arXiv subjects

Pei Li

Publications and source records attributed to Pei Li.

64 records · Page 4Linked to original sources

arXiv2021

Enhancing SUMO simulator for simulation based testing and validation of autonomous vehicles

Current autonomous vehicle (AV) simulators are built to provide large-scale testing required to prove capabilities under varied conditions in controlled, repeatable fashion. However, they have certain failings including the need for user expertise and complex inconvenient tutorials for customized scenario creation. Simulation of Urban Mobility (SUMO) simulator, which has been presented as an open-source AV simulator, is used extensively but suffer from similar issues which make it difficult for entry-level practitioners to utilize the simulator without significant time investment. In that regard, we provide two enhancements to SUMO simulator geared towards massively improving user experience and providing real-life like variability for surrounding traffic. Firstly, we calibrate a car-following model, Intelligent Driver Model (IDM), for highway and urban naturalistic driving data and sample automatically from the parameter distributions to create the background vehicles. Secondly, we combine SUMO with OpenAI gym, creating a Python package which can run simulations based on real world highway and urban layouts with generic output observations and input actions that can be processed via any AV pipeline. Our aim through these enhancements is to provide an easy-to-use platform which can be readily used for AV testing and validation.

cs.RO↗

arXiv2021

Measuring Human Perception to Improve Handwritten Document Transcription

The subtleties of human perception, as measured by vision scientists through the use of psychophysics, are important clues to the internal workings of visual recognition. For instance, measured reaction time can indicate whether a visual stimulus is easy for a subject to recognize, or whether it is hard. In this paper, we consider how to incorporate psychophysical measurements of visual perception into the loss function of a deep neural network being trained for a recognition task, under the assumption that such information can enforce consistency with human behavior. As a case study to assess the viability of this approach, we look at the problem of handwritten document transcription. While good progress has been made towards automatically transcribing modern handwriting, significant challenges remain in transcribing historical documents. Here we describe a general enhancement strategy, underpinned by the new loss formulation, which can be applied to the training regime of any deep learning-based document transcription system. Through experimentation, reliable performance improvement is demonstrated for the standard IAM and RIMES datasets for three different network architectures. Further, we go on to show feasibility for our approach on a new dataset of digitized Latin manuscripts, originally produced by scribes in the Cloister of St. Gall in the the 9th century.

cs.CV↗

arXiv2021

A Unified Theory and Fundamental Rules of Strain-dependent Doping Behaviors in Semiconductors

Enhancing the dopability of semiconductors via strain engineering is critical to improving their functionalities, which is, however, largely hindered by the lack of fundamental rules. In this Letter, for the first time, we develop a unified theory to understand the total energy changes of defects (or dopants) with different charge states under strains, which can exhibit either parabolic or superlinear behaviors, determined by the size of defect-induced local volume change (ΔV). In general, ΔV increases (decreases) when an electron is added (removed) to (from) the defect site. Consequently, in terms of this unified theory, three fundamental rules can be obtained to further understand or predict the diverse strain-dependent doping behaviors, i.e., defect formation energies, charge-state transition levels, and Fermi pinning levels, in semiconductors. These three fundamental rules could be generally applied to improve the doping performance or overcome the doping bottlenecks in various semiconductors.

cond-mat.mtrl-sci↗

arXiv2020

Remarkable antibacterial activity of reduced graphene oxide functionalized by copper ions

Despite long-term efforts for exploring antibacterial agents or drugs, it remains challenging how to potentiate antibacterial activity and meanwhile minimize toxicity hazards to the environment. Here, we experimentally show that the functionality of reduced graphene oxide (rGO) through copper ions displays selective antibacterial activity significantly stronger than that of rGO itself and no toxicity to mammalian cells. Remarkably, this antibacterial activity is two orders of magnitude greater than the activity of its surrounding copper ions. We demonstrate that the rGO is functionalized through the cation-$π$ interaction to massively adsorb copper ions to form a rGO-copper composite in solution and result in an extremely low concentration level of surrounding copper ions (less than ~0.5 $μM$). These copper ions on rGO are positively charged and strongly interact with negatively charged bacterial cells to selectively achieve antibacterial activity, while rGO exhibits the functionality to not only actuate rapid delivery of copper ions and massive assembly onto bacterial cells but also result in the valence shift in the copper ions from Cu$^{2+}$ into Cu$^{+}$ which greatly enhances the antibacterial activity. Notably, this functionality of rGO through cation-$π$ interaction with copper ions can similarly achieve algaecidal activity but does not exert cytotoxicity against neutrally charged mammalian cells. The remarkable selective antibacterial activity from the rGO functionality as well as the inherent broad-spectrum-antibacterial physical mechanism represents a significant step toward the development of a novel antibacterial material and reagent without environmental hazards for practical application.

physics.app-ph↗

arXiv2020

ABC of Order Dependencies

We enhance constrained-based data quality with approximate band conditional order dependencies (abcODs). Band ODs model the semantics of attributes that are monotonically related with small variations without there being an intrinsic violation of semantics. The class of abcODs generalizes band ODs to make them more relevant to real-world applications by relaxing them to hold approximately (abODs) with some exceptions and conditionally (bcODs) on subsets of the data. We study the problem of automatic dependency discovery over a hierarchy of abcODs. First, we propose a more efficient algorithm to discover abODs than in recent prior work. The algorithm is based on a new optimization to compute a longest monotonic band (longest subsequence of tuples that satisfy a band OD) through dynamic programming by decreasing the runtime from O(n^2) to O(n \log n) time. We then illustrate that while the discovery of bcODs is relatively straightforward, there exist codependencies between approximation and conditioning that make the problem of abcOD discovery challenging. The naive solution is prohibitively expensive as it considers all possible segmentations of tuples resulting in exponential time complexity. To reduce the search space, we devise a dynamic programming algorithm for abcOD discovery that determines the optimal solution in O(n^3 \log n) complexity. To further optimize the performance, we adapt the algorithm to cheaply identify consecutive tuples that are guaranteed to belong to the same band--this improves the performance significantly in practice without losing optimality. While unidirectional abcODs are most common in practice, for generality we extend our algorithms with both ascending and descending orders to discover bidirectional abcODs. Finally, we perform a thorough experimental evaluation of our techniques over real-world and synthetic datasets.

cs.DB↗

arXiv2019

Face Recognition in Low Quality Images: A Survey

Low-resolution face recognition (LRFR) has received increasing attention over the past few years. Its applications lie widely in the real-world environment when high-resolution or high-quality images are hard to capture. One of the biggest demands for LRFR technologies is video surveillance. As the the number of surveillance cameras in the city increases, the videos that captured will need to be processed automatically. However, those videos or images are usually captured with large standoffs, arbitrary illumination condition, and diverse angles of view. Faces in these images are generally small in size. Several studies addressed this problem employed techniques like super resolution, deblurring, or learning a relationship between different resolution domains. In this paper, we provide a comprehensive review of approaches to low-resolution face recognition in the past five years. First, a general problem definition is given. Later, systematically analysis of the works on this topic is presented by catogory. In addition to describing the methods, we also focus on datasets and experiment settings. We further address the related works on unconstrained low-resolution face recognition and compare them with the result that use synthetic low-resolution data. Finally, we summarized the general limitations and speculate a priorities for the future effort.

cs.CV↗

arXiv2019

On Low-Resolution Face Recognition in the Wild: Comparisons and New Techniques

Although face recognition systems have achieved impressive performance in recent years, the low-resolution face recognition (LRFR) task remains challenging, especially when the LR faces are captured under non-ideal conditions, as is common in surveillance-based applications. Faces captured in such conditions are often contaminated by blur, nonuniform lighting, and nonfrontal face pose. In this paper, we analyze face recognition techniques using data captured under low-quality conditions in the wild. We provide a comprehensive analysis of experimental results for two of the most important applications in real surveillance applications, and demonstrate practical approaches to handle both cases that show promising performance. The following three contributions are made: {\em (i)} we conduct experiments to evaluate super-resolution methods for low-resolution face recognition; {\em (ii)} we study face re-identification on various public face datasets including real surveillance and low-resolution subsets of large-scale datasets, present a baseline result for several deep learning based approaches, and improve them by introducing a GAN pre-training approach and fully convolutional architecture; and {\em (iii)} we explore low-resolution face identification by employing a state-of-the-art supervised discriminative learning approach. Evaluations are conducted on challenging portions of the SCFace and UCCSface datasets.

cs.CV↗

arXiv2018

An Anti-fraud System for Car Insurance Claim Based on Visual Evidence

Automatically scene understanding using machine learning algorithms has been widely applied to different industries to reduce the cost of manual labor. Nowadays, insurance companies launch express vehicle insurance claim and settlement by allowing customers uploading pictures taken by mobile devices. This kind of insurance claim is treated as small claim and can be processed either manually or automatically in a quick fashion. However, due to the increasing amount of claims every day, system or people are likely to be fooled by repeated claims for identical case leading to big lost to insurance companies.Thus, an anti-fraud checking before processing the claim is necessary. We create the first data set of car damage images collected from internet and local parking lots. In addition, we proposed an approach to generate robust deep features by locating the damages accurately and efficiently in the images. The state-of-the-art real-time object detector YOLO \cite{redmon2016you}is modified to train and discover damage region as an important part of the pipeline. Both local and global deep features are extracted using VGG model\cite{Simonyan14c}, which are fused later for more robust system performance. Experiments show our approach is effective in preventing fraud claims as well as meet the requirement to speed up the insurance claim prepossessing.

cs.CV↗

arXiv2015

Study of grain boundary transparency in (Yb1-xCax)Ba2Cu3O bi-crystal thin films over a wide temperature, field and field orientation range

The residual low angle grain boundary (GB) network is still the most important current-limiting mechanism operating in bi-axially textured rare earth barium copper oxide (REBCO) coated conductors. While Ca-doping is well established to improve super-current flow across low angle GBs in weak fields at high temperatures, Ca-doping also depresses Tc, making it so far impractical for high temperature applications of REBCO coated conductors. On the other hand, high field magnet applications of REBCO require low temperatures. Here we systematically evaluate the effectiveness of Ca-doping in improving the GB transparency, r$^{GB}$= Jc$^{GB}$/Jc$^{grain}$ , of low angle Yb1-xCaxBaCuO [001] tilt bi-crystal films down to 10K and with magnetic fields perpendicular and parallel to the film surfaces, while varying the Ca and oxygen doping level. Using Low Temperature Scanning Laser Microscopy (LTSLM) and Magneto-Optical Imaging (MOI), we found rGB to strongly depend on the angle between magnetic field and the GB plane and clearly identified regimes in which Jc$^{GB}$ can exceed Jc$^{grain}$ (r$^{GB}$>1) where the GB pinning is optimized by the field being parallel to the GB dislocations. However, even in this favorable situation, we found that r$^{GB}$ became much smaller at lower temperatures. Calculations of the GB Ca segregation profile predict that the high Jc channels between the GB dislocation cores are almost Ca-free. It may be therefore that the positive effects of Ca doping seen by many authors near Tc are partly a consequence of the higher Tc of these Ca-free channels.

cond-mat.supr-con↗

arXiv2015

Robust Group Linkage

We study the problem of group linkage: linking records that refer to entities in the same group. Applications for group linkage include finding businesses in the same chain, finding conference attendees from the same affiliation, finding players from the same team, etc. Group linkage faces challenges not present for traditional record linkage. First, although different members in the same group can share some similar global values of an attribute, they represent different entities so can also have distinct local values for the same or different attributes, requiring a high tolerance for value diversity. Second, groups can be huge (with tens of thousands of records), requiring high scalability even after using good blocking strategies. We present a two-stage algorithm: the first stage identifies cores containing records that are very likely to belong to the same group, while being robust to possible erroneous values; the second stage collects strong evidence from the cores and leverages it for merging more records into the same group, while being tolerant to differences in local values of an attribute. Experimental results show the high effectiveness and efficiency of our algorithm on various real-world data sets.

cs.DB↗