Search

Real-time object detection on Unmanned Aerial Vehicles (UAVs) is a challenging issue due to the limited computing resources of edge GPU devices as Internet of Things (IoT) nodes. To solve this problem, in this paper, we propose a novel lightweight deep learning architectures named FasterX based on YOLOX model for real-time object detection on edge GPU. First, we design an effective and lightweight PixSF head to replace the original head of YOLOX to better detect small objects, which can be further embedded in the depthwise separable convolution (DS Conv) to achieve a lighter head. Then, a slimmer structure in the Neck layer termed as SlimFPN is developed to reduce parameters of the network, which is a trade-off between accuracy and speed. Furthermore, we embed attention module in the Head layer to improve the feature extraction effect of the prediction head. Meanwhile, we also improve the label assignment strategy and loss function to alleviate category imbalance and box optimization problems of the UAV dataset. Finally, auxiliary heads are presented for online distillation to improve the ability of position embedding and feature extraction in PixSF head. The performance of our lightweight models are validated experimentally on the NVIDIA Jetson NX and Jetson Nano GPU embedded platforms.Extensive experiments show that FasterX models achieve better trade-off between accuracy and latency on VisDrone2021 dataset compared to state-of-the-art models., 12 pages, 7 figures

A crystal oscillator is a typical frequency generating unit that is widely used in computers, neural chips, biosensors and other applications; thus, it is very important to estimate and predict its remaining useful life (RUL) precisely. However, there are few existing RUL prediction methods because the observed data involve various uncertainties, leading to the great limitation of RUL prediction in practical application. In this work, we propose an uncertainty RUL prediction method based on the exponential stochastic degradation model that considers the multiple uncertainty sources of oscillator stochastic degradation processes simultaneously. Next, based on Bayesian theory, a novel Bayesian-Extreme Learning Machine parameter-updating algorithm that combines the local and global similarity methods is presented and used to eliminate the effects of multiple uncertainty sources and predict the RUL accurately. The effectiveness of the method is demonstrated using the accelerated degradation tests of crystal oscillators. Through comparisons with the predicted results without uncertainty, the proposed method demonstrates its superiority in describing the stochastic degradation processes and predicting the oscillator's RUL.