A Practical Study of Intelligent Image-Based Mobile Robot for Tracking Colored Objects

Object tracking is one of the major tasks for mobile robots in many real-world applications.Also,artificial intelligence and automatic control techniques play an important role in enhancing the performance of mobile robot navigation.In contrast to previous simulation studies,this paper presents a new intelligent mobile robot for accomplishing multi-tasks by tracking red-green-blue(RGB)colored objects in a real experimental field.Moreover,a practical smart controller is developed based on adaptive fuzzy logic and custom proportional-integral-derivative(PID)schemes to achieve accurate tracking results,considering robot command delay and tolerance errors.The design of developed controllers implies some motion rules to mimic the knowledge of experienced operators.Twelve scenarios of three colored object combinations have been successfully tested and evaluated by using the developed controlled image-based robot tracker.Classical PID control failed to handle some tracking scenarios in this study.The proposed adaptive fuzzy PID control achieved the best accurate results with the minimum average final error of 13.8 cm to reach the colored targets,while our designed custom PID control is efficient in saving both average time and traveling distance of 6.6 s and 14.3 cm,respectively.These promising results demonstrate the feasibility of applying our developed image-based robotic system in a colored object-tracking environment to reduce human workloads.

Structural control of magnetic nanoparticles for positive nuclear magnetic resonance imaging

In addition to the tens of millions of medical doses consumed annually around the world,a vast number of nuclear magnetic resonance imaging(MRI)contrast agents are being deployed in MRI research and development,offering precise diagnostic information,targeting capabilities,and analyte sensing.Superparamagnetic iron oxide nanoparticles(SPIONs)are notable among these agents,providing effective and versatile MRI applications while also being heavy-metal-free,bioconjugatable,and theranostic.We designed and implemented a novel two-pronged computational and experimental strategy to meet the demand for the efficient and rigorous development of SPION-based MRI agents.Our MATLAB-based modeling simulation and magnetic characterization revealed that extremely small maghemite SPIONs in the 1-3 nm range possess significantly reduced transversal relaxation rates(R_(2))and are therefore preferred for positive(T_(1)-weighted)MRI.Moreover,X-ray diffraction and X-ray absorption fine structure analyses demonstrated that the diffraction pattern and radial distribution function of our SPIONs matched those of the targeted maghemite crystals.In addition,simulations of the X-ray near-edge structure spectra indicated that our synthesized SPIONs,even at 1 nm,maintained a spherical structure.Furthermore,in vitro and in vivo MRI investigations showed that our 1-nm SPIONs effectively highlighted whole-body blood vessels and major organs in mice and could be cleared through the kidney route to minimize potential post-imaging side effects.Overall,our innovative approach enabled a swift discovery of the desired SPION structure,followed by targeted synthesis,synchrotron radiation spectroscopic studies,and MRI evaluations.The efficient and rigorous development of our high-performance SPIONs can set the stage for a computational and experimental platform for the development of future MRI agents.

Line Patterns Segmentation in Blurred Images Using Contrast Enhancement and Local Entropy Thresholding

Finger vein extraction and recognition hold significance in various applications due to the unique and reliable nature of finger vein patterns. While recently finger vein recognition has gained popularity, there are still challenges associated with extracting and processing finger vein patterns related to image quality, positioning and alignment, skin conditions, security concerns and processing techniques applied. In this paper, a method for robust segmentation of line patterns in strongly blurred images is presented and evaluated in vessel network extraction from infrared images of human fingers. In a four-step process: local normalization of brightness, image enhancement, segmentation and cleaning were involved. A novel image enhancement method was used to re-establish the line patterns from the brightness sum of the independent close-form solutions of the adopted optimization criterion derived in small windows. In the proposed method, the computational resources were reduced significantly compared to the solution derived when the whole image was processed. In the enhanced image, where the concave structures have been sufficiently emphasized, accurate detection of line patterns was obtained by local entropy thresholding. Typical segmentation errors appearing in the binary image were removed using morphological dilation with a line structuring element and morphological filtering with a majority filter to eliminate isolated blobs. The proposed method performs accurate detection of the vessel network in human finger infrared images, as the experimental results show, applied both in real and artificial images and can readily be applied in many image enhancement and segmentation applications.

Realizing precision pulse TIG welding with arc length control and visual image sensing based weld detection

Methods of arc length control and visual image based weld detection for precision pulse TIG welding were investigated. With a particular all hardware circuit, arc voltage during peak current stage is sampled and integrated to indicate arc length, deviation of arc length and adjusting parameters are calculated and output to drive a step motor directly. According to the features of welding image grabbed with CCD camera, a special algorithm was developed to detect the central line of weld fast and accurately. Then an application system were established, whose static arc length error is ±0.1 mm with 20 A average current and 1 mm given arc length, static detection precision of weld is 0.01 mm , processing time of each image is less than 120 ms . Precision pulse TIG welding of some given thin stainless steel components with complicated curved surface was successfully realized.

Flotation Control System Based on Recognition of Froth Image

In industrial flotation, froth layer plays an important role and reflects directly whether coal, air, water and reagents match each other properly or not and whether the quality of flotation is good or not. So the supervision and recognition of the state of froth layer is very important in the flotation process. The ash content of clean coal froth was predicted through extracting the features of images of flotation froth. The froth images were classified according to their structure. A control system of adding flotation reagents was established based on the LVQ neural net.

Microcomputer Controlled High Precision Image Scanning Systems for Railway Tunnel Width Measurement

There should be high resolution demand that is better than 1000 DPI(dot per inch) for high precision image scanning system. This paper introduced the two-level computer controlled system that consisted of LS-3500 film scanner, AST386/33 monitoring control level and Intel 8031 single chip computer that is used as DDC level. The formula for scanning image data processing and methods of statistic parameters calculating are described.

Data Hiding Method with Quality Control for Binary Images

Secret data hiding in binary images is more difficult than other formats since binary images require only one bit repre-sentation to indicate black and white. This study proposes a new method for data hiding in binary images using opti-mized bit position to replace a secret bit. This method manipulates blocks, which are sub-divided. The parity bit for a specified block decides whether to change or not, to embed a secret bit. By finding the best position to insert a secret bit for each divided block, the image quality of the resulting stego-image can be improved, while maintaining low computational complexity. The experimental results show that the proposed method has an improvement with respect to a previous work.

AUTOMATIC SEARCHING OF CONTROL POINT IN NOAA AVHRR IMAGE

This paper discusses the approaches for automatical searching of control points in the NOAA AVHRR image on the basis of data rearrangement in the form of latitude and longitude grid. The vegetation index transformation and multi-level matching strategies have been proven effective and successful as the experiments show while the control point database is established.

A Post-Processing Algorithm for Boosting Contrast of MRI Images

Low contrast of Magnetic Resonance(MR)images limits the visibility of subtle structures and adversely affects the outcome of both subjective and automated diagnosis.State-of-the-art contrast boosting techniques intolerably alter inherent features of MR images.Drastic changes in brightness features,induced by post-processing are not appreciated in medical imaging as the grey level values have certain diagnostic meanings.To overcome these issues this paper proposes an algorithm that enhance the contrast of MR images while preserving the underlying features as well.This method termed as Power-law and Logarithmic Modification-based Histogram Equalization(PLMHE)partitions the histogram of the image into two sub histograms after a power-law transformation and a log compression.After a modification intended for improving the dispersion of the sub-histograms and subsequent normalization,cumulative histograms are computed.Enhanced grey level values are computed from the resultant cumulative histograms.The performance of the PLMHE algorithm is comparedwith traditional histogram equalization based algorithms and it has been observed from the results that PLMHE can boost the image contrast without causing dynamic range compression,a significant change in mean brightness,and contrast-overshoot.

Feeding Control System of Conveyor-belt Based on Image Processing

Based on the real time measurement of the width of coal flow, the method for measuring the width and the relative position of coal flow on a conveyor-belt by image processing was presented. A feeding control system of conveyor-belt was proposed using a fuzzy controller. This control system consists of CCD camera, universal image sampling system, control network and executor. The result shows that the algorithm used in the image processing is simple and efficient, and the measuring error of width is less than 4%.

Correcting Image Distortion for Adaptive Cruise Control

One of the main drivers for intelligent transportation systems is safety. Adaptive cruise control, as a common solution for traffic safety, lias extended from radars to cameras. Due to high mobility of vehicles and unevenness of roads, the picture quality of cameras has been great challenges for camera-based adaptive cruise control. In this paper, an image distortion correction algorithm is addressed. Our method is based on optical flow technology which is normally applied in motion estimation and video compression research. We are the first to attempt to adapt it in image distortion correction. Two optical flow approaches, the Lucas-Kanade method and the Horn-Schunck method, are selected and compared. The procedure of image distortion correction using the optical flow method has been tested by both synthetic test images and camera images. The experimental results show that the Lucas-Kanade method is more suitable in the correction of image distortion.

Investigation of Unsteady Flow Fields for Flow Control Research by Means of Particle Image Velocimetry

Unsteady three-dimensional flow phenomena must be investigated and well understood to be able to design devices to control such complex flow phenomena in order to achieve the desired behavior of the flow and to assess their performance, even in harsh industrial environments. Experimental investigations for flow control research require measurement techniques capable to resolve the flow field with high spatial and temporal resolution to be able to perceive the relevant phenomena. Particle Image Velocimetry (PIV), providing access to the unsteady flow velocity field, is a measurement technique which is readily available commercially today. This explains why PIV is widely used for flow control research. A number of standard configurations exist, which, with increasing complexity, allow capturing flow velocity data instantaneously in geometrical arrangements extending from planes to volumes and in temporal arrangements extending from snapshots to temporarily well resolved data. With increasing complexity these PIV systems require advancing expertise of the user and growing investment costs. Using typical problems of flow control research, three different standard PIV systems will be characterized briefly. It is possible to upgrade a PIV system from a simple planar to a “high end” tomographic PIV system over a period of time, if sufficient PIV expertise can be built up and budget for additional investments becomes available.

A rate control approach to distributed source coding for interferential multispectral image compression

Distributed source coding （DSC） is applied to interferential multispectral image compression owing to strong correlation among the image frames. Many DSC systems in the literature use feedback channel （FC） to control rate at the decoder, which limits the application of DSC. Upon an analysis of the image data, a rate control approach is proposed to avoid FC. Low-complexity motion compensation is applied first to estimate side information at the encoder. Using a polynomial fitting method, a new mathematical model is then derived to estimate rate based on the correlation between the source and side information. The experimental results show that our estimated rate is a good approximation to the actual rate required by FC while incurring a little bit-rate overhead. Our compression scheme performs comparable with the FC based DSC system and outperforms JPEG2000 significantly.

Controlled illumination and seismic acquisition geometry for target-oriented imaging

The conventional method of seismic data acquisition geometry design is based on the assumption of horizontal subsurface reflectors, which often is not suitable for complex structure. We start from a controlled illumination analysis and put forward a method of seismic survey geometry design for target-oriented imaging. The method needs a velocity model obtained by a preliminary seismic interpretation. The one-way Fourier finite-difference wave propagator is used to extrapolate plane wave sources on the target layer to the surface. By analyzing the wave energy distribution at the surface extrapolated from the target layer, the shot or receiver locations needed for target layer imaging can be determined. Numerical tests using the SEG-EAGE salt model suggest that this method is useful for confirming the special seismic acquisition geometry layout for target-oriented imaging.

Controllable image generation based on causal representation learning

Artificial intelligence generated content(AIGC)has emerged as an indispensable tool for producing large-scale content in various forms,such as images,thanks to the significant role that AI plays in imitation and production.However,interpretability and controllability remain challenges.Existing AI methods often face challenges in producing images that are both flexible and controllable while considering causal relationships within the images.To address this issue,we have developed a novel method for causal controllable image generation(CCIG)that combines causal representation learning with bi-directional generative adversarial networks(GANs).This approach enables humans to control image attributes while considering the rationality and interpretability of the generated images and also allows for the generation of counterfactual images.The key of our approach,CCIG,lies in the use of a causal structure learning module to learn the causal relationships between image attributes and joint optimization with the encoder,generator,and joint discriminator in the image generation module.By doing so,we can learn causal representations in image’s latent space and use causal intervention operations to control image generation.We conduct extensive experiments on a real-world dataset,CelebA.The experimental results illustrate the effectiveness of CCIG.

Weld pool image sensor for pulsed MIG welding

Visual image sensor is developed to detect the weld pool images in pulsed MIG welding. An exposure controller, which is composed of the modules of the voltage transforming, the exposure parameters presetting, the complex programmable logic device （CPLD） based logic controlling, exposure signal processing, the arc state detecting, the mechanical iris driving and so on, is designed at first. Then, a visual image sensor consists of an ordinary CCD camera, optical system and exposure controller is established. The exposure synchronic control logic is described with very-high-speed integrated circuit hardware description language （VHDL） and programmed with CPLD , to detect weld pool images at the stage of base current in pulsed MIG welding. Finally, both bead on plate welding and V groove filled welding are carried out, clear and consistent weld pool images are acquired.

Impact of GCP distribution on the rectification accuracy of Landsat TM imagery in a coastal zone

The purpose is to explore the effect of the spatial distribution of ground control points （GCPs） on the accuracy of imagery rectification. Both area-distributed and linearly distributed GCPs were used to rectify a Landsat TM image of a coastal zone. Rectification accuracy was checked against 99 independent points over the intertidal mudflats with no ground control. Results indicate that the root-mean-square error of residuals over these areas is several times larger than its GCPs-measured counterpart. If the GCPs are spatially dispersed over an area, residuals fluctuate but increase steadily with distance to the source of control in easting （R^2= 0. 827）. in northing they fluctuate around 150 m until 15 km, beyond which they rise steadily at a small range of fluctuation. These residuals are less predictable from distance to the source of control than in easting （R^2= 0.517 ）. If the GCPs are distributed along a control line, residuals rise with distance to it linearly and predictably （R^2 = 0. 877） in the direction perpendicular to it. In a direction parallel to it, the distance has little impact on rectification residuals.

Off-axis multi-wavelength dispersion controllingmetalens for multi-color imaging

Dispersion control is crucial in optical systems,and chromatic aberration is an important factor affecting imaging quality in imaging systems.Due to the inherent property of materials,dispersion engineering is complex and needs to trade off other aberration in traditional ways.Although metasurface offers an effective method to overcome these limits and results in well-engineered dispersion,off-axis dispersion control is still a challenging topic.In this paper,we design a single-layer metalens which is capable of focusing at three wavelengths(473 nm,532 nm,and 632 nm)with different incident angles(0°,-17°and 17°)into the same point.We also demonstrate that this metalens can provide an alternative for the bulky color synthetic prism in a 3-chips digital micromirror device(DMD)laser projection system.Through this approach,various off-axis dispersion controlling optical devices could be realized.

Recent advancement of chemical imaging in pharmaceutical quality control:From final product testing to industrial utilization

Chemical imaging(CI)possesses a strong ability of pharmaceutical analysis.Its great strength relies on the integration of traditional spectroscopy(one dimension)and imaging technique(two dimensions)to generate three-dimensional data hypercubes.Data pre-processing or processing methods are proposed to analyze vast data matrixes and thereby realizing different research objectives.In this review paper,various pharmaceutical applications of quality control over the past few years are summed up in two groups of final product test and industrial utilization.The scope of"quality control"here includes traditional analytical use,process understanding and manufactural control.Finally,two major challenges about undesirable sample geometry and lengthy acquisition time are discussed for prospective commercial or industrial application.

A Controlled Study on Comparing Differences in CT Perfusion Imaging between Rabbits inoculated with VX2 Lung Tumor and Patients with Squamous Cell Carcinoma of the Lung

OBJECTIVE By analysis and evaluation of the perfusion images and perfusion parameters of the rabbits with VX2 lung tumor, the association between the perfusion parameters and tumor angiogenesis of patients with squamous cell carcinoma of the lung has been studied in order to establish a non-invasive and effective way to detect tumor blood supply, which is be able to exhibit hemodynamic data in tumors during cancer treatments. METHODS Fifteen Netherlands rabbits inoculated with VX2 lung tumor （rabbit group） and 25 patients with squamous cell carcinoma of the lung （patient group） received a multi-slice spiral CT perfusion imaging test using the Netherlands PHILIPS Brilliance 16-slice spiral CT and a U.S. MEDRAD binocular highpressure syringe. Image postprocessing was done using the special perfusion software and EBW 4.0 Workstation. Perfusion volume （PV）, peak enhanced increment （PEI）, transit time peak （TTP）, and blood volume （BV） were measured and analyzed. RESULTS In the rabbit group, the values of the PV, PEI, TTP, and BV of the tumor margin were （53.89 ± 13.38） mL/（min.mL）, （45.71 ± 15.52） Hu, （39.29 ± 10.10） sec, and （31.45 ± 18.19） mL/100 g, respectively; these values of the tumor center were （36.57 ± 14.17） mL/（min.mL）, （28.64 ± 11.74） Hu, （39.00 ＋ 9.78） sec, and （19.76 ± 13.95） mL/100 g, respectively; the values of the muscles were （12.45± 4.38） mL/（min.mL）, （10.98 ± 5.03） Hu, （38.86 ± 10.04） sec, and （5.38 ±2.87） mL/100 g, respectively. The values of the relative perfusion volume （RPV）, relative peak enhanced increment （RPEI）, and relative blood volume （RBV） of the tumor margin were 4.38 ± 1.45, 3.96± 1.45, 9.99 ± 11.7, respectively; these values of the tumor center were 2.14 ± 1.08, 1.83±1.45, 4.17 ±3.39, respectively. The values of the PV, PEL BV of the tumor margin vs. the values of the muscles developed t-values, which were 15.028, 10.79, and 5.88, respectively （P ≤ 0.01）, with statistical significance; the values of the PV, PEI, BV of the tumor center vs. the values of the muscles produced t-values, which were 8.67, 7.49, and 4.55, respectively （P 〈 0.01）, with statistical significance. The values of the TTP of the tumor margin vs. TTP values of the muscles, and the TTP values of the tumor center vs. TTP values of the muscles developed t-values, which were 1.7 and 0.806, respectively （P ≥ 0.05）, without statistical significance. In the patient group, the values of the PV, PE, TTP, and BV of the tumor margin were （88.95 ± 30.89） mL/（min.mL）, （61.87 ± 27.31） Hu, （37.72 ± 12.53） sec, and （18.38 ± 7.2） mL/100 g, respectively; these values of the tumor center were （39.77 ± 18.29） mL/（min.mL）, （14.57 ± 8.1） Hu, （35.64 ± 12.41） sec, and （11.22 ± 6.02） mL/100 g, respectively; these values of the muscles were （12.45 ± 6.5） mL/（min.mL）, （6.14 ± 2.66） Hu, （35.68± 12.35） sec, and （2.23 ± 1.11） mL/100 g, respectively. The values of the RPV, RPEI, and RBV of the tumor margin were 8.05 ± 5.04, 8.87 ± 4.32, and 12.16 ± 8.49, respectively; these values of the tumor center were 2.39 ± 1.68, 2.97 ± 2.1, 3.53 ± 2.82, respectively. The values of the PV, PEI, BV of the tumor margin in the patient group vs. the values of the muscles produced t-values, which were 13.8, 10.85, and 12.22, respectively （P 〈 0.01）, with significant differences; these values of the tumor center vs. the values of the muscles developed t-values, which were 9.158, 6.26, 8.654, respectively （P 〈 0.01）, with significant differences. The TTP value of the tumor margin vs. that of the muscles produced t-value, which was 0.371, and the TTP value of the tumor center vs. that of the muscles developed t-value, which was 1 （P 〉 0.05）, without statistical difference. CONCLUSION CT perfusion imaging technics demonstrates directly dynamic changes of blood flow to tumors, which assists in identifying tumor growth and necrosis, therefore, this research provides an evidence-based guidelines for the treatment of human lung squamous cell carcinoma and has far-reaching clinical significance.