No abstract

Multi-object tracking has been a key research subject in many computer vision applications. We propose a novel approach based on multi-agent deep reinforcement learning (MADRL) for multi-object tracking to solve the problems in the existing tracking methods, such as a varying number of targets, noncausal, and non-realtime. At first, we choose YOLO V3 to detect the objects included in each frame. Unsuitable candidates were screened out and the rest of detection results are regarded as multiple agents and forming a multi-agent system. Independent Q-Learners (IQL) is used to learn the agents' policy, in which, each agent treats other agents as part of the environment. Then, we conducted offline learning in the training and online learning during the tracking. Our experiments demonstrate that the use of MADRL achieves better performance than the other state-of-art methods in precision, accuracy, and robustness.

This paper presents a method for using neighboring cascaded quadruplet (CQ) units sharing resonators to decrease the order of filter so as to reduce the size of a high temperature superconducting (HTS) linear phase filter. The main advantage is that it will not reduce the number of the filter's transmission zeros, and will not increase the difficulty of circuit design and tuning. Based on this method, this paper presents a 10-order HTS linear phase filter with two pairs of transmission zeros on double-sided YBCO/LaAlO 3 /YBCO films with a size of 20.3 mm×20.92 mm, a thickness of 0.5 mm and a dielectric constant of 24.04. At 77 K, the filter's measured center frequency is 830.03 MHz with a bandwidth of 10 MHz, an edge out-ofband rejection greater than 30 dB MHz −1 , and a group delay variation of less than ±10 ns over 60% of the filter bandwidth.

No abstract

Multiple-object tracking is a challenging issue in the computer vision community. In this paper, we propose a multiobject tracking algorithm in videos based on long short-term memory (LSTM) and deep reinforcement learning. Firstly, the multiple objects are detected by the object detector YOLO V2. Secondly, the problem of single-object tracking is considered as a Markov decision process (MDP) since this setting provides a formal strategy to model an agent that makes sequence decisions. The single-object tracker is composed of a network that includes a CNN followed by an LSTM unit. Each tracker, regarded as an agent, is trained by utilizing deep reinforcement learning. Finally, we conduct a data association using LSTM for each frame between the results of the object detector and the results of single-object trackers. From the experimental results, we can see that our tracker achieves better performance than the other state-of-the-art methods. Multiple targets can be steadily tracked even when frequent occlusions, similar appearances, and scale changes happened.