Visual Detection Method Research Articles

Visual detection of donkey-derived ingredients by loop-mediated isothermal amplification with 4-(2-pyridylazo)-resorcinol sodium salt

ABSTRACT The objective of this study was to develop a reliable visual method for rapid detection of donkey components to protect consumers from commercial adulteration. Six specific loop-mediated isothermal amplification (LAMP) primers targeted at donkey mitochondrial cytochrome b gene were designed, the mitochondrial DNA extraction simplified, the LAMP reaction system optimized, the specificity verified with mitochondrial DNA of horse, pork, cow, sheep, chicken, duck, and rabbit as negative controls, the detection limit determined with gradient dilution of adulterated meat with donkey meat, and the visual LAMP method for detection of donkey-derived ingredient in common meat products established. The results showed that the modified mitochondrial DNA extraction method was simple and repeatable, and the visual LAMP method with 4-(2-pyridylazo)-resorcinol sodium salt as indicator can accurately and specifically detect the donkey meat in common meat products, 1% detection limit. The study provided a promising solution for facilitating the surveillance of the commercial adulteration in processed meat.

Visual Object Detector for Cow Sound Event Detection

Sound event detection (SED) is a reasonable choice in a number of application domains including cattle sheds, dense forests, or any dark environments where visual objects are usually concealed or invisible. This study presents an autonomous monitoring system based on sound characteristics developed for welfare management in large cattle farms. Two types of artificial audio datasets are prepared: the cow sound event dataset and the UrbanSound8K dataset, which are then used with various sound object detectors for real world implementation. Using a data-driven approach, a conventional convolutional neural network structure with certain improvements is first applied, and from there proceed to a two-stage visual object detection method for audio by treating acoustic signals as an RGB images. The object detection method achieves a higher quantitative evaluation score and more precise qualitative results than previous related studies. We conclude that visual object detection methods are more effective than currently-available CNN architectures for rare sound object detection. Indeed, an artificial data preparation strategy can provide a better method for addressing the problem of data scarcity and the annotation difficulties involved in rare sound event detection.

Field Verifications of Geological Structures Related to SAR Detected Lineaments

Identifying geological structures is a crucial step in geological field mapping. One common technique to interpret geological structures is using lineament analyses on the satellite imagery. The usual encounters is many lineaments do not concordance to the geological structures. Overcoming the problem, we used dual orbit Synthetic Aperture Radar (SAR) images to obtain lineaments related to geological structures at ground level. In this paper, we presented the sensitivity of the lineaments detection method visually and automatically using Yamaguchi and modified Segment Tracing Algorithm (mSTA) methods, respectively. The Yamaguchi method is a visual lineament detection using an optimum image-scale and resolution. The method was used to detect lineaments based on visual limitation of the interpreter. On the contrary, the mSTA method is an automatic lineament detection utilizing SAR backscattering intensity images in opposite Line of Sight (LOS). Accordingly, we compared the effectiveness between the visual and automatic detection methods in detecting the faults and joints correctly at ground surface. The verification of detected lineaments at the field was then performed and analyzed to obtain comparison of the effectiveness between two lineaments detection methods. The direction of joints at EKA-01 were oblique 45 degrees to Yamaguchi method, and 25 degrees to mSTA method. Besides, the direction of faults and joints at EKA-10 were oblique 5 degrees to Yamaguchi method, and 2 degrees to mSTA method. mSTA method has smaller offset angle to field measurements than Yamaguchi method, indicating that the automatic is more effective and representative to detect lineaments related to geological structures than visual method.

Establishment of RT-LAMP assay for detection of citrus leaf blotch virus 柑橘叶斑驳病毒的 RT-LAMP 检测

This study aim of is to establishe the detection method of reverse transcription loop-mediated isothermal amplification (RT-LAMP)method for visual detection of CLBV, and validate its sensitivity and accuracy. The primers were designed and screened based on the conserved region of coat protein gene of CLBV. The reaction conditions of the RT-LAMP, including amplification temperature and amplification time were optimized. The optimized RT-LAMP can be done at 65 ℃ within 60 min. The detection limits of the RT-LAMP was 23.2 pg · µL. When the SYBR greenⅠdye was added to the amplification product, the positive samples were observed visually to be green, whereas the negative samples were orange, and there is no need for gel electrophoresis analysis. The eastablished RT-LAMP was used to detect CLBV from 120 field samples. The detection rate of different source samples was between 0 and 15%, the result of the RT-LAMP was in accord with RT-PCR method.

Microfluidic paper-based analytical device using gold nanoparticles modified with N,N′-bis(2-hydroxyethyl)dithiooxamide for detection of Hg(ii) in air, fish and water samples

A new method for visual detection of mercury by color change is developed that can detect Hg2+ by the naked eye or a digital camera.

A high-precision multi-targets visual detection method in automatic driving scene

This is an application of multiple targets detection in the automatic driving scene based on computer vision, which integrates most of the major-aspects of the automatic driving scene, including the detection of lane lines and the identification of targets in current road conditions, such as vehicles, pedestrians, etc. This method has high precision, computational efficiency and strong practicability. The invention is mainly divided into two parts. First of all, in the lane line detection, we first carry out gray transformation on the input image, converting the RGB image into gray. Canny operator was used to obtain edge images after graying and binarization of ROI region. Then the edge image is transformed by Hough transform, and the edge line segment is converted from image space to Hough space. r- Image input r-l-mage g raysca e change Hough Canny transform edge extracts extraction Line rstablishment of regions of interest Morphological Canny Opening edge Operation extraction - wmr] Figure I

A Visual Detection Method for Foreign Objects in Power Lines Based on Mask R-CNN

The high-voltage power lines and transmission towers are large in volume, large in number, and wide in coverage, so they are easily attached to foreign objects, which may cause failure of the transmission line. The existing object detection methods are susceptible to weather and environmental factors, and the use of neural networks for target detection can achieve good results. Therefore, this article uses MASK R-CNN as the basic network detection method for detecting foreign objects in the transmission network. The experimental results show that compared with the traditional target detection method, the method adopted in this article has achieved good results in the speed, efficiency, and recognition precision of foreign object detection. In the future, image processing operations can be performed for complex backgrounds of transmission lines to improve recognition effect.

Visibility Detection Based on the Recognition of the Preceding Vehicle’s Taillight Signals

This paper proposes a method for visibility detection based on the recognition of the preceding vehicle’s taillight signals using in-vehicle camera and millimeter-wave (mm-W) radar. First, we design two methods of vehicle identification. One is to use Haar-like features and an AdaBoost algorithm to train the vehicle classifier, which is mainly used to identify vehicles without turning on the taillights. The other is to identify vehicles with taillights on by means of taillight segmentation. The two identification methods are combined with a Discriminative Scale Space Tracker (DSST) to track the vehicle in the image acquired by vehicle camera and to measure anthropic visibility with mm-W radar. In addition, we drove a test vehicle on a foggy highway and collected experimental data through in-vehicle camera and mm-W radar. The experimenter observed the movement of the vehicle in front until it disappeared from the field of vision and recorded the distance of the vehicle in front measured by radar at that time as human visibility, which was also used as the ground truth to verify the accuracy of the proposed visibility detection method. The experimental results show that the visibility measured by the proposed algorithm is essentially consistent with the visibility obtained by human eyes, that is, the visibility of vehicles with no taillights, clearance lamp, emergency flasher, or fog lamp tends to rise, with an average accuracy of 88%, 91%, 90%, and 95%, respectively. In contrast to the traditional visibility measurement, this method mainly measures the maximum distance that the driver can observe when the front vehicle is not turned on or different taillights are turned on.

Sensitive Multicolor Visual Detection of Exosomes via Dual Signal Amplification Strategy of Enzyme-Catalyzed Metallization of Au Nanorods and Hybridization Chain Reaction.

Exosomes as nanosized vesicles have been recognized as potential noninvasive biomarkers for early cancer diagnosis. Herein, we presented a sensitive multicolor visual method for exosome detection based on enzyme-induced silver deposition on gold nanorods (Au NRs). To achieve highly sensitive determination of exosomes, hybridization chain reaction (HCR) was employed to introduce more alkaline phosphatase (ALP) for signal amplification. First, exosomes were captured by magnetic bead-labeled CD63 aptamer, and, then, cholesterol-modified DNA probes were spontaneously inserted into the exosomal lipid membrane. The ends of the DNA probes act as the initiator to trigger the HCR for signal amplification. Finally, with the help of HCR, increased sites led to enhanced ALP loading and thus boosted the ascorbic acid generation. Silver ions were reduced by ascorbic acid, and silver shells were formed on Au NRs, giving rise to the blue shift of the longitudinal localized surface plasmon resonance peak. Correspondingly, the concentration of exosomes can be obviously distinguished with naked eyes via the vivid color variation. Due to the dual signal amplification of HCR and metallization of Au NRs, highly sensitive detection for exosomes were realized with detection limits as low as 1.6 × 102 particles/μL by UV-vis spectroscopy and 9 × 103 particles/μL by naked eyes. Compared to the reported colorimetric methods for exosome quantification, visualization based on plentiful color tonalities is the most captivating merit of our approach, and HCR-induced signal amplification highlights the virtue of the strategy. The applicability of the method was validated by the analysis of clinical samples.

Molecular method for rapid detection of the red tide dinoflagellate Karenia mikimotoi in the coastal region of Xiangshan Bay, China

The species Karenia mikimotoi is a common nearshore red tide alga that can secrete hemolytic exotoxin and ichthyotoxin, which can induce the death of fish and shellfish, causing severe economic losses. In this study, loop-mediated isothermal amplification (LAMP) was employed in combination with the lateral flow dipstick (LFD) visual detection method to establish the LAMP-LFD rapid detection method for K. mikimotoi. The internal transcribed spacer ITS1-5.8S-ITS2 of K. mikimotoi was used as the target sequence and was amplified with specific primers designed in this study. The results indicated that the amplification optimal reaction conditions for LAMP in this paper were for 20 min at 65 °C. Moreover, LAMP had excellent specificity, showing negative results for other common red tide causing algal species. In field samples, we successfully reduced the total time, with only 23 min needed from LAMP amplification to LFD result display, which was shorter than that of conventional PCR. Consequently, LAMP-LFD should be useful for rapid field detection of low-density K. mikimotoi and for the early prevention of red tide induced by such algae.

Object detection based on color and shape features for service robot in semi-structured indoor environment

Intelligent service robot is a challenging area of research that is rapidly expanding in our daily life. To meet robot’s object detection requirements in a messy surrounding, this paper provides a visual object detection method based on color and shape features. Firstly, a color hierarchical model and a multi-size filter are built to obtain initial object regions from scene image. Then a straight line-corner-arc strategy is presented to detect shape features. After comparing color and shape features with known-objects’ features stored in database, the detection scope is narrowed. So speeded up robust features algorithm is used to quickly match object features. The proposed method is tested by mobile robot in a semi-structured indoor environment. Finally, combined with the above steps, the total detection accuracy achieves 88.5% that confirms the feasibility of the proposed method.

Dual-emission carbon dots-stabilized copper nanoclusters for ratiometric and visual detection of Cr2O72- ions and Cd2+ ions

The pollution of heavy metal increases greatly accompanying by the development of industries. So, it is very important to build up a quick and reliable technique for detection of heavy metal ions. In this work, we developed a simple and convenient method for ratiometric and visual detection of Cr2O72- ions and Cd2+ ions. We utilized glutathione as raw material to prepare cyan-emitting carbon dots (GSH@CDs). The GSH@CDs were further used as the template to prepare carbon dots-stabilized copper nanoclusters (GSH@CDs-Cu NCs) that displayed two well-separated emission peaks respectively at 450 nm and 750 nm. The GSH@CDs-Cu NCs can be applied for the ratiometric and visual detection of Cr2O72- and Cd2+ ions based on the fluorescence quenching or enhancement of GSH@CDs-Cu NCs at 750 nm. A linear range of 2–40 μmol L-1 with a detection limit of 0.9 μmol L-1 for Cr2O72- ions, and a linear range of 0–20 μmol L-1 with a detection limit of 0.6 μmol L-1 for Cd2+ ions were achieved based on this method. The fluorescent test strips for Cr2O72- ions were successfully prepared based on GSH@CDs-Cu NCs. Moreover, the GSH@CDs-Cu NCs were successfully applied to determine Cr2O72- and Cd2+ ions in real samples with promising results.

Visual and rapid detection of Plesiomonas shigelloides using loop-mediated isothermal amplification method.

Plesiomonas shigelloides is a common pathogen of aquatic animals and can pose a certain hazard to aquaculture. Here, we aimed to develop a loop-mediated isothermal amplification (LAMP) method for the visual detection of P. shigelloides to aid the diagnosis of infections caused by this pathogen in aquatic animals. We used LAMP to amplify P. shigelloides DNA and combined it with calcein or nucleic acid dipstick assay (NADA) to visualize the amplified products. The optimal LAMP amplification temperature was 64°C, and the reaction lasted for 50min. The limit of detection of recombinant plasmids containing the target gene using the LAMP method was 2·0×102 copies per μl, which is ten times higher than that using conventional polymerase chain reaction (PCR). LAMP products could be visualized without agarose gel electrophoresis. We tested 85 fish specimens using the established LAMP method and conventional PCR. The detection rate was 42·4% using the LAMP method and 34·1% using conventional PCR. Based on our results, the LAMP method combined with calcein or NADA is a rapid, specific, sensitive and accurate method for visual detection of fish-derived P. shigelloides and can be used for the laboratory diagnosis of infections caused by it. SIGNIFICANCE AND IMPACT OF THE STUDY: The combination of loop-mediated isothermal amplification (LAMP) and calcein and nucleic acid dipstick assay (NADA) provided a rapid, specific and sensitive method for detecting Plesiomonas shigelloides, which is an important pathogen that causes diseases in aquatic animals worldwide. In the present study, the LAMP method showed a higher detection rate than conventional PCR for P. shigelloides using templates from 85 fish specimens. Thus, the LAMP method could be a reliable and convenient tool for diagnosing diseases in aquatic animals in the laboratory.

A simple visual method for DNA detection based on the formation of gold nanoparticles

A simple visual method for DNA detection during the formation of gold nanoparticles (AuNPs) was developed based on different electrostatic properties of single strand DNA (ssDNA) and double strand DNA (dsDNA). Since the ssDNA is easy to bind to AuNPs due to its exposed bases which could prevent salt-induced aggregation of AuNPs. The dsDNA always present negative charge because its negatively charged phosphate backbone is exposed. In this case, the dsDNA could disturb the adsorption between dsDNA and AuNPs and result in non-aggregation of AuNPs. After hybridization, chloroauric acid and ascorbic acid were added to the mixture solution, and the solution changed to red immediately and turned to purple in 10 min in the present of target DNA. TEM results confirmed that the change of color stemed from aggregation of AuNPs. In order to obtain accurate results by naked eye, the DNA detection assay should be conducted under pH 7.0.

Development of a reverse transcription-loop-mediated isothermal amplification assay for the detection of parrot bornavirus 4

Avian bornavirus (ABV) is the causative agent of proventricular dilatation disease, which is fatal in psittacine birds. ABVs have spread worldwide, and outbreaks have led to mass deaths of captive birds in commercial and breeding facilities. The segregation of infected birds is a countermeasure to prevent ABV spread in aviaries. However, this approach requires a highly sensitive detection method for the screening of infected birds before virus transmission. In this study, we developed a reverse transcription-loop-mediated isothermal amplification (RT-LAMP) assay for the diagnosis of parrot bornavirus 4 (PaBV-4), a dominant ABV genotype. Using this assay, we successfully detected PaBV-4 RNA in cell cultures, brain tissues, and feces. We also developed methods for simple RNA extraction and visual detection without electrophoresis. The sensitivity of the newly established RT-LAMP assay was 100-fold higher than that of the real-time PCR (RT-qPCR) assay. Accordingly, the RT-LAMP assay developed in this study is suitable for the rapid and sensitive diagnosis of PaBV-4 without specialized equipment and will contribute to virus control in aviaries.

A Visual Detection and Location Method for Soft Fabrics

The soft fabric is prone to burr, fold, enfold and blur, which poses a great challenge to the accuracy of visual edge detection and localization of the autonomous loading and unloading material system of garment robot. In order to overcome the above problems, it proposes an adaptive edge localization method based on double filtering in this paper, which can be used to guide the garment robot to achieve grasping of soft fabric automatically. Firstly, the Gauss filtering and morphological filtering are used to smooth the image, and then it calculates the canny adaptive threshold based on the edge gradient information and detect the edge, finally it locates the coordinates of edge feature extracted. The experiment results show that the method is effective accuracy greater than 96%and robust tested on the real data sets composed of soft fabric. The method has good application value for the autonomous loading and unloading operation of the garment robot and has positive significance for the construction of the intelligent garment factory.

A Method of Visibility Detection Based on the Transfer Learning

AbstractAtmospheric visibility is an important element of meteorological observation. With existing methods, defining image features that reflect visibility accurately and comprehensively is difficult. This paper proposes a visibility detection method based on transfer learning using deep convolutional neural networks (DCNN) that addresses issues caused by a lack of sufficient visibility labeled datasets. In the proposed method, each image was first divided into several subregions, which were encoded to extract visual features using a pretrained no-reference image quality assessment neural network. Then a support vector regression model was trained to map the extracted features to the visibility. The fusion weight of each subregion was evaluated according to the error analysis of the regression model. Finally, the neural network was fine-tuned to better fit the problem of visibility detection using the current detection results conversely. Experimental results demonstrated that the detection accuracy of the proposed method exceeds 90% and satisfies the requirements of daily observation applications.

Visual detection of porcine reproductive and respiratory syndrome virus using CRISPR-Cas13a.

Porcine reproductive and respiratory syndrome virus (PRRSV) has varied constantly and circulated in the pig industry worldwide. The prevention and control of porcine reproductive and respiratory syndrome (PRRS) is complicated. A visual, sensitive and specific diagnostic method is advantageous to the control of PRRS. The collateral cleavage activity of LwCas13a is activated to degrade non-targeted RNA, when crRNA of LwCas13a bond to target RNA. The enhanced Cas13a detection is the combination of collateral cleavage activity of LwCas13a and recombinase polymerase amplification (RPA). In this study, the enhanced Cas13a detection for PRRSV was established. The novel method was an isothermal detection at 37°C, and the detection can be used for real-time analysis or visual readout. The detection limit of the enhanced Cas13a detection was 172 copies/μl, and there were no cross-reactions with porcine circovirus 2, porcine parvovirus, classical swine fever virus and pseudorabies virus. The enhanced Cas13a detection can work well in clinical samples. In summary, a visual, sensitive and specific nucleic acid detection method based on CRISPR-Cas13a was developed for PRRSV.

Identification of pork in raw meat or cooked meatballs within 20 min using rapid PCR coupled with visual detection

Meat adulteration is seriously damaging the interests of consumers. It is important to develop a rapid, simple, cost-effective and sensitive method to identify meat species. In this study, a pair of suitable pork-specific primers was determined by the comparison of three pairs of pork-specific primers and the annealing/extension temperature optimized here was set at 64 °C. Rapid polymerase chain reaction (PCR) with glass capillary as reaction vessel, which could complete 45 cycles in 5 min by using two ordinary water baths, was established to detect pork contents in raw beef meat or cooked beef meatballs. A SYTO 9-based visual detection method was used to evaluate the amplification results. The fluorescence signal of negative samples could be removed at 72 °C according to the results of original melt curves of positive and negative samples. Strong green fluorescence would be produced in positive samples while the color of negative samples still remained black under the blue light (470 nm). A simple and portable device was designed to prevent detection results disturbed by ambient light and make operation easier. As low as 0.01% pork contents in binary mixtures could be detected and the whole detection process could be finished in 20 min from sampling to results. The developed method would have great potential for rapid on-site detection of pork meat and identification of meat species.

Computer Vision Measurement of Pointer Meter Readings Based on Inverse Perspective Mapping

A computer vision method for measuring multiple pointer meters is proposed based on the inverse perspective mapping. First, the measured meter scales are used as the calibration objects to obtain the extrinsic parameters of the meter plane. Second, normal vector of the meter plane can be acquired by the extrinsic parameters, obtaining the rotation transformation matrix of the meter image. Then, the acquired meter image is transformed to a position both parallel to the meter plane and near the main point by the rotation transformation matrix and the extrinsic parameters, eliminating the perspective effect of the acquired image. Finally, the transformed image is tested by the visual detection method to obtain the readings of the pointer meter, improving measurement precision. The results of the measurement verify the effectiveness and accuracy of the method.