Transfer learning for vehicle detection using two cameras with different focal lengths

Quang Dinh, Vinh,Munir, Farzeen,Azam, Shoaib,Yow, Kin-Choong,Jeon, Moongu Elsevier science 2020 Information sciences Vol.514 No.-

<P><B>Abstract</B></P> <P>This paper proposes a vehicle detection method using transfer learning for two cameras with different focal lengths. A detected vehicle region in an image of one camera is transformed into a binary map. After that, the map is used to filter convolutional neural network (CNN) feature maps which are computed for the other camera’s image. We also introduce a robust evolutionary algorithm that is used to compute the relationship between the two cameras in an off-line mode efficiently. We capture video sequences and sample them to make a dataset that includes images with different focal lengths for vehicle detection. We compare the proposed vehicle detection method with baseline detection methods, including faster region proposal networks (Faster-RCNN), single-shot-multi-Box detector (SSD), and detector using recurrent rolling convolution (RRC), in the same experimental context. The experimental results show that the proposed method can detect vehicles at a wide range of distances accurately and robustly, and significantly outperforms the baseline detection methods.</P> <P><B>Highlights</B></P> <P> <UL> <LI> A transfer learning based vehicle detection method is proposed for two cameras with different focal lengths and effectively solves tiny object size problems. </LI> <LI> REAL is introduced to compute relationship between two cameras effectively. </LI> <LI> Vehicle datasets using cameras with different focal lengths were captured and labeled to evaluate vehicle detection methods. Experimental results show the proposed vehicle detection method significantly outperforms baseline methods. </LI> </UL> </P>

Local Stereo Matching Using an VariableWindow, Census Transform and an Edge-preserving Filter

Vinh Quang Dinh,Dung Duc Nguyen,Vinh Dinh Nguyen,Jae Wook Jeon 제어로봇시스템학회 2012 제어로봇시스템학회 국제학술대회 논문집 Vol.2012 No.10

In this paper, we propose an alternative blocking-matching approach to the correspondence problem in stereo matching. In blocking-matching algorithms, a local window is used to measure the similarity (or dissimilarity) between pixels of a stereo pair. Although some area-based stereo matching methods have been developed and work well in many kinds of regions such as textureless or object boundary regions, their performance can degrade when working in some types of radiometric conditions. Our proposed algorithm is an improved method that uses a non-parametric transform in the pre-processing step and an edge-preserving filter in the post-processing step. Input images are first pre-processed by the census transform, which makes the proposed method more robust when the image pair is captured in different light sources or camera exposure conditions. The window cost in our approach is computed from the transformed images using the Hamming distance, and the correspondence is finally chosen by a Winner-Takes-All strategy. The experimental results for the Middleburry images show that the proposed method outperforms test local stereo methods in radiometrically different images.

Fuzzy Encoding Pattern for Stereo Matching Cost

Dinh, Vinh Quang,Nguyen, Vinh Dinh,Van Nguyen, Hau,Jeon, Jae Wook IEEE 2016 IEEE Transactions on Circuits and Systems for Vide Vol.26 No.7

<P>We propose a novel fuzzy encoding pattern that fuzzily encodes the relative orders between pixel pairs. An image window is divided into disjoint neighboring pixel sets for the window's center pixel, and the relative order is established not only between the center pixel and its neighbors but also between the pixel pairs in each neighboring pixel set. The relative orders are fuzzily encoded to extract more detailed information from a local structure. We successfully apply the pattern as a matching cost function for stereo correspondence under severe radiometric variations. We conduct experiments using the proposed matching cost function and compare it with functions employing the census transform, supporting local binary pattern, and adaptive normalized cross correlation, as well as a mutual information-based matching cost function, using different stereo data sets. Compared with the census transform, the proposed function reduces the error from 33.1% to 16.9% in the Middlebury data set and from 17.6% to 9.5% in the Kitti data set. The experimental results indicate that the proposed function is superior to the state-of-the-art functions under radiometric variations. In addition, the proposed function is faster than recently developed functions, such as the adaptive normalized cross correlation, a mutual information-based function, and support local binary pattern.</P>

Matching cost function using robust soft rank transformations

Dinh, Vinh Quang,Pham, Cuong Cao,Jeon, Jae Wook IET 2016 IET image processing Vol.10 No.7

<P>Stereo correspondence is a challenging task because stereo images are affected by many factors such as radiometric distortion, sun and rain flares, flying snow, occlusions and object boundaries. However, most of the existing stereo correspondence methods use simple matching cost functions. As a result, their performance is degraded significantly when operating with real-world stereo images whose intensities of corresponding pixels can be arbitrarily transformed. In this study, the authors propose a novel matching cost function based on the order relations between pixel pairs that can operate accurately under various conditions of transformed intensities between stereo images. The proposed matching cost function is an improvement of the soft rank transform (SRT) and can tolerate local, monotonically non-linear changes in intensities between the left and right images. The proposed function significantly reduces the error rate from 24.7 to 12.7% in the Middlebury dataset, and from 19.8 to 7.1% in the KITTI dataset as compared with the SRT. The qualitative and quantitative experimental results obtained using stereo images in different datasets under various conditions show that the proposed matching cost function outperforms the state-of-the-art matching cost functions in indoor and outdoor stereo images.</P>

Robust Adaptive Normalized Cross-Correlation for Stereo Matching Cost Computation

Dinh, Vinh Quang,Pham, Cuong Cao,Jeon, Jae Wook Institute of Electrical and Electronics Engineers 2017 IEEE transactions on circuits and systems for vide Vol.27 No.7

<P>Stereo matching is a challenging task because stereo images are affected by many factors, such as radiometric distortion, sun and rain flare, flying snow, occlusion, textureless and noisy image regions, and object boundaries. However, most of the existing methods for stereo matching aim to solve only one specific problem. As a result, their performance is degraded significantly when operating with stereo images captured under a variety of scenes and conditions. In this paper, we propose a novel matching cost function based on adaptive normalized cross-correlation (ANCC). We demonstrate several weaknesses of ANCC and propose techniques to resolve them. In addition, we employ available information, such as intensity mean, intensity variance, and support window radius, to estimate the parameters of the proposed matching cost function. Compared with ANCC, the proposed matching cost function reduces the error rates from 24.1% to 17.8% in the Middlebury data set and from 64.1% to 26.4% in the KITTI data set. In addition, for noisy stereo pairs, the proposed function reduces the error rate from 73.6% to 37.3%. The qualitative and quantitative experimental results based on stereo images in different data sets under various conditions show that our proposed matching cost function outperforms state-of-the-art matching cost functions in indoor and outdoor stereo images having various radiometric distortions.</P>

Local Tetra Pattern and Its Benefits to Improve the Performance of Car and Pedestrian Detection Under Hostile Conditions

Anh Linh Dang,Tuyen Quang Nguyen,Tri Thien Cao,Vinh Quang Dinh,Vinh Dinh Nguyen 제어로봇시스템학회 2021 제어로봇시스템학회 국제학술대회 논문집 Vol.2021 No.10

Traffic detection is a topic of great interest in recent years due to a high demand for better traffic detection systems. Existing traffic detection algorithms work well under ideal driving conditions, however their performance decreases under difficult conditions such as insufficient lighting and illumination. Recently, local patterns have been successfully applied in order to handle complex texture conditions, such as stereo matching, and texture classification. We propose a method that applies Local Tetra Pattern for data preprocessing, so as to improve the performance of deep learning models under said conditions. Our approach achieved better performance than the original raw-models while the changes in inference time are maintained within a negligible interval. By fusing local patterns and raw images, the model gains an acquisition of discriminative information in regions that are highly similar. In challenging conditions, these kinds of information are essential for the model to recover its consciousness of concerned objects which cause many re-cognitional obstructions. Experimental results show a percentage as high as 35.847%, an increase of 12.575% in comparison with the original result on the SKKU data set.

Cyclotron Resonance Linewidth in GaAs/AlAs Quantum Wires

Huynh Vinh Phuc,Le Dinh Quang,Tran Cong Phong 한국물리학회 2012 THE JOURNAL OF THE KOREAN PHYSICAL SOCIETY Vol.60 No.9

In this paper, we study cyclotron-resonance linewidths in an electron-phonon system with the presence of a z-directional triangular potential and a y-directional parabolic potential. A general analytical expression for the absorption power is obtained in the presence of an external static magnetic field applied to the sample along the z-axis. The dependence of the absorption power on the photon energy is numerically calculated and graphically plotted for a specific GaAs/AlAs quantum wire. From graphs of the absorption power, we identified the locations of the cyclotron resonance peaks and obtained the cyclotron resonance linewidth (CRLW) as profiles of the curves. The temperature and the magnetic field dependences of the CRLW have been investigated. The CRLW is shown to increase with increasing temperature and magnetic field. In this paper, we study cyclotron-resonance linewidths in an electron-phonon system with the presence of a z-directional triangular potential and a y-directional parabolic potential. A general analytical expression for the absorption power is obtained in the presence of an external static magnetic field applied to the sample along the z-axis. The dependence of the absorption power on the photon energy is numerically calculated and graphically plotted for a specific GaAs/AlAs quantum wire. From graphs of the absorption power, we identified the locations of the cyclotron resonance peaks and obtained the cyclotron resonance linewidth (CRLW) as profiles of the curves. The temperature and the magnetic field dependences of the CRLW have been investigated. The CRLW is shown to increase with increasing temperature and magnetic field.

Metabolic Syndrome and Insulin Resistance Syndrome among Infertile Women with Polycystic Ovary Syndrome: A Cross-Sectional Study from Central Vietnam

Minh Tam Le,Vu Quoc Huy Nguyen,Quang Vinh Truong,Dinh Duong Le,Viet Nguyen Sa Le,Ngoc Thanh Cao 대한내분비학회 2018 Endocrinology and metabolism Vol.33 No.4

Background: Polycystic ovarian syndrome (PCOS) is one of the most common endocrinopathies among reproductive-age women. Its metabolic features often overlap with those associated with metabolic syndrome (MS) and insulin resistance syndrome (IRS). Theobjective of this study was to determine the prevalence and predictors of MS and IRS in infertile Vietnamese women with PCOS. Methods: A cross-sectional study was conducted at a tertiary fertility centre at Hue University Hospital from June 2016 to November 2017. A total of 441 infertile women diagnosed with PCOS based on the revised 2003 Rotterdam consensus criteria were enrolled. MS and IRS were defined based on the National Heart, Lung, and Blood Institute/American Heart Association Adult Treatment Panel III 2005 and American College of Endocrinology IRS 2003 criteria, respectively. Complete clinical and biochemicalmeasurements of 318 women were available for analysis. Independent predictors of MS and IRS were identified using multivariatelogistic regression. Results: The overall prevalence of MS and IRS in women with PCOS was 10.4% and 27.0%, respectively. We identified older age(>30 years) and obesity as independent predictors of MS and IRS. Elevated anti-Müllerian hormone levels increased the risk of IRS,but not that of MS. Conclusion: MS and IRS are prevalent disorders among infertile Vietnamese women with PCOS. PCOS is not solely a reproductiveproblem. Screening and early intervention for MS and/or IRS based on anthropometric, metabolic, and reproductive hormone riskfactors should be an integral part of fertility care.

Vietnamese Health Care Providers' Preferences Regarding Recommendation of HPV Vaccines

Asiedu, Gladys B,Breitkopf, Carmen Radecki,Kremers, Walter K,Ngo, Quang V,Nguyen, Nguyen V,Barenberg, Benjamin J,Tran, Vinh D,Dinh, Tri A Asian Pacific Journal of Cancer Prevention 2015 Asian Pacific journal of cancer prevention Vol.16 No.12

Physician recommendation is an important predictor of HPV vaccine acceptance; however, physician willingness and preferences regarding HPV vaccination may be influenced by factors including patient age, vaccine type, and cost. A cross-sectional survey was administered to a convenience sample of health care providers in Da Nang, Vietnam, to evaluate awareness, perceptions about HPV and HPV vaccines, and willingness to vaccinate a female patient. Willingness to vaccinate was evaluated using a full-factorial presentation of scenarios featuring the following factors: vaccine cost (free vs 1,000,000 VND), patient age (12, 16, or 22 years), and HPV vaccine type (bivalent vs quadrivalent). Responses from 244 providers were analyzed; providers had a mean age of $34{\pm}11.9$ years; a majority were female, married, and had children of their own. Thirty-six percent specialized in obstetrics/gynecology and 24% were providers in family medicine. Of the three factors considered in conjoint analysis, vaccine cost was the most important factor in willingness to vaccinate, followed by patient age, and vaccine type. The most favorable scenario for vaccinating a female patient was when the vaccine was free, the patient was 22 years of age, and the HPV4 vaccine was described. In multivariable analysis, older age, being a physician, being married, and having children were all associated with increased willingness to recommend HPV vaccination (p<0.05). Provider willingness is an important aspect of successful HPV vaccination programs; identifying preferences and biases in recommendation patterns will highlight potential areas for education and intervention.