• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.897-905
• /
• 2022

Research for video key frame detection has been actively conducted in the fields of computer vision. Recently with the advances on deep learning techniques, performance of key frame detection has been improved, but the various type of video content and complicated background are still a problem for efficient learning. In this paper, we propose a novel method for key frame detection, witch utilizes contrastive learning and memory bank module. The proposed method trains the feature extracting network based on the difference between neighboring frames and frames from separate videos. Founded on the contrastive learning, the method saves and updates key frames in the memory bank, witch efficiently reduce redundancy from the video. Experimental results on video dataset show the effectiveness of the proposed method for key frame detection.

• Computers and Concrete
• /
• v.32 no.6
• /
• pp.615-623
• /
• 2023

Crack detection is an essential method to ensure the safety of dam concrete structures. Low-quality crack images of dam concrete structures limit the application of neural network methods in crack detection. This research proposes a modified attentional mechanism model to reduce the disturbance caused by uneven light, shadow, and water spots in crack images. Also, the focal loss function solves the small ratio of crack information. The dataset collects from the network, laboratory and actual inspection dataset of dam concrete structures. This research proposes a novel method for crack detection of dam concrete structures based on the U-Net neural network, namely AF-UNet. A mutual comparison of OTSU, Canny, region growing, DeepLab V3+, SegFormer, U-Net, and AF-UNet (proposed) verified the detection accuracy. A binocular camera detects cracks in the experimental scene. The smallest measurement width of the system is 0.27 mm. The potential goal is to achieve real-time detection and localization of cracks in dam concrete structures.

• Current Optics and Photonics
• /
• v.1 no.3
• /
• pp.196-202
• /
• 2017

Corona discharge is always a sign of failure processes of high-voltage electrical apparatus, including those utilized in electric railway systems. Solar-blind ultraviolet (UV) cameras are effective tools for corona inspection. In this work, we present an automatic railway corona-discharge detection system based on solar-blind ultraviolet detection. The UV camera, mounted on top of a train, inspects the electrical apparatus, including transmission lines and insulators, along the railway during fast cruising of the train. An algorithm based on the Hough transform is proposed for distinguishing the emitting objects (corona discharge) from the noise. The detection system can report the suspected corona discharge in real time during fast cruises. An experiment was carried out during a routine inspection of railway apparatus in Xinjiang Province, China. Several corona-discharge points were found along the railway. The false-alarm rate was controlled to less than one time per hour during this inspection.

• Parasites, Hosts and Diseases
• /
• v.59 no.2
• /
• pp.167-171
• /
• 2021

Haemonchosis remains a significant problem in small ruminants. In this study, the assay of recombinase polymerase amplification (RPA) combined with the lateral flow strip (LFS-RPA) was established for the rapid detection of Haemonchus contortus in goat feces. The assay used primers and a probe targeting a specific sequence in the ITS-2 gene. We compared the performance of the LFS-RPA assay to a PCR assay. The LFS-RPA had a detection limit of 10 fg DNA, which was 10 times less compared to the lowest detection limit obtained by PCR. Out of 24 goat fecal samples, LFS-RPA assay detected H. contortus DNA with 95.8% sensitivity, compared to PCR, 79.1% sensitivity. LFS-RPA assay did not detect DNA from other related helminth species and demonstrated an adequate tolerance to inhibitors present in the goat feces. Taken together, our results suggest that LFS-RPA assay had a high diagnostic accuracy for the rapid detection of H. contortus and merits further evaluation.

• ETRI Journal
• /
• v.41 no.5
• /
• pp.608-618
• /
• 2019

We propose a general framework for keyed learning, where a secret key is used as an additional input of an adversarial learning system. We also define models and formal challenges for an adversary who knows the learning algorithm and its input data but has no access to the key value. This adversarial learning framework is subsequently applied to a more specific context of anomaly detection, where the secret key finds additional practical uses and guides the entire learning and alarm-generating procedure.

• Journal of Veterinary Science
• /
• v.23 no.5
• /
• pp.32.1-32.11
• /
• 2022

Background: Classical swine fever (CSF) is a severe infectious disease of pigs that causes significant economic losses to the swine industry. Objectives: This study developed a solid-phase blocking enzyme-linked immunosorbent assay (spbELISA) method for the specific detection of antibodies against the CSF virus (CSFV) in porcine serum samples. Methods: A spbELISA method was developed based on the recombinant E2 expressed in Escherichia coli. The specificity of this established spbELISA method was evaluated using reference serum samples positive for antibodies against other common infectious diseases. The stability and sensitivity were evaluated using an accelerated thermostability test. Results: The spbELISA successfully detected the antibody levels in swine vaccinated with the C-strain of CSFV. In addition, the detection ability of spbELISA for CSFV antibodies was compared with that of other commercial ELISA kits and validated using an indirect immunofluorescence assay. The results suggested that the spbELISA provides an alternative, stable, and rapid serological detection method suitable for the large-scale screening of CSFV serum antibodies. Conclusions: The spbELISA has practical applications in assessing the vaccination status of large pig herds.

• Parasites, Hosts and Diseases
• /
• v.60 no.3
• /
• pp.201-205
• /
• 2022

Babesia microti is one of the most common causative agents of babesiosis. A sensitive and rapid detection is necessary for screening potentially infected individuals. In this study, B. microti cytochrome c oxidase subunit I (cox1) was selected as the target gene, multiple primers were designed, and optimized by a recombinase-aided amplification (RAA) assay. The optimal primers and probe were labeled with fluorescein. The sensitivity of fluorescent RAA (fRAA) was evaluated using gradient diluents of the cox1 recombinant plasmid and genomic DNA extracted from whole blood of B. microti infected mice. The specificity of fRAA was assessed by other transfusion transmitted parasites. The analytical sensitivity of the fRAA assay was 10 copies of recombinant plasmid per reaction and 10 fg/µl B. microti genomic DNA. No cross-reaction with any other blood-transmitted parasites was observed. Our results demonstrated that the fRAA assay would be rapid, sensitive, and specific for the detection of B. microti.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1817-1839
• /
• 2024

To solve the problem of insufficient recognition of key nodes in the existing software defect detection process, this paper proposes a key node recognition algorithm based on node expansion degree and improved K-shell position, shortened as SDD_KNR. Firstly, the calculation formula of node expansion degree is designed to improve the degree that can measure the local defect propagation capability of nodes in the software network. Secondly, the concept of improved K-shell position of node is proposed to obtain the improved K-shell position of each node. Finally, the measurement of node defect propagation capability is defined, and the key node recognition algorithm is designed to identify the key function nodes with large defect impact range in the process of software defect detection. Using real software systems such as Nano, Cflow and Tar to design three sets of experiments. The corresponding directed weighted software function invoke networks are built to simulate intentional attack and defect source infection. The proposed SDD_KNR algorithm is compared with the BC algorithm, K-shell algorithm, KNMWSG algorithm and NMNC algorithm. The changing trend of network efficiency and the strength of node propagation force are analyzed to verify the effectiveness of the proposed SDD_KNR algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.1989-2011
• /
• 2019

Vehicle detection based on aerial images is an interesting and challenging research topic. Most of the traditional vehicle detection methods are based on the sliding window search algorithm, but these methods are not sufficient for the extraction of object features, and accompanied with heavy computational costs. Recent studies have shown that convolutional neural network algorithm has made a significant progress in computer vision, especially Faster R-CNN. However, this algorithm mainly detects objects in natural scenes, it is not suitable for detecting small object in aerial view. In this paper, an accurate and effective vehicle detection algorithm based on Faster R-CNN is proposed. Our method fuse a hyperactive feature map network with Eltwise model and Concat model, which is more conducive to the extraction of small object features. Moreover, setting suitable anchor boxes based on the size of the object is used in our model, which also effectively improves the performance of the detection. We evaluate the detection performance of our method on the Munich dataset and our collected dataset, with improvements in accuracy and effectivity compared with other methods. Our model achieves 82.2% in recall rate and 90.2% accuracy rate on Munich dataset, which has increased by 2.5 and 1.3 percentage points respectively over the state-of-the-art methods.

• Smart Structures and Systems
• /
• v.33 no.6
• /
• pp.449-463
• /
• 2024

Automated crack detection is crucial for structural health monitoring and post-earthquake rapid damage detection. However, realizing high precision automatic crack detection in the absence of corresponding manual labeling presents a formidable challenge. This paper presents a novel crack segmentation transfer learning method and a novel crack segmentation model called Swin-CrackFormer. The proposed method facilitates efficient crack image style transfer through a meticulously designed data preprocessing technique, followed by the utilization of a GAN model for image style transfer. Moreover, the proposed Swin-CrackFormer combines the advantages of Transformer and convolution operations to achieve effective local and global feature extraction. To verify the effectiveness of the proposed method, this study validates the proposed method on three unlabeled crack datasets and evaluates the Swin-CrackFormer model on the METU dataset. Experimental results demonstrate that the crack transfer learning method significantly improves the crack segmentation performance on unlabeled crack datasets. Moreover, the Swin-CrackFormer model achieved the best detection result on the METU dataset, surpassing existing crack segmentation models.