Searcharxiv⌕ Search

arXiv subjects

Peng Lu

Publications and source records attributed to Peng Lu.

At least 127 records · Page 7Linked to original sources
arXiv2020

Training-Set Distillation for Real-Time UAV Object Tracking

Correlation filter (CF) has recently exhibited promising performance in visual object tracking for unmanned aerial vehicle (UAV). Such online learning method heavily depends on the quality of the training-set, yet complicated aerial scenarios like occlusion or out of view can reduce its reliability. In this work, a novel time slot-based distillation approach is proposed to efficiently and effectively optimize the training-set's quality on the fly. A cooperative energy minimization function is established to score the historical samples adaptively. To accelerate the scoring process, frames with high confident tracking results are employed as the keyframes to divide the tracking process into multiple time slots. After the establishment of a new slot, the weighted fusion of the previous samples generates one key-sample, in order to reduce the number of samples to be scored. Besides, when the current time slot exceeds the maximum frame number, which can be scored, the sample with the lowest score will be discarded. Consequently, the training-set can be efficiently and reliably distilled. Comprehensive tests on two well-known UAV benchmarks prove the effectiveness of our method with real-time speed on a single CPU.

cs.CV↗
arXiv2019

Monotonicity of functionals along conformal Ricci flow

The main purpose of this note is to construct two functionals of the positive solutions to the conjugate heat equation associated to the metrics evolving by the conformal Ricci flow on closed manifolds. We show that they are nondecreasing by calculating the explicit evolution formulas of these functionals. For the entropy functional we give another proof of the monotonicity by establishing a pointwise formula. Moreover, we show that the increase are strict unless the metrics are Einstein.

math.DG↗
arXiv2019

An End-to-End Neural Network for Image Cropping by Learning Composition from Aesthetic Photos

As one of the fundamental techniques for image editing, image cropping discards unrelevant contents and remains the pleasing portions of the image to enhance the overall composition and achieve better visual/aesthetic perception. In this paper, we primarily focus on improving the accuracy of automatic image cropping, and on further exploring its potential in public datasets with high efficiency. From this respect, we propose a deep learning based framework to learn the objects composition from photos with high aesthetic qualities, where an anchor region is detected through a convolutional neural network (CNN) with the Gaussian kernel to maintain the interested objects' integrity. This initial detected anchor area is then fed into a light weighted regression network to obtain the final cropping result. Unlike the conventional methods that multiple candidates are proposed and evaluated iteratively, only a single anchor region is produced in our model, which is mapped to the final output directly. Thus, low computational resources are required for the proposed approach. The experimental results on the public datasets show that both cropping accuracy and efficiency achieve the state-ofthe-art performances.

cs.CV↗
arXiv2019

Boundary Effect-Aware Visual Tracking for UAV with Online Enhanced Background Learning and Multi-Frame Consensus Verification

Due to implicitly introduced periodic shifting of limited searching area, visual object tracking using correlation filters often has to confront undesired boundary effect. As boundary effect severely degrade the quality of object model, it has made it a challenging task for unmanned aerial vehicles (UAV) to perform robust and accurate object following. Traditional hand-crafted features are also not precise and robust enough to describe the object in the viewing point of UAV. In this work, a novel tracker with online enhanced background learning is specifically proposed to tackle boundary effects. Real background samples are densely extracted to learn as well as update correlation filters. Spatial penalization is introduced to offset the noise introduced by exceedingly more background information so that a more accurate appearance model can be established. Meanwhile, convolutional features are extracted to provide a more comprehensive representation of the object. In order to mitigate changes of objects' appearances, multi-frame technique is applied to learn an ideal response map and verify the generated one in each frame. Exhaustive experiments were conducted on 100 challenging UAV image sequences and the proposed tracker has achieved state-of-the-art performance.

cs.CV↗
arXiv2019

Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking

Traditional framework of discriminative correlation filters (DCF) is often subject to undesired boundary effects. Several approaches to enlarge search regions have been already proposed in the past years to make up for this shortcoming. However, with excessive background information, more background noises are also introduced and the discriminative filter is prone to learn from the ambiance rather than the object. This situation, along with appearance changes of objects caused by full/partial occlusion, illumination variation, and other reasons has made it more likely to have aberrances in the detection process, which could substantially degrade the credibility of its result. Therefore, in this work, a novel approach to repress the aberrances happening during the detection process is proposed, i.e., aberrance repressed correlation filter (ARCF). By enforcing restriction to the rate of alteration in response maps generated in the detection phase, the ARCF tracker can evidently suppress aberrances and is thus more robust and accurate to track objects. Considerable experiments are conducted on different UAV datasets to perform object tracking from an aerial view, i.e., UAV123, UAVDT, and DTB70, with 243 challenging image sequences containing over 90K frames to verify the performance of the ARCF tracker and it has proven itself to have outperformed other 20 state-of-the-art trackers based on DCF and deep-based frameworks with sufficient speed for real-time applications.

cs.CV↗
arXiv2019

Instance-level Sketch-based Retrieval by Deep Triplet Classification Siamese Network

Sketch has been employed as an effective communicative tool to express the abstract and intuitive meanings of object. Recognizing the free-hand sketch drawing is extremely useful in many real-world applications. While content-based sketch recognition has been studied for several decades, the instance-level Sketch-Based Image Retrieval (SBIR) tasks have attracted significant research attention recently. The existing datasets such as QMUL-Chair and QMUL-Shoe, focus on the retrieval tasks of chairs and shoes. However, there are several key limitations in previous instance-level SBIR works. The state-of-the-art works have to heavily rely on the pre-training process, quality of edge maps, multi-cropping testing strategy, and augmenting sketch images. To efficiently solve the instance-level SBIR, we propose a new Deep Triplet Classification Siamese Network (DeepTCNet) which employs DenseNet-169 as the basic feature extractor and is optimized by the triplet loss and classification loss. Critically, our proposed DeepTCNet can break the limitations existed in previous works. The extensive experiments on five benchmark sketch datasets validate the effectiveness of the proposed model. Additionally, to study the tasks of sketch-based hairstyle retrieval, this paper contributes a new instance-level photo-sketch dataset - Hairstyle Photo-Sketch dataset, which is composed of 3600 sketches and photos, and 2400 sketch-photo pairs.

cs.CV↗
arXiv2019

Evolution of relative Yamabe constant under Ricci Flow

Let $W$ be a manifold with boundary $M$ given together with a conformal class $\bar C$ which restricts to a conformal class $C$ on $M$. Then the relative Yamabe constant $Y_{\bar C}(W,M;C)$ is well-defined. We study the short-time behavior of the relative Yamabe constant $Y_{[\bar g_t]}(W,M;C)$ under the Ricci flow $\bar g_t$ on $W$ with boundary conditions that mean curvature $H_{\bar g_t}\equiv 0$ and $\bar{g}_t|_M\in C = [\bar{g}_0]$. In particular, we show that if the initial metric $\bar{g}_0$ is a Yamabe metric, then, under some natural assumptions, $\left.\frac{d}{dt}\right|_{t=0}Y_{[\bar g_t]}(W,M;C)\geq 0$ and is equal to zero if and only the metric $\bar{g}_0$ is Einstein.

math.DG↗
arXiv2018

Ancient solutions for Andrews' hypersurface flow

We construct the ancient solutions of the hypersurface flows in Euclidean spaces studied by B. Andrews in 1994. As time $t \rightarrow 0^-$ the solutions collapse to a round point where $0$ is the singular time. But as $t\rightarrow-\infty$ the solutions become more and more oval. Near the center the appropriately-rescaled pointed Cheeger-Gromov limits are round cylinder solutions $S^J \times \mathbb{R}^{n-J}$, $1 \leq J \leq n-1$. These results are the analog of the corresponding results in Ricci flow ($J=n-1$) and mean curvature flow.

math.DG↗
arXiv2018

Nonlinear disturbance attenuation control of hydraulic robotics

This paper presents a novel nonlinear disturbance rejection control for hydraulic robots. This method requires two third-order filters as well as inverse dynamics in order to estimate the disturbances. All the parameters for the third-order filters are pre-defined. The proposed method is nonlinear, which does not require the linearization of the rigid body dynamics. The estimated disturbances are used by the nonlinear controller in order to achieve disturbance attenuation. The performance of the proposed approach is compared with existing approaches. Finally, the tracking performance and robustness of the proposed approach is validated extensively on real hardware by performing different tasks under either internal or both internal and external disturbances. The experimental results demonstrate the robustness and superior tracking performance of the proposed approach.

cs.RO↗
arXiv2018

PAMPC: Perception-Aware Model Predictive Control for Quadrotors

We present the first perception-aware model predictive control framework for quadrotors that unifies control and planning with respect to action and perception objectives. Our framework leverages numerical optimization to compute trajectories that satisfy the system dynamics and require control inputs within the limits of the platform. Simultaneously, it optimizes perception objectives for robust and reliable sens- ing by maximizing the visibility of a point of interest and minimizing its velocity in the image plane. Considering both perception and action objectives for motion planning and control is challenging due to the possible conflicts arising from their respective requirements. For example, for a quadrotor to track a reference trajectory, it needs to rotate to align its thrust with the direction of the desired acceleration. However, the perception objective might require to minimize such rotation to maximize the visibility of a point of interest. A model-based optimization framework, able to consider both perception and action objectives and couple them through the system dynamics, is therefore necessary. Our perception-aware model predictive control framework works in a receding-horizon fashion by iteratively solving a non-linear optimization problem. It is capable of running in real-time, fully onboard our lightweight, small-scale quadrotor using a low-power ARM computer, to- gether with a visual-inertial odometry pipeline. We validate our approach in experiments demonstrating (I) the contradiction between perception and action objectives, and (II) improved behavior in extremely challenging lighting conditions.

cs.RO↗
arXiv2017

New proofs of Perelman's theorem on shrinking Breathers in Ricci flow

We give two new proofs of Perelman's theorem that shrinking breathers of Ricci flow on closed manifolds are gradient Ricci solitons, using the fact that the singularity models of type I solutions are shrinking gradient Ricci solitons and the fact that non-collapsed type I ancient solutions have rescaled limits being shrinking gradient Ricci solitons.

math.DG↗
arXiv2017

Design and implementation of wire tension measurement system for MWPCs used in the STAR iTPC upgrade

The STAR experiment at RHIC is planning to upgrade the Time Projection Chamber which lies at the heart of the detector. We have designed an instrument to measure the tension of the wires in the multi-wire proportional chambers (MWPCs) which will be used in the TPC upgrade. The wire tension measurement system causes the wires to vibrate and then it measures the fundamental frequency of the oscillation via a laser based optical platform. The platform can scan the entire wire plane, automatically, in a single run and obtain the wire tension on each wire with high precision. In this paper, the details about the measurement method and the system setup will be described. In addition, the test results for a prototype MWPC to be used in the STAR-iTPC upgrade will be presented.

physics.ins-det↗
arXiv2016

Ancient Solutions on Bundles with Non-abelian Structural Group

We generalize the ancient solutions of the Ricci flow on certain principal ${\rm SO}(3)$ bundles over compact quaternionic Kähler manifolds constructed by Bakas, Kong, and Ni to certain $RP^3$ fibre bundles over a product of two compact quaternionic Kähler manifolds. The ancient solutions are of Type I, $κ$-noncollapsed, and have positive Ricci curvature. Analogous solutions on even-dimensional non-Kählerian bundle spaces are also constructed.

math.DG↗
arXiv2016

Framework for state and unknown input estimation of linear time-varying systems

The design of unknown-input decoupled observers and filters requires the assumption of an existence condition in the literature. This paper addresses an unknown input filtering problem where the existence condition is not satisfied. Instead of designing a traditional unknown input decoupled filter, a Double-Model Adaptive Estimation approach is extended to solve the unknown input filtering problem. It is proved that the state and the unknown inputs can be estimated and decoupled using the extended Double-Model Adaptive Estimation approach without satisfying the existence condition. Numerical examples are presented in which the performance of the proposed approach is compared to methods from literature.

eess.SY↗
arXiv2016

Ancient Ricci Flow Solutions on Bundles

We generalize the circle bundle examples of ancient solutions of the Ricci flow discovered by Bakas, Kong, and Ni to a class of principal torus bundles over an arbitrary finite product of Fano Kähler-Einstein manifolds studied by Wang and Ziller in the context of Einstein geometry. As a result, continuous families of $κ$-collapsed and $κ$-noncollapsed ancient solutions of type I are obtained on circle bundles for all odd dimensions $\geq 7$. In dimension $7$ such examples moreover exist on pairs of homeomorphic but not diffeomorphic manifolds. Continuous families of $κ$-collapsed ancient solutions of type I are also obtained on torus bundles for all dimensions $\geq 8$.

math.DG↗