Girshick, R., Donahue, J., Darrell, T.: Region-based convolutional networks for accurate object detection and segmentation. In: IEEE Conference on Computer Vision & Pattern Recognition, pp. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. Nam, H., Han, B.: Learning multi-domain convolutional neural networks for visual tracking. Wu, P.F., Xiao, F., Sha, C., Huang, H.P., Wang, R.C., Xiong, N.: Node scheduling strategies for achieving full-view area coverage in camera sensor networks. In: IEEE International Conference on Computer Vision, pp. Wang, L., Ouyang, W., Wang, X.: Visual tracking with fully convolutional networks. Wang, N., Yeung, D.Y.: Learning a deep compact image representation for visual tracking. Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark. The tracking model proposed above demonstrates good performance in an existing tracking benchmark. Specifically, Spatial-Temporal Context learning (STC) algorithm is added into our model to achieve its tracking performance more efficiently. In order to maximize tracking performance and make a great use the continuous, inter-frame correlation in the long term, this paper harnesses the power of deep reinforcement learning (RL) algorithm. So a recurrent convolutional neural network is adopted acting as an agent in this model, with the important insight that it can interact with the video overtime. Considering the tracking task can be processed as a sequential decision-making process and historical semantic coding that is highly relevant to future decision-making information. Crucially, this task is tackled in an end-to-end approach. This paper presents a novel model for IoT video sensors object tracking via deep Reinforcement Learning (RL) algorithm and spatial-temporal context learning algorithm, which provides a tracking solution to directly predict the bounding box locations of the target at every successive frame in video surveillance. The new video sensor network has gradually become a research hotspot in the field of wireless sensor network, and its rich perceptual information is more conducive to the realization of target positioning and tracking function. Using the IoT, different items or devices can be allowed to continuously generate, obtain, and exchange information. The comparison of all three simulation methods was performed as well.The Internet of Things (IoT) is the upcoming one of the major networking technologies. The results of the research present that with exploiting RFID technology, the total disassembly time of a single helicopter was decreased. The computer simulation models were developed using “AnyLogic 7.1” software. Afterwards the results of all three simulation approaches (AB, SD and DE) were compared with considering two scenarios of RL RFID-enabled and RL without RFID. Therefore, in this study, after designing and constructing the RL system through the real case study from Bell Helicopter Company with the aid of unified modeling language (UML), three simulation techniques were proposed for the model. Besides, each computer simulation approach has its own benefits for understanding the RL network from different aspects. The functionality of the RL system can be noticeably elevated by integrating these two systems and techniques. An automated data capturing system like RFID and computer simulation techniques such as agent-based (AB), system dynamic (SD) and discrete event (DE) provide a reliable platform for effective RL tracking and control, as they can respectively decrease the time needed to obtain data and simulate various scenarios for suitable best corrective actions. The RFID system can evaluate and analyze RL performance timely so that in the case of deviation in any areas of RL, the appropriate corrective actions can be taken in a quick manner. A key factor for the success and effectiveness of RL system is to conduct real-time monitoring system such as radio frequency identification (RFID) technology. On the other hand, successful RL network requires a reliable monitoring and control system. However, executing and fulfilling an efficient recovery network needs constructing appropriate logistics system for flows of new, used, and recovered products. Reverse Logistics (RL) has become increasingly popular in different industries especially aerospace industry over the past decade due to the fact that RL can be a profitable and sustainable business strategy for many organizations.
0 Comments
Leave a Reply. |