Target recognition system of dynamic scene based on artificial intelligence vision

Yang, Jianzhong; Li, Xianyang; Jiang, Yu; Qiu, Guihua; Buckdahn, S.

doi:10.3233/jifs-169757

Cited by 4 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this is only a starting point of the development lineage of modern visual design. With the rise of new technologies such as artificial intelligence, virtual reality, and augmented reality, visual design has further expanded the boundaries of innovation [10][11][12][13]. Artificial intelligence has injected intelligent elements into the design field, making design no longer just a static expression but with a wider range of smart applications [14][15][16].…”

Section: Introductionmentioning

confidence: 99%

Research on Image Recognition and Visual Design Based on Artificial Intelligence

Zhang

2024

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

In this paper, the color image is converted to a grayscale image in the image recognition preprocessing stage to accelerate the image recognition processing, and then the image contrast is enhanced by grayscale stretching to compute the grayscale layer covariance matrix and image texture features. Multi-step Markov clustering method is proposed to optimize the GCN, and the instance normalization layer and batch normalization layer are added to strengthen the source domain representation ability of the GCN to form a cross-domain image recognition algorithm based on a pairwise generalization network. Elaborate the visual design path of image information by artificial intelligence image recognition and image processing technology, introduce image recognition technology into the field of visual design, establish a visual design partition model, and completely extract the local feature information of computer image graphics. Use the dataset to evaluate the performance of pairwise generalization networks, and conduct simulation experiments to analyze the visual expression effects of visual design. The PGN-RM method, with the addition of maximum mean distance, instance normalization, and batch normalization, is able to achieve a performance average of 91.843. The peak signal-to-noise ratio of the actual effect image of the visual design of the product packaging is maintained in the range of [95.0312, 97.0032], which is an excellent visual design effect. Visual design that utilizes artificial intelligence graphic recognition technology can express design ideas more deeply and enhance the visual design’s attractiveness.

show abstract

Section: Introductionmentioning

confidence: 99%

Research on Image Recognition and Visual Design Based on Artificial Intelligence

Zhang

2024

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

show abstract

“…In recent years, as the most mainstream algorithms of artificial intelligence, deep learning algorithms have achieved excellent results in intelligent applications such as target recognition, speech recognition, and machine translation, etc. [6][7][8]. At the same time, deep learning has also received more and more attention in the field of fault identification.…”

Section: Introductionmentioning

confidence: 99%

“…To facilitate the training of the network, each signal is standardized and the formula is shown below. * = ̅ , (6) where ̅ and σ represent the mean and standard deviation of the original signal, respectively. Further, data augmentation technology is applied to augment the original data during the preprocessing stage.…”

Section: Dataset Introductionmentioning

confidence: 99%

A Novel Capsule Network Based on Wide Convolution and Multi-Scale Convolution for Fault Diagnosis

Ning

Feng

2020

Applied Sciences

View full text Add to dashboard Cite

In the prognostics health management (PHM) of rotating machinery, the accurate identification of bearing fault is critical. In recent years, various deep learning methods can well identify bearing fault based on monitoring data. However, facing changing operating conditions and noise pollution, the accuracy of these algorithms decreases significantly, which makes the algorithms difficult in practical applications. To solve this problem, a novel capsule network based on wide convolution and multi-scale convolution (WMSCCN) is proposed for fault diagnosis. The proposed WMSCCN algorithm takes one-dimensional vibration signal as an input and no additional manual processing is required. In addition, the adaptive batch normalization (AdaBN) algorithm is introduced to further enhance the adaptability of WMSCCN under noise pollution and load changes. On generalization experiments under different loads, the proposed WMSCCN and WMSCCN-AdaBN algorithms achieve average accuracy rates of 96.44% and 97.44%, respectively, which is superior to other advanced algorithms. In the noise resistance experiment, the proposed WMSCCN-AdaBN can maintain a 92.3% diagnostic accuracy in a strong noise environment with a signal to noise ratio (SNR) = −4 dB, showing a very strong anti-noise ability. When the SNR exceeds 4 dB, the accuracy reaches 100%, indicating that the proposed algorithm has a very good accuracy at low noise levels. Two experiments have effectively verified the validity and generalizability of the proposed model.

show abstract

Innovation Education in Universities from the Perspective of Artificial Intelligence

Zhou

2021

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Target recognition system of dynamic scene based on artificial intelligence vision

Cited by 4 publications

References 11 publications

Research on Image Recognition and Visual Design Based on Artificial Intelligence

Research on Image Recognition and Visual Design Based on Artificial Intelligence

A Novel Capsule Network Based on Wide Convolution and Multi-Scale Convolution for Fault Diagnosis

Innovation Education in Universities from the Perspective of Artificial Intelligence

Contact Info

Product

Resources

About