arXiv subjects

Eng Gee Lim

Publications and source records attributed to Eng Gee Lim.

44 records · Page 3Linked to original sources

arXiv2020

A Semi-Blind Multiuser SIMO GFDM System in the Presence of CFOs and IQ Imbalances

In this paper, we investigate an open topic of a multiuser single-input-multiple-output (SIMO) generalized frequency division multiplexing (GFDM) system in the presence of carrier frequency offsets (CFOs) and in-phase/quadrature-phase (IQ) imbalances. A low-complexity semi-blind joint estimation scheme of multiple channels, CFOs and IQ imbalances is proposed. By utilizing the subspace approach, CFOs and channels corresponding to U users are first separated into U groups. For each individual user, CFO is extracted by minimizing the smallest eigenvalue whose corresponding eigenvector is utilized to estimate channel blindly. The IQ imbalance parameters are estimated jointly with channel ambiguities by very few pilots. The proposed scheme is feasible for a wider range of receive antennas number and has no constraints on the assignment scheme of subsymbols and subcarriers, modulation type, cyclic prefix length and the number of subsymbols per GFDM symbol. Simulation results show that the proposed scheme significantly outperforms the existing methods in terms of bit error rate, outage probability, mean-square-errors of CFO estimation, channel and IQ imbalance estimation, while at much higher spectral efficiency and lower computational complexity. The Cramer-Rao lower bound is derived to verify the effectiveness of the proposed scheme, which is shown to be close to simulation results.

eess.SP↗

arXiv2020

Fast Template Matching and Update for Video Object Tracking and Segmentation

In this paper, the main task we aim to tackle is the multi-instance semi-supervised video object segmentation across a sequence of frames where only the first-frame box-level ground-truth is provided. Detection-based algorithms are widely adopted to handle this task, and the challenges lie in the selection of the matching method to predict the result as well as to decide whether to update the target template using the newly predicted result. The existing methods, however, make these selections in a rough and inflexible way, compromising their performance. To overcome this limitation, we propose a novel approach which utilizes reinforcement learning to make these two decisions at the same time. Specifically, the reinforcement learning agent learns to decide whether to update the target template according to the quality of the predicted result. The choice of the matching method will be determined at the same time, based on the action history of the reinforcement learning agent. Experiments show that our method is almost 10 times faster than the previous state-of-the-art method with even higher accuracy (region similarity of 69.1% on DAVIS 2017 dataset).

cs.CV↗

arXiv2019

Progressive Sample Mining and Representation Learning for One-Shot Person Re-identification with Adversarial Samples

In this paper, we aim to tackle the one-shot person re-identification problem where only one image is labelled for each person, while other images are unlabelled. This task is challenging due to the lack of sufficient labelled training data. To tackle this problem, we propose to iteratively guess pseudo labels for the unlabeled image samples, which are later used to update the re-identification model together with the labelled samples. A new sampling mechanism is designed to select unlabeled samples to pseudo labelled samples based on the distance matrix, and to form a training triplet batch including both labelled samples and pseudo labelled samples. We also design an HSoften-Triplet-Loss to soften the negative impact of the incorrect pseudo label, considering the unreliable nature of pseudo labelled samples. Finally, we deploy an adversarial learning method to expand the image samples to different camera views. Our experiments show that our framework achieves a new state-of-the-art one-shot Re-ID performance on Market-1501 (mAP 42.7%) and DukeMTMC-Reid dataset (mAP 40.3%). Code will be available soon.

cs.CV↗

arXiv2019

Adaptive ROI Generation for Video Object Segmentation Using Reinforcement Learning

In this paper, we aim to tackle the task of semi-supervised video object segmentation across a sequence of frames where only the ground-truth segmentation of the first frame is provided. The challenges lie in how to online update the segmentation model initialized from the first frame adaptively and accurately, even in presence of multiple confusing instances or large object motion. The existing approaches rely on selecting the region of interest for model update, which however, is rough and inflexible, leading to performance degradation. To overcome this limitation, we propose a novel approach which utilizes reinforcement learning to select optimal adaptation areas for each frame, based on the historical segmentation information. The RL model learns to take optimal actions to adjust the region of interest inferred from the previous frame for online model updating. To speed up the model adaption, we further design a novel multi-branch tree based exploration method to fast select the best state action pairs. Our experiments show that our work improves the state-of-the-art of the mean region similarity on DAVIS 2016 dataset to 87.1%.

cs.CV↗

arXiv2019

A Beaconless Asymmetric Energy-Efficient Time Synchronization Scheme for Resource-Constrained Multi-Hop Wireless Sensor Networks

The ever-increasing number of WSN deployments based on a large number of battery-powered, low-cost sensor nodes, which are limited in their computing and power resources, puts the focus of WSN time synchronization research on three major aspects, i.e., accuracy, energy consumption and computational complexity. In the literature, the latter two aspects have not received much attention compared to the accuracy of WSN time synchronization. Especially in multi-hop WSNs, intermediate gateway nodes are overloaded with tasks for not only relaying messages but also a variety of computations for their offspring nodes as well as themselves. Therefore, not only minimizing the energy consumption but also lowering the computational complexity while maintaining the synchronization accuracy is crucial to the design of time synchronization schemes for resource-constrained sensor nodes. In this paper, focusing on the three aspects of WSN time synchronization, we introduce a framework of reverse asymmetric time synchronization for resource-constrained multi-hop WSNs and propose a beaconless energy-efficient time synchronization scheme based on reverse one-way message dissemination. Experimental results with a WSN testbed based on TelosB motes running TinyOS demonstrate that the proposed scheme conserves up to 95% energy consumption compared to the flooding time synchronization protocol while achieving microsecond-level synchronization accuracy.

cs.NI↗

arXiv2016

Simulation Study of an Energy-Efficient Time Synchronization Scheme based on Source Clock Frequency Recovery in Asymmetric Wireless Sensor Networks

In this paper we report preliminary results of a simulation study on an energy-efficient time synchronization scheme based on source clock frequency recovery (SCFR) at sensor nodes in asymmetric wireless sensor networks (WSNs), where a head node --- serving as a gateway between wired and wireless networks --- is equipped with a powerful processor and supplied power from outlet, and sensor nodes --- connected only through wireless channels --- are limited in processing and battery-powered. In the SCFR-based WSN time synchronization scheme, we concentrate on battery-powered sensor nodes and reduce their energy consumption by minimizing the number of message transmissions from sensor nodes to the head node. Through simulation experiments we analyze the performance of the SCFR-based WSN time synchronization scheme, including the impact of SCFR on time synchronization based on two-way message exchange, and demonstrate the feasibility of the proposed time synchronization scheme.

cs.NI↗

arXiv2016

Energy-Efficient Time Synchronization Based on Asynchronous Source Clock Frequency Recovery and Reverse Two-Way Message Exchanges in Wireless Sensor Networks

We consider energy-efficient time synchronization in a wireless sensor network where a head node (i.e., a gateway between wired and wireless networks and a center of data fusion) is equipped with a powerful processor and supplied power from outlet, and sensor nodes (i.e., nodes measuring data and connected only through wireless channels) are limited in processing and battery-powered. It is this asymmetry that our study focuses on; unlike most existing schemes to save the power of all network nodes, we concentrate on battery-powered sensor nodes in minimizing energy consumption for time synchronization. We present a time synchronization scheme based on asynchronous source clock frequency recovery and reverse two-way message exchanges combined with measurement data report messages, where we minimize the number of message transmissions from sensor nodes, and carry out the performance analysis of the estimation of both measurement time and clock frequency with lower bounds for the latter. Simulation results verify that the proposed scheme outperforms the schemes based on conventional two-way message exchanges with and without clock frequency recovery in terms of the accuracy of measurement time estimation and the number of message transmissions and receptions at sensor nodes as an indirect measure of energy efficiency.

cs.NI↗

arXiv2015

On enery-efficient time synchronization based on source clock frequency recovery in wireless sensor networks

In this paper we study energy-efficient time synchronization schemes with focus on asymmetric wireless sensor networks, where a head node, which is connected to both wired & wireless networks, is equipped with a powerful processor and supplied power from outlet, and sensor nodes, which are connected only through wireless channels, are limited in processing and battery-powered. It is this asymmetry that we focus our study on; unlike existing schemes saving the power of all sensor nodes in the network (including the head node), we concentrate on battery-powered sensor nodes in minimizing energy consumption for synchronization. Specifically, we discuss a time synchronization scheme based on source clock frequency recovery, where we minimize the number of message transmissions from sensor nodes to the head node, and its extension to network-wide, multi-hop synchronization through gateway nodes.

cs.NI↗