Grayscale Variation Research Articles

Plasma C-peptide mammographic features and risk of breast cancer

Our study in the Nurses’ Health Study (NHS) and NHS2, a nested case-control study with 1260 cases and 2221 controls, investigated the association between C-peptide levels, mammographic density (MD) parameters, V (a measure of gray scale variation), and breast cancer (BC) risk. We also examined how C-peptide and BC risk vary across quartiles of mammographic features. Linear and logistic regressions were used to study the associations between C-peptide and MD parameters, and breast cancer. C-peptide was inversely associated with percent MD and positively with non-dense area, but no associations were found with dense area and V measure. C-peptide was associated with an increased risk of invasive BC risk (top vs. bottom quartile, odds ratio = 1.46, 95% CI: 1.12–1.91). No multiplicative interactions were found between C-peptide, MD parameters, and BC risk. Our results suggest a positive association between C-peptide and BC risk, and MD parameters do not seem to modify this association.

Automatic Diagnosis of Hepatocellular Carcinoma and Metastases Based on Computed Tomography Images.

Liver cancer, a leading cause of cancer mortality, is often diagnosed by analyzing the grayscale variations in liver tissue across different computed tomography (CT) images. However, the intensity similarity can be strong, making it difficult for radiologists to visually identify hepatocellular carcinoma (HCC) and metastases. It is crucial for the management and prevention strategies to accurately differentiate between these two liver cancers. This study proposes an automated system using a convolutional neural network (CNN) to enhance diagnostic accuracy to detect HCC, metastasis, and healthy liver tissue. This system incorporates automatic segmentation and classification. The liver lesions segmentation model is implemented using residual attention U-Net. A 9-layer CNN classifier implements the lesions classification model. Its input is the combination of the results of the segmentation model with original images. The dataset included 300 patients, with 223 used to develop the segmentation model and 77 to test it. These 77 patients also served as inputs for the classification model, consisting of 20 HCC cases, 27 with metastasis, and 30 healthy. The system achieved a mean Dice score of in segmentation and a mean accuracy of in classification, both in the test phase. The proposed method is a preliminary study with great potential in helping radiologists diagnose liver cancers.

Association between Inflammatory Dietary Pattern and Mammographic Features

BackgroundThe empirical dietary inflammation pattern score (EDIP), which measures the ability of the diet to regulate chronic inflammation, is associated with both higher adiposity and breast cancer (BC) risk. Mammographic density (MD) is an important risk factor for BC. ObjectiveWe examined the associations between EDIP and mammographic features overall and stratified by menopausal status, and assessed the extent to which these associations are mediated by adiposity. MethodsWe included 4145 participants without BC in the Nurses’ Health Study (NHS) and NHSII. Cumulative average EDIP was assessed by food frequency questionnaires every 4–6 y. We assessed MD parameters (percent MD, dense area, and nondense area) and V (measure of grayscale variation). MD parameters were square-root transformed. Multivariable-adjusted linear regression models were used to analyze the associations between EDIP score and MD parameters. Baron and Kenny’s regression method was used to assess the extent to which the associations of EDIP and mammographic traits were mediated by BMI. ResultsIn multivariable-adjusted models, EDIP was significantly inversely associated with percent MD [top compared with bottom quartile, β = –0.57; 95% confidence interval (CI): –0.78, –0.36]. Additional adjustment for BMI attenuated the association (β = –0.15; 95% CI: –0.34, 0.03), with 68% (β = 0.68, 20; 95% CI: 0.54, 0.86) mediation via BMI. In addition, EDIP was positively associated with nondense area after adjusting for BMI and other covariates. No associations were observed for dense area and V measure. Results were similar when stratified by menopausal status. ConclusionsEDIP score was inversely associated with percent MD and positively associated with nondense area, and these associations were largely mediated by BMI.

Fusing Ground-Penetrating Radar Images for Improving Image Characteristics Fidelity

The analysis of ground-penetrating radar (GPR) data is of vital importance for detecting various subsurface features that might manifest as hyperbolic peaks, which are indicators of a buried object or grayscale variation in the case of contrast in the soil texture. This method focuses on identifying exaggerated patterns through a series of image-processing steps. Two GPR images are initially read and preprocessed by extracting channels, flipping, and resizing. Then, specific regions of interest (ROIs) are cropped, and the Fourier transform is further applied to turn them into the frequency domain. With the help of their frequency signatures, these patterns are extracted from the images, and binary masks are constructed to obtain features of interest. These masked images were reconstructed and merged to make hyperbolic features visible. Finally, Local Binary Pattern (LBP) analysis is used to emphasize these hyperbolic peaks, thereby facilitating their recognition across the whole image. The proposed approach improves the detection of performance subsurface features in GPR data; hence, it is an important tool for geophysical surveys and other related applications. The results prove the high performance of the proposed procedure in improving GPR image characteristics.

Experimental and numerical studies on the partial cavitation in a Venturi

Abstract To effectively control the adverse effects of cavitation, it is crucial to understand the mechanism behind the formation of cloud cavitation. The transition from sheet to cloud cavitation, or cavitation shedding, can be caused by two mechanisms: re-entrant jet and condensation shock. This study investigated the shedding mechanism of partial cavitation in a Venturi using high-speed photography and Large-Eddy Simulation. The Rankine-Hugoniot equation was used to verify that the cavitation shedding mechanism: the condensation shock at σ = 0.37 and the re-entrant jet mechanism at σ = 0.98. Both operating conditions exhibit backflow, which can cause variations in image grayscale values. The relation between backflowing velocity and grayscale variation was identified in different shedding mechanisms. When the adverse pressure gradient is constant, the shock velocity is inversely proportional to the image grayscale variation, while the re-entrant jet velocity is proportional to it. These findings may contribute to a better understanding of cavitation shedding mechanism.

Detection method of micro and macro scale defects in silicon carbide castings

Aiming at challenges such as low efficiency, high missing rate, difficulty in identifying contour defects, and difficulty in extracting tiny defects, a defect detection method for extracting micro and macro scale defects is proposed in this paper. After preprocessing the image, contour detection is performed to identify the contours. Subsequently, a contour complementation algorithm is employed to complement the unclosed contours. Finally, the detection of micro scale defects is conducted based on the grayscale variation of the center of the micro scale defects. The experimental results show that compared with the traditional method, the proposed algorithm can accurately detect the bubble defects of different scales in silicon carbide castings and can identify the complex defects better.

PmcaNet: Pyramid multiscale channel attention network for electron microscopy image segmentation

Recent advances in high-throughput electron microscopy (EM) have revolutionized the examination of microstructures by enabling fast EM image generation. However, accurately segmenting EM images remains challenging due to inherent characteristics, including low contrast and subtle grayscale variations. Moreover, as manually annotated EM images are limited, it is usually impractical to utilize deep learning techniques for EM image segmentation. To address these challenges, the pyramid multiscale channel attention network (PmcaNet) is specifically designed. PmcaNet employs a convolutional neural network-based architecture and a multiscale feature pyramid to effectively capture global context information, enhancing its ability to comprehend the intricate structures within EM images. To enable the rapid extraction of channel-wise dependencies, a novel attention module is introduced to enhance the representation of intricate nonlinear features within the images. The performance of PmcaNet is evaluated on two general EM image segmentation datasets as well as a homemade dataset of superalloy materials, regarding pixel-wise accuracy and mean intersection over union (mIoU) as evaluation metrics. Extensive experiments demonstrate that PmcaNet outperforms other models on the ISBI 2012 dataset, achieving 87.85% pixel-wise accuracy and 73.11% mean intersection over union (mIoU), while also advancing results on the Kathuri and SEM-material datasets.

Fusion recognition of palmprint and palm vein based on modal correlation.

Biometric authentication prevents losses from identity misuse in the artificial intelligence (AI) era. The fusion method integrates palmprint and palm vein features, leveraging their stability and security and enhances counterfeiting prevention and overall system efficiency through multimodal correlations. However, most of the existing multi-modal palmprint and palm vein feature extraction methods extract only feature information independently from different modalities, ignoring the importance of the correlation between different modal samples in the class to the improvement of recognition performance. In this study, we addressed the aforementioned issues by proposing a feature-level joint learning fusion approach for palmprint and palm vein recognition based on modal correlations. The method employs a sparse unsupervised projection algorithm with a "purification matrix" constraint to enhance consistency in intra-modal features. This minimizes data reconstruction errors, eliminating noise and extracting compact, and discriminative representations. Subsequently, the partial least squares algorithm extracts high grayscale variance and category correlation subspaces from each modality. A weighted sum is then utilized to dynamically optimize the contribution of each modality for effective classification recognition. Experimental evaluations conducted for five multimodal databases, composed of six unimodal databases including the Chinese Academy of Sciences multispectral palmprint and palm vein databases, yielded equal error rates (EER) of 0.0173%, 0.0192%, 0.0059%, 0.0010%, and 0.0008%. Compared to some classical methods for palmprint and palm vein fusion recognition, the algorithm significantly improves recognition performance. The algorithm is suitable for identity recognition in scenarios with high security requirements and holds practical value.

Infrared Small Dim Target Detection Using Group Regularized Principle Component Pursuit

The detection of an infrared small target faces the problems of background interference and non-obvious target features, which have yet to be efficiently solved. By employing the non-local self-correlation characteristic of the infrared images, the principle component pursuit (PCP)-based methods are demonstrated to be applicable to infrared small target detection in a complex scene. However, existing PCP-based methods heavily depend on the uniform distribution of the background pixels and are prone to generating a high number of false alarms under strong clutter situations. In this paper, we propose a group low-rank regularized principle component pursuit model (GPCP) to solve this problem. First, the local image patches are clustered into several groups that correspond to different grayscale distributions. These patch groups are regularized with a group low-rank constraint, enabling an independent recovery of different background regions. Then, GPCP model integrates the group low-rank components with a global sparse component to extract small targets from the background. Different singular value thresholds can be exploited for image groups corresponding to different brightness and grayscale variance, boosting the recovery of background clutters and also enhancing the detection of small targets. Finally, a customized optimization approach based on alternating direction method of multipliers is proposed to solve this model. We set three representative detection scenes, including the ground background, sea background and sky background for experiment analysis and model comparison. The evaluation results show the proposed model has superiority in background suppression and achieves better adaptability for different scenes compared with various state-of-the-art methods.

Individual Fish Recognition Method with Coarse and Fine-Grained Feature Linkage Learning for Precision Aquaculture

With the increasing level of precision and intelligence in the aquaculture, real-time mastery of the growth status of aquaculture individuals has become an important means to improve aquaculture efficiency and save resources and the environment. Therefore, accurate individual recognition of underwater fish has become one of the key technologies for precision aquaculture. In order to cope with the impact of the complex underwater environment on the recognition accuracy, this paper proposes a coarse and fine-grained features learning method for individual fish recognition. The method consists of a coarse-grained feature learning network and two fine-grained feature learning networks. The trunk of the network is responsible for learning coarse-grained features of the fish, the first branch learns fine-grained features of fish from head, body, and tail, and the second branch learns fine-grained features of fish from upper and lower fins. we supplemented different levels of noise and attack to the training set of fine-grained features and enriched the grayscale variation to cope with the complexity and variability of the underwater environment. The simulation experimental results show that the method achieves more than 96.7% in key indicators such as Rank-1 and Rank-5, and also performs well in other fish recognition tasks with certain generalization.

COVID-19 diagnosis with Deep Learning: Adjacent-pooling CTScan-COVID-19 Classifier Based on ResNet and CBAM

The accurate and rapid diagnosis of COVID-19 has been a critical challenge worldwide. Several approaches have been proposed to address this issue, including clinical tests, imaging techniques like chest X-rays and CT scans, and the widely used RT-PCR test. Recently, deep convolutional neural networks (CNNs) have been shown to be effective in detecting COVID-19 in CT scan images. In this study, we investigated the efficacy of ResNet, a state-of-the-art deep CNN, along with attention mechanisms to detect COVID-19 in CT scan images. Furthermore, we introduced a novel CNN, named AdjCNet, which focuses on the grayscale variations among adjacent areas within the image. Our combination of ResNet, Convolutional Block Attention Module (CBAM), and AdjCNet achieved an outstanding classification accuracy of 99.23% for CT images in identifying COVID-19, Normal, or Community Acquired Pneumonia (CAP). Specifically, our proposed method achieved a precision of 100% for identifying CAP images and a precision exceeding 99% for the other two classes. In addition, we performed a four-folds cross-validation to evaluate the performance of our proposed model for COVID-19 detection using CT-scan images. The results of the four-folds cross-validation demonstrated that our proposed model achieved a mean accuracy and precision of 98.98% and 99.01%, respectively, over the four folds. The final results clearly demonstrate the superiority of our proposed method over the state-of-the-art methods on this dataset. Our findings suggest that our proposed method could serve as an effective and efficient tool for COVID-19 diagnosis, and further studies can explore its application in clinical settings.

A Paper-Based Fluorescent Sensor for Rapid Early Screening of Oral Squamous Cell Carcinoma

Various types of sensors play an irreplaceable role in the detection of biomarkers, but their high cost and complicated operation make it difficult to benefit ordinary people. Herein, we develop a low-cost, double-layered, paper-based fluorescent sensor (CP/HQ) structurally consisting of the upper reaction layer loaded with two oxidases (lactate oxidase and choline oxidase) and the bottom fluorescent layer that physically associates with the porphine-grafted composite fluorescent polymer colloids (PF-PDMTP/HQ). Based on the dramatic and rapid fluorescence decrease of porphine induced by the oxidation between saliva and oxidases and subsequent fluorescence resonance energy transfer from oxidized hydroquinone, the resultant fluorescent paper sensor enables us to achieve visual detection of OSCC, which was further recognized by smartphone scanning as the grayscale variation. It was found that the linear sensing range of grayscale value are 10-200 μM for lactic acid and 10-100 μM for choline, with LODs of 5.7 and 8.9 μM, respectively. More importantly, the sensor can achieve a powerful detection capability comparable to that of high-performance liquid chromatography (HPLC) in clinical settings with simple operation, demonstrating its great application potential. Our proposed sensor not only improves the accuracy of OSCC diagnosis but also provides a valuable attempt for the device modification of polymer-sensing systems and the development of non-invasive and easy-to-operate disease screening methods.

Prediction of Hole Expansion Ratio for Advanced High-Strength Steel with Image Feature Analysis of Sheared Edge

The punching process of AHSS induces edge cracks in successive process, limiting the application of AHSS for vehicle bodies. Controlling and predicting edge quality is substantially difficult due to the large variation in edge quality, die wear induced by high strength, and the complex effect of phase distribution. To overcome this challenge, a quality prediction model that considers the variation of the entire edge should be developed. In this study, the image of the entire edge was analyzed to provide a comprehensive evaluation of its quality. Statistical features were extracted from the edge images to represent the edge quality of DP780, DP980, and MART1500 steels. Combined with punching monitoring signals, a prediction model for hole expansion ratio was developed under punch conditions of varying clearance, punch angle, and punch edge radius. It was found that the features of grayscale variation are affected by the punching conditions and are related to the double burnish and uneven burr, which degrades the edge quality. Prediction of HER was possible based on only edge image and monitoring signals, with the same performance as the prediction based solely on punching parameters and material properties. The prediction performance improved when using all the features.

An Automatic Counting Algorithm for Topographic Maps Based on Videos for Map Management

Topographic maps comprise a rich data source for the processing and analysis of geographic information. However, the management of paper topographic maps is still dominated by an inefficient manual method, and there is no counting equipment for topographic maps that is suitable for narrow map warehouse passages. The existing algorithms relating to paper counting require paper hardness and cannot directly obtain the internal information of topographic maps. To address the above problems, using a map inventory machine transformed from a paddle-type paper counting machine to perform a preliminary count and obtain the video data of the counting progress, an automatic counting algorithm for topographic maps for map management is proposed in this study. First, the periodic feature changes of all the targets and each individual target in the videos are analyzed. Second, a deformable parts model accelerated by fast feature pyramids and by reducing the region of interest is used for the object detection of mechanical wheels. The grayscale variance function is selected to quantify the quality change in the images. Finally, a fusion window counting model is constructed with the adaptive window and fixed window methods. The experimental results show that the average counting accuracy of the model is about 95%, which can verify the initial counting results of the machine and provide high-quality keyframes for the subsequent sheet designation recognition.

High sensitivity tracking of free-moving targets in time-varying complex backgrounds

Tracking of low-visibility targets in complex backgrounds is an important research field, where existing methods struggle to image low-visibility targets with irregular changes in moving direction and speed. Move contrast imaging can greatly improve the sensitivity of target tracking, which has achieved important applications in the field of X-ray imaging, including high-resolution imaging to microvessels in living rats with the help of contrast agents, <i>in-situ</i> dynamic observation of ion migration and redox reactions during electrochemical reactions, and water refilling along vessels in willow branch without resorting to agents. However, all these applications are limited to imaging with fixed trajectories or monotonous backgrounds. In principle, move contrast imaging is based on the frequency spectral characteristics of the time-domain grayscale signal and is highly sensitive to moving components, which is wavelength-independent. This paper extends the move contrast imaging to the visible light waveband for tracking free-moving targets in time-varying complex backgrounds. To meet the need for tracking imaging of free-moving targets in complex backgrounds, we develop a move contrast imaging (MCI) method based on continuous wavelet transform (CWT) and Hilbert-Huang transform (HHT) with high discriminatory capability for non-stationary signals. Selecting birds in the sky and forest for the tracking imaging, the irregular grayscale changes caused by natural light intensity in the wild field and random swaying of tree leaves result in complex imaging backgrounds. The tracing results of low-visibility free-moving targets show that FT-MCI method, CWT-MCI method and HHT-MCI method can improve the target tracing imaging sensitivity by 179.9 times, 175.8 times and 214.6 times compared with temporal subtraction imaging, respectively. The results of tracking imaging of free-moving targets in complex backgrounds show that compared with the FT-MCI method and CWT-MCI method, the HHT-MCI method can further effectively suppress the influence of background noise on tracking imaging of targets of interest, thus achieving high sensitivity imaging of free-moving targets in time-varying complex backgrounds. Combining the phase diagram of FT-MCI and the imaging parameters, we can further show the motion direction, the motion speed or the distance from the observation point. Therefore, the HHT-MCI imaging method developed in this paper is expected to provide a novel method for tracking free-moving targets in time-varying complex backgrounds.

OMIRD: Orientated Modality Independent Region Descriptor for Optical-to-SAR Image Matching

Image matching between optical and SAR images remains challenging due to their different imaging principles. Despite recent developments in image matching methods for optical-to-SAR images, few have seen practical application success due to the significant geometric and radiometric differences between the two modalities. In this letter, we propose a new method called the Orientated Modality Independent Region Descriptor (OMIRD) to overcome these challenges. Our template-based approach effectively extracts consistent structural and textural features from both optical and SAR images. Additionally, we introduce a principal orientation selection method, using the Ratio of Exponentially Weighted Averages (ROEWA) and logarithm Histogram of Gradient (HOG) to identify the most meaningful feature orientations and further simplify the OMIRD descriptor. The experimental results indicate that the proposed OMIRD exhibits superior matching accuracy and robustness under various geometric distortions and non-linear grayscale variations.

A genome-wide association study of mammographic texture variation

BackgroundBreast parenchymal texture features, including grayscale variation (V), capture the patterns of texture variation on a mammogram and are associated with breast cancer risk, independent of mammographic density (MD). However, our knowledge on the genetic basis of these texture features is limited.MethodsWe conducted a genome-wide association study of V in 7040 European-ancestry women. V assessments were generated from digitized film mammograms. We used linear regression to test the single-nucleotide polymorphism (SNP)-phenotype associations adjusting for age, body mass index (BMI), MD phenotypes, and the top four genetic principal components. We further calculated genetic correlations and performed SNP-set tests of V with MD, breast cancer risk, and other breast cancer risk factors.ResultsWe identified three genome-wide significant loci associated with V: rs138141444 (6q24.1) in ECT2L, rs79670367 (8q24.22) in LINC01591, and rs113174754 (12q22) near PGAM1P5. 6q24.1 and 8q24.22 have not previously been associated with MD phenotypes or breast cancer risk, while 12q22 is a known locus for both MD and breast cancer risk. Among known MD and breast cancer risk SNPs, we identified four variants that were associated with V at the Bonferroni-corrected thresholds accounting for the number of SNPs tested: rs335189 (5q23.2) in PRDM6, rs13256025 (8p21.2) in EBF2, rs11836164 (12p12.1) near SSPN, and rs17817449 (16q12.2) in FTO. We observed significant genetic correlations between V and mammographic dense area (rg = 0.79, P = 5.91 × 10−5), percent density (rg = 0.73, P = 1.00 × 10−4), and adult BMI (rg = − 0.36, P = 3.88 × 10−7). Additional significant relationships were observed for non-dense area (z = − 4.14, P = 3.42 × 10−5), estrogen receptor-positive breast cancer (z = 3.41, P = 6.41 × 10−4), and childhood body fatness (z = − 4.91, P = 9.05 × 10−7) from the SNP-set tests.ConclusionsThese findings provide new insights into the genetic basis of mammographic texture variation and their associations with MD, breast cancer risk, and other breast cancer risk factors.

Detection and analysis of phage M13KO7 using biosensor based on imaging ellipsometry

Antibody GP8 (anti-GP8) was used as a ligand to detect phage M13KO7 using a biosensor based on imaging ellipsometry (IE) without oriented ligand immobilization. When the phage M13KO7 in a sample interacted with the antibody in a microarray, a complex formed upon their affinity, and the layer covering the surface cell of the interaction became thicker. The variation in layer thickness was represented by gray-scale (or brightness) variation of the IE image. Direct and oriented immobilization of the antibody were analyzed to identify the best binding locations to capture the phage. In direct immobilization, the phage could be captured by anti-GP8 and not antibody GP3 (anti-GP3), which was attributed to different copy numbers of the coat proteins on the body of the phage specific to the two antibodies. This indicated that different binding locations could produce different detection efficiency. In oriented immobilization, the phage could be captured by the protein G‒Fc-anti-GP3 model, with a low detection efficiency. In contrast, the avidin‒biotin-based oriented immobilization could capture the phage with a high detection efficiency. Specifically, it could expose more Fab domains of anti-GP3 labeled with biotin; one avidin had four biotin-binding sites. To confirm detection and analyze binding location, the phage M13KO7 was imaged by transmission electron microscopy and atomic force microscopy. Our results suggest that binding location plays a significant role in the detection of big targets and contributes to enhancing biosensor detection sensitivity.

Road Network Extraction from SAR Images with the Support of Angular Texture Signature and POIs

Urban road network information is an important part of modern spatial information infrastructure and is crucial for high-precision navigation map production and unmanned driving. Synthetic aperture radar (SAR) is a widely used remote-sensing data source, but the complex structure of road networks and the noises in images make it very difficult to extract road information through SAR images. We developed a new method of extracting road network information from SAR images by considering angular (A) and texture (T) features in the sliding windows and points of interest (POIs, or P), and we named this method ATP-ROAD. ATP-ROAD is a sliding window-based semi-automatic approach that uses the grayscale mean, grayscale variance, and binary segmentation information of SAR images as texture features in each sliding window. Since POIs have much-duplicated information, this study also eliminates duplicated POIs considering distance and then selects a combination of POI linkages by discerning the direction of these POIs to initially determine the road direction. The ATP-ROAD method was applied to three experimental areas in Shanghai to extract the road network using China’s Gaofen-3 imagery. The experimental results show that the extracted road network information is relatively complete and matches the actual road conditions, and the result accuracy is high in the three different regions, i.e., 89.57% for Area-I, 96.88% for Area-II, and 92.65% for Area-III. Our method together with our extraction software can be applied to extract information about road networks from SAR images, providing an alternative for enriching the variety of road information.

Adaptive ORB feature detection with a variable extraction radius in RoI for complex illumination scenes

Feature detection is a crucial technique for a vision navigation system to estimate robot pose according to natural landmarks. It is difficult for the existing feature detection techniques to balance the feature quality, processing time and robustness for a vision-based robot in complex workspaces. An adaptive Oriented fast and Rotated Brief (ORB) feature detection method with a variable extraction radius in Region of Interest (RoI) is proposed to deal with these problems. Firstly, the original camera image is processed by means of the Laplace transform of Gaussian (LTOG) pyramid and the grayscale centroid method, in order to obtain the rotation and scale invariance for ORB features. Then, a RoI segmenting technique is developed to locate the image areas that contain potential ORB features due to obvious grayscale variation. Thirdly, the ORB features are extracted in RoIs by using a set of variable-radius templates, adaptive to different illumination conditions. Finally, a number of feature detection and robot localization experiments are conducted on a vision-based robot prototype in different scenes under complex illumination. The experimental results verify that the RoI segmenting technique can correctly preserve the grayscale-varying regions to search ORB features with scattered distribution but excluding the irrelevant areas to suppress feature noises, while the variable-radius template extraction method can detect more feature inliers in complex workspaces. Therefore, our adaptive ORB method can outperform other commonly-used algorithms in accuracy, efficiency and robustness.