Siamese network have been extensively applied in the tracking field because of its huge speed advantage and great precision performance in solving the tracking problems. In this paper, we propose an efficient framework for real-time object tracking which is end-to-end trained offline-Fully Conventional Anchor-Free Siamese network (FCAF). Specifically, as the backbone network in Siamese trackers is relatively shallow, resulting in insufficient feature information acquired by the trackers and lower accuracy, the deep network ResNet-50 is adopted to provide richer feature representation. Meanwhile, the introduction of multi-layer feature fusion module effectively combines low-level detail information with high-level semantic features, improving the localization performance. In addition, we propose the anchor-free proposal network (AFPN) to replace the region proposal network (RPN). AFPN network consists of correlation section, implemented by depth-wise cross correlation, and supervised section which has two branches, one for classification and the other for regression. In order to suppress the prediction of low quality bounding boxes, center-ness branch is added. We conduct extensive experiments on the OTB2015 and VOT2016 public datasets, demonstrating that our proposed tracker achieves state-of-the-art performance. INDEX TERMS Object tracking, deep Siamese network, feature fusion, anchor-free network.
A new approach method to dealing with the puzzle of spectral analysis in prompt gamma neutron activation analysis (PGNAA) is developed and demonstrated. It consists of utilizing BP neural network to PGNAA energy spectrum analysis which is based on Monte Carlo (MC) simulation, the main tasks which we will accomplish as follows: (1) Completing the MC simulation of PGNAA spectrum library, we respectively set mass fractions of element Si, Ca, Fe from 0.00 to 0.45 with a step of 0.05 and each sample is simulated using MCNP. (2) Establishing the BP model of adaptive quantitative analysis of PGNAA energy spectrum, we calculate peak areas of eight characteristic gamma rays that respectively correspond to eight elements in each individual of 1000 samples and that of the standard sample. (3) Verifying the viability of quantitative analysis of the adaptive algorithm where 68 samples were used successively. Results show that the precision when using neural network to calculate the content of each element is significantly higher than the MCLLS.
The research of the existing speech recognition is based on speech feature parameter, acco-rding to the shortage of poor anti noise and larger storage capacity, etc. So, curve interpolation has been introduced into speech feature parameter extraction to enhance that. Refer to the speech spectrum dynamic changes and the short-time energy smooth stationary characteristics of speech signal, this paper puts forward and designs an arithmetic of speech feature parameter extraction based on interpolation, constructs the feature parameter extraction and personal identification scheme based on speech, and also designs critical modules algorithm. The detail process of feature parameter extraction: firstly, it creates two-dimensional coordinate for each frame data. Then, according to two-dimensional coordinate, it performs Lagrange cubic interpolation for segmentation the data in a signal frame. Get the interpolation coefficient, average the interpolation coefficient for a signal frame, here the average value is seen as the feature parameter for each frame. Lastly, the each frame’s feature parameter is connected in series to form feature parameter of the speech segment. The arithmetic has been simulated an experiment, in order to confirm the applicability and feasibility. The results illustrates the method has preferable anti noise performance, especially expression and storage for overall speech segment feature parameter show more obvious advantages.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.