Real-Time Detection and Instance Segmentation of Strawberry in Unstructured Environment

The real-time detection and instance segmentation of strawberries constitute fundamental components in the development of strawberry harvesting robots.Real-time identification of strawberries in an unstructured envi-ronment is a challenging task.Current instance segmentation algorithms for strawberries suffer from issues such as poor real-time performance and low accuracy.To this end,the present study proposes an Efficient YOLACT(E-YOLACT)algorithm for strawberry detection and segmentation based on the YOLACT framework.The key enhancements of the E-YOLACT encompass the development of a lightweight attention mechanism,pyramid squeeze shuffle attention(PSSA),for efficient feature extraction.Additionally,an attention-guided context-feature pyramid network(AC-FPN)is employed instead of FPN to optimize the architecture’s performance.Furthermore,a feature-enhanced model(FEM)is introduced to enhance the prediction head’s capabilities,while efficient fast non-maximum suppression(EF-NMS)is devised to improve non-maximum suppression.The experimental results demonstrate that the E-YOLACT achieves a Box-mAP and Mask-mAP of 77.9 and 76.6,respectively,on the custom dataset.Moreover,it exhibits an impressive category accuracy of 93.5%.Notably,the E-YOLACT also demonstrates a remarkable real-time detection capability with a speed of 34.8 FPS.The method proposed in this article presents an efficient approach for the vision system of a strawberry-picking robot.

Real-Time Object Detection and Face Recognition Application for the Visually Impaired

The advancement of navigation systems for the visually impaired has significantly enhanced their mobility by mitigating the risk of encountering obstacles and guiding them along safe,navigable routes.Traditional approaches primarily focus on broad applications such as wayfinding,obstacle detection,and fall prevention.However,there is a notable discrepancy in applying these technologies to more specific scenarios,like identifying distinct food crop types or recognizing faces.This study proposes a real-time application designed for visually impaired individuals,aiming to bridge this research-application gap.It introduces a system capable of detecting 20 different food crop types and recognizing faces with impressive accuracies of 83.27%and 95.64%,respectively.These results represent a significant contribution to the field of assistive technologies,providing visually impaired users with detailed and relevant information about their surroundings,thereby enhancing their mobility and ensuring their safety.Additionally,it addresses the vital aspects of social engagements,acknowledging the challenges faced by visually impaired individuals in recognizing acquaintances without auditory or tactile signals,and highlights recent developments in prototype systems aimed at assisting with face recognition tasks.This comprehensive approach not only promises enhanced navigational aids but also aims to enrich the social well-being and safety of visually impaired communities.

Analyzing the Impact of Scene Transitions on Indoor Camera Localization through Scene Change Detection in Real-Time

Real-time indoor camera localization is a significant problem in indoor robot navigation and surveillance systems.The scene can change during the image sequence and plays a vital role in the localization performance of robotic applications in terms of accuracy and speed.This research proposed a real-time indoor camera localization system based on a recurrent neural network that detects scene change during the image sequence.An annotated image dataset trains the proposed system and predicts the camera pose in real-time.The system mainly improved the localization performance of indoor cameras by more accurately predicting the camera pose.It also recognizes the scene changes during the sequence and evaluates the effects of these changes.This system achieved high accuracy and real-time performance.The scene change detection process was performed using visual rhythm and the proposed recurrent deep architecture,which performed camera pose prediction and scene change impact evaluation.Overall,this study proposed a novel real-time localization system for indoor cameras that detects scene changes and shows how they affect localization performance.

A YOLOv8-CE-based real-time traffic sign detection and identification method for autonomous vehicles

Traffic sign detection in real scenarios is challenging due to their complexity and small size,often preventing existing deep learning models from achieving both high accuracy and real-time performance.An improved YOLOv8 model for traffic sign detection is proposed.Firstly,by adding Coordinate Attention(CA)to the Backbone,the model gains location information,improving detection accuracy.Secondly,we also introduce EIoU to the localization function to address the ambiguity in aspect ratio descriptions by calculating the width-height difference based on CIoU.Additionally,Focal Loss is incorporated to balance sample difficulty,enhancing regression accuracy.Finally,the model,YOLOv8-CE(YOLOv8-Coordinate Attention-EIoU),is tested on the Jetson Nano,achieving real-time street scene detection and outperforming the Raspberry Pi 4B.Experimental results show that YOLOv8-CE excels in various complex scenarios,improving mAP by 2.8%over the original YOLOv8.The model size and computational effort remain similar,with the Jetson Nano achieving an inference time of 96 ms,significantly faster than the Raspberry Pi 4B.

Current trends in nanomaterials-mediated biosensing platforms and signal amplification strategies for antibiotics detection in dairy products

Dairy products have become one of the most prevalent daily foods worldwide,but safety concerns are rising.In dairy farming,unscrupulous traders misuse antibiotics to treat some diseases such as mastitis in cows,leading to antibiotic residues in dairy products.Rapid,sensitive,and simple detection methods for antibiotic residues are particularly important for food safety in dairy products.Traditional detection technology can effectively detect antibiotics,but there are defects such as complicated pre-treatment and high cost.Biosensors are widely used in food safety due to fast detection speed,low detection cost,strong anti-interference ability,and suitability for the field application.Nevertheless,these sensors often fail to trigger the signal conversion output due to low target concentration.To cope with this issue,some high-efficiency signal amplification systems can be introduced to improve the detection sensitivity and linear range of biosensors.In this review,we focused on:(i)Sources and toxicity of major antibiotics in animal-derived foods.(ii)Nanomaterial-mediated biosensors for real-time detection of target antibiotics in animal-derived foods.(iii)Signal amplification techniques to increase the sensitivity of biosensors.Finally,future prospects and challenges in this research field are discussed.

A CNN-Based Single-Stage Occlusion Real-Time Target Detection Method

Aiming at the problem of low accuracy of traditional target detection methods for target detection in endoscopes in substation environments, a CNN-based real-time detection method for masked targets is proposed. The method adopts the overall design of backbone network, detection network and algorithmic parameter optimisation method, completes the model training on the self-constructed occlusion target dataset, and adopts the multi-scale perception method for target detection. The HNM algorithm is used to screen positive and negative samples during the training process, and the NMS algorithm is used to post-process the prediction results during the detection process to improve the detection efficiency. After experimental validation, the obtained model has the multi-class average predicted value (mAP) of the dataset. It has general advantages over traditional target detection methods. The detection time of a single target on FDDB dataset is 39 ms, which can meet the need of real-time target detection. In addition, the project team has successfully deployed the method into substations and put it into use in many places in Beijing, which is important for achieving the anomaly of occlusion target detection.

Development of an One-step Reverse Transcription Loop-mediated Isothermal Amplification Method for Rapid Detection of Bovine Viral Diarrhea Virus

Objective] This study aimed to develop a reverse transcription loop-medi-ated isothermal amplification （RT-LAMP） method for detecting BVDV. [Method] Since gp48 gene of BVDV is among the most conserved regions, a set of four primers was designed to amplify six target sequences at the gp48 gene region for the RT-LAMP assay. The optimization of the RT-LAMP reaction was performed by evaluat-ing reaction temperature and reaction time. [Result] The RT-LAMP aasay was suc-cessful y conducted at 56 ℃ within 40 min under isothermal conditions, and the re-sults could be detected as ladder-like bands using agarose gel electrophoresis. The RT-LAMP assay is highly sensitive and able to detect 3.74 ×100 copies/μl of BVDV RNA, as no cross-reaction was observed with other viruses. [Conclusion] Overal , the newly established RT-LAMP assay indicates the potential application in both clinical diagnosis and field surveil ance of BVDV.

Establishment of Reverse-transcription Loopmediated Isothermal Amplification Method for Detection of Wheat Streak Mosaic Virus

A reverse-transcription loop-mediated isothermal amplification （RT-LAMP） method was established for the detection of wheat streak mosaic virus （WSMV）. Ac-cording to the conservative regions of the genes that encode the coat protein of WSMV, 2 pairs of primers were designed. Final y, the 1st pair of primers was select-ed through the specificity test. The sensitivity test showed the sensitivity of RT-LAMP method was 10 times higher than that of RT-PCR. In addition, the amplifica-tion of target gene could be judged visual y from the presence of fluorescence （cal-cein） in the final reaction system. The RT-LAMP method, established in this study, was rapid, easy, specific and sensitive. Moreover, it did not require sophisticated equip-ment. The RT-LAMP was suitable for the rapid detection of WSMV.

The Application of Reverse Transcription-loop-mediated Isothermal Amplification for the Rapid Detection of Maize Chlorotic Dwarf Virus

Maize chlorotic dwarf virus （MCDV） is a quarantine pest as approved by Chinese government. A rapid, sensitive and specific MCDV detection method using reverse transcription-loop-mediated isothermal amplification （RT-LAMP） was estab- lished in this study. Based on the sequence of MCDV coat protein coding gene, specific primers were designed and similar sensitivities were observed between RT- LAMP and RT-PCR, except that RT-LAMP was quicker, and the reaction could be finished within 1 h. In addition, the presence or absence of the fluorescent display in daylight allows naked easy detection of the amplification of MCDV genomic RNA using calcein. The RT-LAMP assay was applied successfully to detect MCDV in maize seeds, and the result by the addition of calcein was consistent with the result detected by the real time turbidimeter.

Real-time image processing and display in object size detection based on VC++

Real-time detection for object size has now become a hot topic in the testing field and image processing is the core algorithm. This paper focuses on the processing and display of the collected dynamic images to achieve a real-time image pro- cessing for the moving objects. Firstly, the median filtering, gain calibration, image segmentation, image binarization, cor- ner detection and edge fitting are employed to process the images of the moving objects to make the image close to the real object. Then, the processed images are simultaneously displayed on a real-time basis to make it easier to analyze, understand and identify them, and thus it reduces the computation complexity. Finally, human-computer interaction （HCI）-friendly in- terface based on VC ＋＋ is designed to accomplish the digital logic transform, image processing and real-time display of the objects. The experiment shows that the proposed algorithm and software design have better real-time performance and accu- racy which can meet the industrial needs.

Visual Detection of Vibrio parahaemolyticus using Combined CRISPR/Cas12a and Recombinase Polymerase Amplification

Objective To establish an ultra-sensitive,ultra-fast,visible detection method for Vibrio parahaemolyticus(VP).Methods We established a new method for detecting the tdh and trh genes of VP using clustered regularly interspaced short palindromic repeats/CRISPR-associated protein 12a(CRISPR/Cas12a)combined with recombinase polymerase amplification and visual detection(CRISPR/Cas12a-VD).Results CRISPR/Cas12a-VD accurately detected target DNA at concentrations as low as 10^(-18)M(single molecule detection)within 30 min without cross-reactivity against other bacteria.When detecting pure cultures of VP,the consistency of results reached 100%compared with real-time PCR.The method accurately analysed pure cultures and spiked shrimp samples at concentrations as low as 10^(2)CFU/g.Conclusion The novel CRISPR/Cas12a-VD method for detecting VP performed better than traditional detection methods,such as real-time PCR,and has great potential for preventing the spread of pathogens.

Real-Time Detection of Cracks on Concrete Bridge Decks Using Deep Learning in the Frequency Domain

This paper presents a vision-based crack detection approach for concrete bridge decks using an integrated one-dimensional convolutional neural network(1D-CNN)and long short-term memory(LSTM)method in the image frequency domain.The so-called 1D-CNN-LSTM algorithm is trained using thousands of images of cracked and non-cracked concrete bridge decks.In order to improve the training efficiency,images are first transformed into the frequency domain during a preprocessing phase.The algorithm is then calibrated using the flattened frequency data.LSTM is used to improve the performance of the developed network for long sequence data.The accuracy of the developed model is 99.05%,98.9%,and 99.25%,respectively,for training,validation,and testing data.An implementation framework is further developed for future application of the trained model for large-scale images.The proposed 1D-CNN-LSTM method exhibits superior performance in comparison with existing deep learning methods in terms of accuracy and computation time.The fast implementation of the 1D-CNN-LSTM algorithm makes it a promising tool for real-time crack detection.

Rapid detection of Pseudomonas aeruginosa by cross priming amplification

Pseudomonas aeruginosa(PA)is an opportunistic pathogen of humans and animals and a common source of nosocomial infections especially of the respiratory tract.Pseudomonas aeruginosa is also a major bacterial disease of poultry and in particular,eggs and newly hatched chicks.In this study,we developed a simple,accurate and rapid molecular detection method using cross priming amplification(CPA)with a nucleic acid test strip to detect P.aeruginosa.The assay efficiently amplified the target gene within 45 min at 62℃only using a simple water bath.The detection limit of the method was 1.18x 102 copiesμL^-1 for plasmid DNA and 4.4 CFU mL^-1 for bacteria in pure culture,and was 100 times more sensitive than conventional PCR.We screened 83 clinical samples from yellow-feather broiler breeder chickens and hospitalized/treated dogs and cats using CPA,PCR and traditional culture methods.The positive sample ratios were 15.3%(13/83)by CPA,13.3%(11/83)by PCR and 12.1%(10/83)by the culture method.The established CPA method has significant advantages for detecting P.aeruginosa.The method is easy to use and possesses high specificity and sensitivity without the requirements of complicated experimental equipment.The PA-CPA assay is especially fit for outdoor and primary medical units and is an ideal system for the rapid detection and monitoring of P.aeruginosa.

A fast and adaptive method for automatic weld defect detection in various real-time X-ray imaging systems

A first and effective method is proposed to detect weld deject adaptively in various Dypes of real-time X-ray images obtained in different conditions. After weld extraction and noise reduction, a proper template of median filter is used to estimate the weld background. After the weld background is subtracted from the original image, an adaptite threshold segmentation algorithm is proposed to obtain the binary image, and then the morphological close and open operation, labeling algorithm and fids＇e alarm eliminating algorithm are applied to pracess the binary image to obtain the defect, ct detection result. At last, a fast realization procedure jbr proposed method is developed. The proposed method is tested in real-time X-ray image,s obtairted in different X-ray imaging sutems. Experiment results show that the proposed method is effective to detect low contrast weld dejects with few .false alarms and is adaptive to various types of real-time X-ray imaging systems.

Real-time Fluorescence PCR Method for Detection of Burkholderia glumae from Rice

Burkholderia glumae causing seedling rot and grain rot of rice was listed as a plant quarantine disease of China in 2007. It＇s quite necessary to set up effective detection methods for the pathogen to manage further dispersal of this disease. The present study combined the real-time PCR method with classical PCR to increase the detecting efficiency, and to develop an accurate, rapid and sensitive method to detect the pathogen in the seed quarantine for effective management of the disease. The results showed that all the tested strains of B. glumae produced about 139 bp specific fragments by the real-time PCR and the general PCR methods, while others showed negative PCR result. The bacteria could be detected at the concentrations of 1×10^4 CFU/mL by general PCR method and at the concentrations below 100 CFU/mL by real-time fluorescence PCR method. B. glumae could be detected when the inoculated and healthy seeds were mixed with a proportion of 1：100.

Rapid and Sensitive Detection of PRRSV by a Reverse Transcription-Loop-mediated Isothermal Amplification Assay

A real-time monitoring reverse transcription loop-mediated isothermal amplification (RT-LAMP) assay was developed for the sensitive and specific detection of prototypic,prevalent North American porcine reproductive and respiratory syndrome virus (PRRSV) strains.As a higher sensitivity and specificity method than reverse transcription polymerase chain reaction (RT-PCR),the RT-LAMP method only used a turbidimeter,exhibited a detection limit corresponding to a 10-4 dilution of template RNA extracted from 250 μL of 105 of the 50% tissue culture infective dose (TCID50) of PRRSV-containing cells,and no cross-reactivity was observed with other related viruses including porcine circovirus type 2,swine influenza virus,porcine rotavirus and classical swine fever virus.From forty-two field samples,33 samples in the RT-LAMP assay was detected positive,whereas three of which were not detected by RT-PCR.Furthermore,in 33 strains of PRRSV,an identical detection rate was observed with the RT-LAMP assay to what were isolated using porcine alveolar macrophages.These findings demonstrated that the RT-LAMP assay has potential clinical applications for the detection of highly pathogenic PRRSV isolates,especially in developing countries.

Comparison of ligase detection reaction and real-time PCR for detection of low abundant YMDD mutants in patients with chronic hepatitis B

AIM: To compare the ligase detection reaction (LDR) and real-time PCR for detection of low abundant YMDD mutants in patients with chronic hepatitis B infection.METHODS: Mixtures of plasmids and serum samples from 52 chronic hepatitis B patients with low abundant lamivudine-resistant mutations were tested with LDR and real-time PCR. Time required and reagent cost for both assays were evaluated.RESULTS: Real-time PCR detected 100, 50, 10, 1 and 0.1% of YIDD plasmid, whereas LDR detected 100, 50, 10, 1, 0.1, and 0.01% of YIDD plasmid, in mixtures with YMDD plasmid of 106 copies/mL. Among the 52 clinical serum samples, completely concordant results were obtained for all samples by both assays, and 39 YIDD, 9 YVDD, and 4 YIDD/YVDD were detected. Cost and time required for LDR and real-time PCR are 60/80 CNY (8/10.7 US dollars) and 4.5/2.5 h, respectively.CONCLUSION: LDR and real-time PCR are both sensitive and inexpensive methods for monitoring low abundant YMDD mutants during lamivudine therapy in patients with chronic hepatitis B. LDR is more sensitive and less expensive, while real-time PCR is more rapid.

A real-time PCR targeted to the upstream regions of HlyB for specific detection of Edwardsiella tarda

Edwardsiella tarda has become one of the most important emerging pathogens in aquaculture industry. Therefore, a rapid, reproducible, and sensitive method for detection and quantification of this pathogen is needed urgently. To achieve this purpose, we developed a TaqMan-based real-time PCR assay for detection and quantification orE. tarda. The assay targets the hemolysin activator HlyB domain protein of E. tarda. Our optimized TaqMan assay is capable of detecting as little as 40 fg of genomic DNA per reaction. A standard curve was generated from the threshold cycle values （y） against log10 （E. tarda genomic DNA concentration） as x. The intra- and inter-assay coefficient of variation （CV） values were less than 2.06% and 1.05% respectively, indicating that the assay had good reproducibility. This method is highly specific to E. tarda strains, as it shows no cross-reactivity to Edwardsiella ictaluri, a member of the same genus, or to nine other fish-pathogenic bacteria species belonging to three other genera. This sensitive and specific real-time PCR assay provides a valuable tool for diagnostic quantitation of E. tarda in clinical samples.

Development of Nucleic Acid Sequence-Based Amplification Assay for Detection of Macrobrachium rosenbergii Nodavirus

A nucleic acid sequence-based amplification（NASBA）assay was established for the detection of Macrobrachium rosenbergii Nodavirus（MrNV）.The specific primers were designed according to the high conserved region of RNA2 sequence of MrNV.The 224 bp specific amplification product was obtained in positive sample determined with 3%agarose gel electrophoresis,while no product was generated from shrimp infected with other viruses including DNA viruses（IHHNV,WSSV）and RNA viruses（TSV,IMNV,YHV）.The detecting limit of the assay was 8pg nucleic acid,which is more sensitive than that of PCR method.

Development and validation of a TaqMan^(TM) fluorescent quantitative real-time PCR assay for the rapid detection of Edwardsiella tarda

Edwardsiella tarda is one of the most important emerging pathogens in tile global aquaculture industries. As such, an accurate diagnosis and quantitative analytical methods are urgently needed for this bacterium. In this study, primers and a TaqMan probe specific to the conservative sequences of the 16S rRNA gene of E. tarda were designed. The concentration of primers and TaqMan probe were optimized to 200 nmol/L and 120 nmol/L, respectively. The detection sensitivity of the FQ- PCR assay was determined to be as low as five copies of the target sequence per reaction using the pGEM-16S rDNA recombinant plasmid as a template, which was 100 times more sensitive than conventional PCR. A standard curve by plotting the threshold cycle values （y） against the common logarithmic copies （logl0n~ as x; n~ is copy number） of pGEM-16S rDNA was generated. The results of intra- and inter-assay variability tests demonstrate that the established FQ-PCR method was highly reproducible. The assay was specific for E. tarda as it showed that there was no cross-reactivity to eight additional bacterial pathogen strains in aquaculture. Thus, the FQ-PCR assay has the potential for diagnostic purposes and for other applications, especially for the rapid detection and quantification of low-grade E. tarda infections.