arXiv subjects

Yuan Yuan

Publications and source records attributed to Yuan Yuan.

At least 271 records · Page 15Linked to original sources

arXiv2019

VSSA-NET: Vertical Spatial Sequence Attention Network for Traffic Sign Detection

Although traffic sign detection has been studied for years and great progress has been made with the rise of deep learning technique, there are still many problems remaining to be addressed. For complicated real-world traffic scenes, there are two main challenges. Firstly, traffic signs are usually small size objects, which makes it more difficult to detect than large ones; Secondly, it is hard to distinguish false targets which resemble real traffic signs in complex street scenes without context information. To handle these problems, we propose a novel end-to-end deep learning method for traffic sign detection in complex environments. Our contributions are as follows: 1) We propose a multi-resolution feature fusion network architecture which exploits densely connected deconvolution layers with skip connections, and can learn more effective features for the small size object; 2) We frame the traffic sign detection as a spatial sequence classification and regression task, and propose a vertical spatial sequence attention (VSSA) module to gain more context information for better detection performance. To comprehensively evaluate the proposed method, we do experiments on several traffic sign datasets as well as the general object detection dataset and the results have shown the effectiveness of our proposed method.

cs.CV↗

arXiv2019

A Joint Convolutional Neural Networks and Context Transfer for Street Scenes Labeling

Street scene understanding is an essential task for autonomous driving. One important step towards this direction is scene labeling, which annotates each pixel in the images with a correct class label. Although many approaches have been developed, there are still some weak points. Firstly, many methods are based on the hand-crafted features whose image representation ability is limited. Secondly, they can not label foreground objects accurately due to the dataset bias. Thirdly, in the refinement stage, the traditional Markov Random Filed (MRF) inference is prone to over smoothness. For improving the above problems, this paper proposes a joint method of priori convolutional neural networks at superpixel level (called as ``priori s-CNNs'') and soft restricted context transfer. Our contributions are threefold: (1) A priori s-CNNs model that learns priori location information at superpixel level is proposed to describe various objects discriminatingly; (2) A hierarchical data augmentation method is presented to alleviate dataset bias in the priori s-CNNs training stage, which improves foreground objects labeling significantly; (3) A soft restricted MRF energy function is defined to improve the priori s-CNNs model's labeling performance and reduce the over smoothness at the same time. The proposed approach is verified on CamVid dataset (11 classes) and SIFT Flow Street dataset (16 classes) and achieves competitive performance.

cs.CV↗

arXiv2019

Embedding Structured Contour and Location Prior in Siamesed Fully Convolutional Networks for Road Detection

Road detection from the perspective of moving vehicles is a challenging issue in autonomous driving. Recently, many deep learning methods spring up for this task because they can extract high-level local features to find road regions from raw RGB data, such as Convolutional Neural Networks (CNN) and Fully Convolutional Networks (FCN). However, how to detect the boundary of road accurately is still an intractable problem. In this paper, we propose a siamesed fully convolutional networks (named as ``s-FCN-loc''), which is able to consider RGB-channel images, semantic contours and location priors simultaneously to segment road region elaborately. To be specific, the s-FCN-loc has two streams to process the original RGB images and contour maps respectively. At the same time, the location prior is directly appended to the siamesed FCN to promote the final detection performance. Our contributions are threefold: (1) An s-FCN-loc is proposed that learns more discriminative features of road boundaries than the original FCN to detect more accurate road regions; (2) Location prior is viewed as a type of feature map and directly appended to the final feature map in s-FCN-loc to promote the detection performance effectively, which is easier than other traditional methods, namely different priors for different inputs (image patches); (3) The convergent speed of training s-FCN-loc model is 30\% faster than the original FCN, because of the guidance of highly structured contours. The proposed approach is evaluated on KITTI Road Detection Benchmark and One-Class Road Detection Dataset, and achieves a competitive result with state of the arts.

cs.CV↗

arXiv2019

Memory-Augmented Temporal Dynamic Learning for Action Recognition

Human actions captured in video sequences contain two crucial factors for action recognition, i.e., visual appearance and motion dynamics. To model these two aspects, Convolutional and Recurrent Neural Networks (CNNs and RNNs) are adopted in most existing successful methods for recognizing actions. However, CNN based methods are limited in modeling long-term motion dynamics. RNNs are able to learn temporal motion dynamics but lack effective ways to tackle unsteady dynamics in long-duration motion. In this work, we propose a memory-augmented temporal dynamic learning network, which learns to write the most evident information into an external memory module and ignore irrelevant ones. In particular, we present a differential memory controller to make a discrete decision on whether the external memory module should be updated with current feature. The discrete memory controller takes in the memory history, context embedding and current feature as inputs and controls information flow into the external memory module. Additionally, we train this discrete memory controller using straight-through estimator. We evaluate this end-to-end system on benchmark datasets (UCF101 and HMDB51) of human action recognition. The experimental results show consistent improvements on both datasets over prior works and our baselines.

cs.CV↗

arXiv2019

Early Action Prediction with Generative Adversarial Networks

Action Prediction is aimed to determine what action is occurring in a video as early as possible, which is crucial to many online applications, such as predicting a traffic accident before it happens and detecting malicious actions in the monitoring system. In this work, we address this problem by developing an end-to-end architecture that improves the discriminability of features of partially observed videos by assimilating them to features from complete videos. For this purpose, the generative adversarial network is introduced for tackling action prediction problem, which improves the recognition accuracy of partially observed videos though narrowing the feature difference of partially observed videos from complete ones. Specifically, its generator comprises of two networks: a CNN for feature extraction and an LSTM for estimating residual error between features of the partially observed videos and complete ones, and then the features from CNN adds the residual error from LSTM, which is regarded as the enhanced feature to fool a competing discriminator. Meanwhile, the generator is trained with an additional perceptual objective, which forces the enhanced features of partially observed videos are discriminative enough for action prediction. Extensive experimental results on UCF101, BIT and UT-Interaction datasets demonstrate that our approach outperforms the state-of-the-art methods, especially for videos that less than 50% portion of frames is observed.

cs.CV↗

arXiv2019

Cross-Modal Message Passing for Two-stream Fusion

Processing and fusing information among multi-modal is a very useful technique for achieving high performance in many computer vision problems. In order to tackle multi-modal information more effectively, we introduce a novel framework for multi-modal fusion: Cross-modal Message Passing (CMMP). Specifically, we propose a cross-modal message passing mechanism to fuse two-stream network for action recognition, which composes of an appearance modal network (RGB image) and a motion modal (optical flow image) network. The objectives of individual networks in this framework are two-fold: a standard classification objective and a competing objective. The classification object ensures that each modal network predicts the true action category while the competing objective encourages each modal network to outperform the other one. We quantitatively show that the proposed CMMP fuses the traditional two-stream network more effectively, and outperforms all existing two-stream fusion method on UCF-101 and HMDB-51 datasets.

cs.CV↗

arXiv2019

Anomaly Detection in Traffic Scenes via Spatial-aware Motion Reconstruction

Anomaly detection from a driver's perspective when driving is important to autonomous vehicles. As a part of Advanced Driver Assistance Systems (ADAS), it can remind the driver about dangers timely. Compared with traditional studied scenes such as the university campus and market surveillance videos, it is difficult to detect abnormal event from a driver's perspective due to camera waggle, abidingly moving background, drastic change of vehicle velocity, etc. To tackle these specific problems, this paper proposes a spatial localization constrained sparse coding approach for anomaly detection in traffic scenes, which firstly measures the abnormality of motion orientation and magnitude respectively and then fuses these two aspects to obtain a robust detection result. The main contributions are threefold: 1) This work describes the motion orientation and magnitude of the object respectively in a new way, which is demonstrated to be better than the traditional motion descriptors. 2) The spatial localization of object is taken into account of the sparse reconstruction framework, which utilizes the scene's structural information and outperforms the conventional sparse coding methods. 3) Results of motion orientation and magnitude are adaptively weighted and fused by a Bayesian model, which makes the proposed method more robust and handle more kinds of abnormal events. The efficiency and effectiveness of the proposed method are validated by testing on nine difficult video sequences captured by ourselves. Observed from the experimental results, the proposed method is more effective and efficient than the popular competitors, and yields a higher performance.

cs.CV↗

arXiv2019

Ultra-high-speed color imaging with single-pixel detectors under low light level

Single-pixel imaging is suitable for low light level scenarios because a bucket detector is employed to maximally collect the light from an object. However, one of the challenges is its slow imaging speed, mainly due to the slow light modulation technique. We here demonstrate 1.4MHz video imaging based on computational ghost imaging with a RGB LED array having a full-range frame rate up to 100MHz. With this method, the motion of a high speed propeller is observed. Moreover, by exploiting single-photon detectors to increase the detection efficiency, this method is developed for ultra-high-speed imaging under low light level.

physics.ins-det↗

arXiv2019

Forward Vehicle Collision Warning Based on Quick Camera Calibration

Forward Vehicle Collision Warning (FCW) is one of the most important functions for autonomous vehicles. In this procedure, vehicle detection and distance measurement are core components, requiring accurate localization and estimation. In this paper, we propose a simple but efficient forward vehicle collision warning framework by aggregating monocular distance measurement and precise vehicle detection. In order to obtain forward vehicle distance, a quick camera calibration method which only needs three physical points to calibrate related camera parameters is utilized. As for the forward vehicle detection, a multi-scale detection algorithm that regards the result of calibration as distance priori is proposed to improve the precision. Intensive experiments are conducted in our established real scene dataset and the results have demonstrated the effectiveness of the proposed framework.

cs.CV↗

arXiv2019

Tracking as A Whole: Multi-Target Tracking by Modeling Group Behavior with Sequential Detection

Video-based vehicle detection and tracking is one of the most important components for Intelligent Transportation Systems (ITS). When it comes to road junctions, the problem becomes even more difficult due to the occlusions and complex interactions among vehicles. In order to get a precise detection and tracking result, in this work we propose a novel tracking-by-detection framework. In the detection stage, we present a sequential detection model to deal with serious occlusions. In the tracking stage, we model group behavior to treat complex interactions with overlaps and ambiguities. The main contributions of this paper are twofold: 1) Shape prior is exploited in the sequential detection model to tackle occlusions in crowded scene. 2) Traffic force is defined in the traffic scene to model group behavior, and it can assist to handle complex interactions among vehicles. We evaluate the proposed approach on real surveillance videos at road junctions and the performance has demonstrated the effectiveness of our method.

cs.CV↗

arXiv2019

Naked-Eye Ghost Imaging via Photoelectric-Feedback

Based on optical correlations, ghost imaging is usually reconstructed by computer algorithm from the acquired data. We here proposed an alternatively high contrast naked-eye ghost imaging scheme which avoids computer algorithm processing. Instead, the proposed scheme uses a photoelectric feedback loop to realize the multiplication process of traditional ghost imaging. Meanwhile, it exploits the vision persistence effect to implement integral process and to generate negative images observed by naked eyes. To realize high contrast naked-eye ghost imaging, a special pattern-scanning architecture on a low-speed light-modulation mask is designed, which enables high-resolution imaging with lower-order Hadamard vectors and boosts the imaging speed as well. Moreover, two kinds of feedback circuits, the digital circuit and the analog circuit, are presented respectively, which can achieve high-speed feedback operation on the light intensity. With this approach, we demonstrate high-contrast real-time imaging for moving objects.

eess.IV↗

arXiv2019

All-optical naked-eye ghost imaging

Ghost imaging is usually based on optoelectronic process and eletronic computing. We here propose a new ghost imaging scheme, which avoids any optoelectronic or electronic process. Instead, the proposed scheme exploits all-optical correlation via the light-light interaction and the vision persistence effect to generate images observed by naked eyes. To realize high contrast naked-eye ghost imaging, a special pattern-scanning architecture on a low-speed light-modulation disk is designed, which also enables high-resolution imaging with lower-order Hadamard vectors and boosts the imaging speed. With this approach, we realize high-contrast real-time ghost imaging for moving colored objects.

eess.IV↗

arXiv2019

$L^p$ regularity of the Bergman Projection on domains covered by the polydisk

If a bounded domain can be covered by the polydisk through a rational proper holomorphic map, then the Bergman projection is $L^p$-bounded for $p$ in a certain range depending on the ramified rational covering. This result can be applied to the symmetrized polydisk and to the Hartogs triangle with exponent $γ$.

math.CV↗

arXiv2019

Learning from Synthetic Data for Crowd Counting in the Wild

Recently, counting the number of people for crowd scenes is a hot topic because of its widespread applications (e.g. video surveillance, public security). It is a difficult task in the wild: changeable environment, large-range number of people cause the current methods can not work well. In addition, due to the scarce data, many methods suffer from over-fitting to a different extent. To remedy the above two problems, firstly, we develop a data collector and labeler, which can generate the synthetic crowd scenes and simultaneously annotate them without any manpower. Based on it, we build a large-scale, diverse synthetic dataset. Secondly, we propose two schemes that exploit the synthetic data to boost the performance of crowd counting in the wild: 1) pretrain a crowd counter on the synthetic data, then finetune it using the real data, which significantly prompts the model's performance on real data; 2) propose a crowd counting method via domain adaptation, which can free humans from heavy data annotations. Extensive experiments show that the first method achieves the state-of-the-art performance on four real datasets, and the second outperforms our baselines. The dataset and source code are available at https://gjy3035.github.io/GCC-CL/.

cs.CV↗

arXiv2019

Experimentally reducing the quantum measurement back-action in work distributions by a collective measurement

In quantum thermodynamics, the standard approach to estimate work fluctuations in unitary processes is based on two projective measurements, one performed at the beginning of the process and one at the end. The first measurement destroys any initial coherence in the energy basis, thus preventing later interference effects. In order to decrease this back-action, a scheme based on collective measurements has been proposed in~[PRL 118, 070601 (2017)]. Here, we report its experimental implementation in an optical system. The experiment consists of a deterministic collective measurement on identically prepared two qubits, encoded in the polarisation and path degree of a single photon. The standard two projective measurement approach is also experimentally realized for comparison. Our results show the potential of collective schemes to decrease the back-action of projective measurements, and capture subtle effects arising from quantum coherence.

quant-ph↗

arXiv2019

ASIED: A Bayesian Adaptive Subgroup-Identification Enrichment Design

Developing targeted therapies based on patients' baseline characteristics and genomic profiles such as biomarkers has gained growing interests in recent years. Depending on patients' clinical characteristics, the expression of specific biomarkers or their combinations, different patient subgroups could respond differently to the same treatment. An ideal design, especially at the proof of concept stage, should search for such subgroups and make dynamic adaptation as the trial goes on. When no prior knowledge is available on whether the treatment works on the all-comer population or only works on the subgroup defined by one biomarker or several biomarkers, it is necessary to incorporate the adaptive estimation of the heterogeneous treatment effect to the decision-making at interim analyses. To address this problem, we propose an Adaptive Subgroup-Identification Enrichment Design, ASIED, to simultaneously search for predictive biomarkers, identify the subgroups with differential treatment effects, and modify study entry criteria at interim analyses when justified. More importantly, we construct robust quantitative decision-making rules for population enrichment when the interim outcomes are heterogeneous in the context of a multilevel target product profile, which defines the minimal and targeted levels of treatment effect. Through extensive simulations, the ASIED is demonstrated to achieve desirable operating characteristics and compare favorably against alternatives.

stat.AP↗

arXiv2019

Experimental investigation of majorization uncertainty relations in the high-dimensional systems

Uncertainty relation is not only of fundamental importance to quantum mechanics, but also crucial to the quantum information technology. Recently, majorization formulation of uncertainty relations (MURs) have been widely studied, ranging from two measurements to multiple measurements. Here, for the first time, we experimentally investigate MURs for two measurements and multiple measurements in the high-dimensional systems, and study the intrinsic distinction between direct-product MURs and direct-sum MURs. The experimental results reveal that by taking different nonnegative Schur-concave functions as uncertainty measure, the two types of MURs have their own particular advantages, and also verify that there exists certain case where three-measurement majorization uncertainty relation is much stronger than the one obtained by summing pairwise two-measurement uncertainty relations. Our work not only fills the gap of experimental studies of majorization uncertainty relations, but also represents an advance in quantitatively understanding and experimental verification of majorization uncertainty relations which are universal and capture the essence of uncertainty in quantum theory.

quant-ph↗

arXiv2018

On the self-similar solution to full compressible Navier-Stokes equations without heat conductivity

In this work, we establish a class of globally defined, large solutions to the free boundary problem of compressible Navier-Stokes equations with constant shear viscosity and vanishing bulk viscosity. We establish such solutions with initial data perturbed arbound any self-similar solution when γ> 7/6. In the case when 7/6 < γ< 7/3, as long as the self-similar solution has bounded entropy, a solution with bounded entropy can be constructed. It should be pointed out that the solutions we obtain in this fashion do not in general keep being a small perturbation of the self-similar solution due to the second law of thermodynamics, i.e., the growth of entropy. If in addition, in the case when 11/9 < γ< 5/3, we can construct a solution as a global-in-time small perturbation of the self-similar solution and the entropy is uniformly bounded in time.

math.AP↗