readers, as opposed to time-consuming scheduling. First, MRTI-BT identifies tags exclusive to different RFIDs, concurrently. Second, the concept of bit tracking and the proposed parallel identification property are leveraged to reduce the identification time compared to the state-of-the-art. Our simulation results exhibit considerable performance improvement with 113% reduction in the identification time, on the average, compared to Season [2].