基于改进角度直方图和最小二乘法的移动机器人地图构建

本文主要研究完全未知结构化环境下的移动机器人二维几何地图构建及其不确定性描述问题。在考虑测量噪声干扰的基础上，基于改进的角度直方图算法进行环境线段特征提取和参数初始估计，然后利用加权最小二乘法对线段特征参数及其方差进行精确估计，并同时给出了多位姿地图合并的处理方法.文章最后给出了在SmartROB2机器人平台上进行的实验结果，证明了算法的有效性和实用性。

一种基于多特征融合的汽车变速箱螺栓在线视觉检测系统

本文根据汽车变速箱装配线螺栓检测的要求,结合检测现场的实际图像特点,采用融合灰度投影与颜色直方图两种特征的方法,利用相似性测度的计算方法,设计了一种变速箱螺栓在线装配质量检测系统,该系统用于实现螺栓的的缺失及漏拧检测,试验结果表明,方法具有良好的实用性,取得了比较理想的效果。

龙滩工程左岸边坡监测资料分析与稳定性评价研究

On the basis of the geological analysis and rock mass toppling deformation and failure mechanism analysis of Longtan engineering left bank slope, the synthetic space-time analysis and influence factors analysis on the surface monitoring data and deep rock mass monitoring data of B-zone of left bank slope are carried on. At the same time, based on the monitoring data analysis in conjunction with the predecessor's mechanics analysis results, the deformation state of B-zone of the left bank slope is discussed and its stability is synthetically evaluated. The detailed research contents and results are as following: According to the monitoring drill histogram analysis of Longtan engineering left bank slope, numerical simulation analysis and model experimentation analysis of bedded counter-inclined steep slope, a new type of toppling deformation and failure mode is proposed, that is "up-slope warping". Then the deformation and failure mode of bedded counter-inclined steep slope is summarized as "down-slope toppling" type, "up-slope warping" type and "complex fold" type. On the basis of synthetic space-time analysis to surface monitoring data and deep rock mass deformation monitoring data of B-zone of Longtan left bank slope;, we can get the conclusion that there exists potential instability rock mass over 520m altitude, especially over 560m altitude of slope B, and the rock mass of around strong-weathering line or creep rock mass breaking band controls the deformation of the whole slope. 1. According to the synthetic space-time analysis and influence factors analysis to the surface monitoring data of B-zone of Longtan left bank slope, a dynamical index, accumulative total acceleration index, which is used to analyze the influence factors of slope surface deformation, is raised. The principle and method of accumulative acceleration index are explained, and the index can be used for the influence factors analysis of the similar slope. 2. Summarize the results of geologic analysis, monitoring analysis and mechanics analysis, the following conclusion can be gotten: the stability of B-zone of the slope is basically good. However, on the condition of drainage and slope toe loading engineering, there is still some creep deformation in the rock mass over 520m altitude, especially over 560m altitude. So, better measures of the monitoring and timely maintenance of the drainage system are suggested in the paper.

Skin Color-Based Video Segmentation under Time-Varying Illumination

A novel approach for real-time skin segmentation in video sequences is described. The approach enables reliable skin segmentation despite wide variation in illumination during tracking. An explicit second order Markov model is used to predict evolution of the skin-color (HSV) histogram over time. Histograms are dynamically updated based on feedback from the current segmentation and predictions of the Markov model. The evolution of the skin-color distribution at each frame is parameterized by translation, scaling and rotation in color space. Consequent changes in geometric parameterization of the distribution are propagated by warping and resampling the histogram. The parameters of the discrete-time dynamic Markov model are estimated using Maximum Likelihood Estimation, and also evolve over time. The accuracy of the new dynamic skin color segmentation algorithm is compared to that obtained via a static color model. Segmentation accuracy is evaluated using labeled ground-truth video sequences taken from staged experiments and popular movies. An overall increase in segmentation accuracy of up to 24% is observed in 17 out of 21 test sequences. In all but one case the skin-color classification rates for our system were higher, with background classification rates comparable to those of the static segmentation.

An alignment based similarity measure for hand detection in cluttered sign language video

Locating hands in sign language video is challenging due to a number of factors. Hand appearance varies widely across signers due to anthropometric variations and varying levels of signer proficiency. Video can be captured under varying illumination, camera resolutions, and levels of scene clutter, e.g., high-res video captured in a studio vs. low-res video gathered by a web cam in a user’s home. Moreover, the signers’ clothing varies, e.g., skin-toned clothing vs. contrasting clothing, short-sleeved vs. long-sleeved shirts, etc. In this work, the hand detection problem is addressed in an appearance matching framework. The Histogram of Oriented Gradient (HOG) based matching score function is reformulated to allow non-rigid alignment between pairs of images to account for hand shape variation. The resulting alignment score is used within a Support Vector Machine hand/not-hand classifier for hand detection. The new matching score function yields improved performance (in ROC area and hand detection rate) over the Vocabulary Guided Pyramid Match Kernel (VGPMK) and the traditional, rigid HOG distance on American Sign Language video gestured by expert signers. The proposed match score function is computationally less expensive (for training and testing), has fewer parameters and is less sensitive to parameter settings than VGPMK. The proposed detector works well on test sequences from an inexpert signer in a non-studio setting with cluttered background.

Estimation and Prediction of Evolving Color Distributions for Skin Segmentation Under Varying Illumination

A novel approach for real-time skin segmentation in video sequences is described. The approach enables reliable skin segmentation despite wide variation in illumination during tracking. An explicit second order Markov model is used to predict evolution of the skin color (HSV) histogram over time. Histograms are dynamically updated based on feedback from the current segmentation and based on predictions of the Markov model. The evolution of the skin color distribution at each frame is parameterized by translation, scaling and rotation in color space. Consequent changes in geometric parameterization of the distribution are propagated by warping and re-sampling the histogram. The parameters of the discrete-time dynamic Markov model are estimated using Maximum Likelihood Estimation, and also evolve over time. Quantitative evaluation of the method was conducted on labeled ground-truth video sequences taken from popular movies.

Optimizing the reliability of power electronics module isolation substrates

Optimal design of a power electronics module isolation substrate is assessed using a combination of finite element structural mechanics analysis and response surface optimisation technique. Primary failure modes in power electronics modules include the loss of structural integrity in the ceramic substrate materials due to stresses induced through thermal cycling. Analysis of the influence of ceramic substrate design parameters is undertaken using a design of experiments approach. Finite element analysis is used to determine the stress distribution for each design, and the results are used to construct a quadratic response surface function. A particle swarm optimisation algorithm is then used to determine the optimal substrate design. Analysis of response surface function gradients is used to perform sensitivity analysis and develop isolation substrate design rules. The influence of design uncertainties introduced through manufacturing tolerances is assessed using a Monte-Carlo algorithm, resulting in a stress distribution histogram. The probability of failure caused by the violation of design constraints has been analyzed. Six geometric design parameters are considered in this work and the most important design parameters have been identified. Overall analysis results can be used to enhance the design and reliability of the component.

Whole Slide Image Cytometry: a Novel Method for the Detection and Quantification of Abnormal DNA Contents in Barrett’s Oesophagus

Background: Barrett's oesophagus (BO) is a well recognized precursor of the majority of cases of oesophageal adenocarcinoma (OAC). Endoscopic surveillance of BO patients is frequently undertaken in an attempt to detect early OAC, high grade dysplasia (HGD) or low grade dysplasia (LGD). However histological interpretation and grading of dysplasia is subjective and poorly reproducible. The alternative flow cytometry and cytology-preparation image cytometry techniques require large amounts of tissue and specialist expertise which are not widely available for frontline health care.
Methods: This study has combined whole slide imaging with DNA image cytometry, to provide a novel method for the detection and quantification of abnormal DNA contents. 20 cases were evaluated, including 8 Barrett's specialised intestinal metaplasia (SIM), 6 LGD and 6 HGD. Feulgen stained oesophageal sections (1µm thickness) were digitally scanned in their entirety and evaluated to select regions of interests and abnormalities. Barrett’s mucosa was then interactively chosen for automatic nuclei segmentation where irrelevant cell types are ignored. The combined DNA content histogram for all selected image regions was then obtained. In addition, histogram measurements, including 5c exceeding ratio (xER-5C), 2c deviation index (2cDI) and DNA grade of malignancy (DNA-MG), were computed.
Results: The histogram measurements, xER-5C, 2cDI and DNA-MG, were shown to be effective in differentiating SIM from HGD, SIM from LGD, and LGD from HGD. All three measurements discriminated SIM from HGD cases successfully with statistical significance (pxER-5C=0.0041, p2cDI=0.0151 and pDNA-MG=0.0057). Statistical significance is also achieved differentiating SIM from LGD samples with pxER-5C=0.0019, p2cDI=0.0023 and pDNA-MG=0.0030. Furthermore the differences between LGD and HGD cases are statistical significant (pxER-5C=0.0289, p2cDI=0.0486 and pDNA-MG=0.0384).
Conclusion: Whole slide image cytometry is a novel and effective method for the detection and quantification of abnormal DNA content in BO. Compared to manual histological review, this proposed method is more objective and reproducible. Compared to flow cytometry and cytology-preparation image cytometry, the current method is low cost, simple to use and only requires a single 1µm tissue section. Whole slide image cytometry could assist the routine clinical diagnosis of dysplasia in BO, which is relevant for future progression risk to OAC.

A sparse representation based fast detection method for surface defect detection of bottle caps

A practical machine-vision-based system is developed for fast detection of defects occurring on the surface of bottle caps. This system can be used to extract the circular region as the region of interests (ROI) from the surface of a bottle cap, and then use the circular region projection histogram (CRPH) as the matching features. We establish two dictionaries for the template and possible defect, respectively. Due to the requirements of high-speed production as well as detecting quality, a fast algorithm based on a sparse representation is proposed to speed up the searching. In the sparse representation, non-zero elements in the sparse factors indicate the defect's size and position. Experimental results in industrial trials show that the proposed method outperforms the orientation code method (OCM) and is able to produce promising results for detecting defects on the surface of bottle caps.

Management of Bartholin's gland carcinoma using high-dose-rate interstitial brachytherapy boost

To describe the patterns of use, clinical outcomes, and dose-volume histogram parameters of high-dose-rate interstitial brachytherapy (HDR-ISBT) in the management of Bartholin's gland cancer.

Predictors of Chest Wall Toxicity after Lung Stereotactic Ablative Radiotherapy

AIMS: To determine the incidence and predictive factors of rib fracture and chest wall pain after lung stereotactic ablative radiotherapy (SABR).

MATERIALS AND METHODS: Patients were treated with lung SABR of 48-60 Gy in four to five fractions. The treatment plan and follow-up computed tomography scans of 289 tumours in 239 patients were reviewed. Dose-volume histogram (DVH) metrics and clinical factors were evaluated as potential predictors of chest wall toxicity.

RESULTS: The median follow-up was 21.0 months (range 6.2-52.1). Seventeen per cent (50/289) developed a rib fracture, 44% (22/50) were symptomatic; the median time to fracture was 16.4 months. On univariate analysis, female gender, osteoporosis, tumours adjacent (within 5 mm) to the chest wall and all of the chest wall DVH metrics predicted for rib fracture, but only tumour location adjacent to the chest wall remained significant on the multivariate model (P < 0.01). The 2 year fracture-free probability for those adjacent to the chest wall was 65.6%. Among those tumours adjacent to the chest wall, only osteoporosis (P = 0.02) predicted for fracture, whereas none of the chest wall DVH metrics were predictive. Eight per cent (24/289) experienced chest wall pain without fracture.

CONCLUSIONS: None of the chest wall DVH metrics independently predicted for SABR-induced rib fracture when tumour location is taken into account. Patients with tumours adjacent (within 5 mm) to the chest wall are at greater risk of rib fracture after lung SABR, and among these, an additional risk was observed in osteoporotic patients.

The Impact of Colleague Peer Review on the Radiotherapy Treatment Planning Process in the Radical Treatment of Lung Cancer

AIMS: Modern radiotherapy uses techniques to reliably identify tumour and reduce target volume margins. However, this can potentially lead to an increased risk of geographic miss. One source of error is the accuracy of target volume delineation (TVD). Colleague peer review (CPR) of all curative-intent lung cancer plans has been mandatory in our institution since May 2013. At least two clinical oncologists review plans, checking treatment paradigm, TVD, prescription dose tumour and critical organ tolerances. We report the impact of CPR in our institution.

MATERIALS AND METHODS: Radiotherapy treatment plans of all patients receiving radical radiotherapy were presented at weekly CPR meetings after their target volumes were reviewed and signed off by the treating consultant. All cases and any resultant change to TVD (including organs at risk) or treatment intent were recorded in our prospective CPR database. The impact of CPR over a 13 month period from May 2013 to June 2014 is reported.

RESULTS: One hundred and twenty-two patients (63% non-small cell lung carcinoma, 17% small cell lung carcinoma and 20% 'clinical diagnosis') were analysed. On average, 3.2 cases were discussed per meeting (range 1-8). CPR resulted in a change in treatment paradigm in 3% (one patient proceeded to induction chemotherapy, two patients had high-dose palliative radiotherapy). Twenty-one (17%) had a change in TVD and one (1%) patient had a change in dose prescription. In total, 6% of patients had plan adjustment after review of dose volume histogram.

CONCLUSION: The introduction of CPR in our centre has resulted in a change in a component of the treatment plan for 27% of patients receiving curative-intent lung radiotherapy. We recommend CPR as a mandatory quality assurance step in the planning process of all radical lung plans.

FPGA Soft-core Processors, Compiler and Hardware Optimizations validated using HOG

There is demand for an easily programmable, high performance image processing platform based on FPGAs. In previous work, a novel, high performance processor - IPPro was developed and a Histogram of Orientated Gradients (HOG) algorithm study undertaken on a Xilinx Zynq platform. Here, we identify and explore a number of mapping strategies to improve processing efficiency for soft-cores and a number of options for creation of a division coprocessor. This is demonstrated for the revised high definition HOG implementation on a Zynq platform, resulting in a performance of 328 fps which represents a 146% speed improvement over the original realization and a tenfold reduction in energy.

Monte Carlo studies of phase transitions and adsorption : application to n-6 Lennard-Jones, C60 and zeolite systems

The solid-fluid transition properties of the n - 6 Lennard-Jones system are studied by means of extensive free energy calculations. Different values of the parameter n which regulates the steepness of the short-range repulsive interaction are investigated. Furthermore, the free energies of the n < 12 systems are calculated using the n = 12 system as a reference. The method relies on a generalization of the multiple histogram method that combines independent canonical ensemble simulations performed with different Hamiltonians and computes the free energy difference between them. The phase behavior of the fullerene C60 solid is studied by performing NPT simulations using atomistic models which treat each carbon in the molecule as a separate interaction site with additional bond charges. In particular, the transition from an orientationally frozen phase at low temperatures to one where the molecules are freely rotating at higher temperatures is studied as a function of applied pressure. The adsorption of molecular hydrogen in the zeolite NaA is investigated by means of grand-canonical Monte Carlo, in a wide range of temperatures and imposed gas pressures, and results are compared with available experimental data. A potential model is used that comprises three main interactions: van der Waals, Coulomb and induced polarization by the permanent electric field in the zeolite.

Automatic Video Analysis for Fisheries Survey Systems

Thesis (Ph.D.)--University of Washington, 2015