The Implementation of Infrared Image Edge Detection Algorithm Based on CNN on FPGA

Wei, 王巍 Wang; You-wei, 安友伟 An; Zhan, 黄展 Huang; Feng, 丁锋 Ding; Keng, 杨铿 Yang; Cheng-xu, 白晨旭 Bai

doi:10.3788/gzxb20124111.1354

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CNN is a deep learning model, which is successfully used in different fields and has become one of the most important models in deep learning [19][20]. The advantage of CNN lies in its ability to automatically learn features in images, as well as its translation invariance and local connectivity, making it excellent in processing images and other two-dimensional data [21][22].…”

Section: Mca Construction Based On Cnn-lstm Algorithm Fusionmentioning

confidence: 99%

Motion Capture Algorithm for Students' Physical Activity Recognition in Physical Education Curriculum

Lu,

Long

2023

JAIT

View full text Add to dashboard Cite

Physical training learning is one of the important ways to raise the national physical quality and health level. However, there are many problems in traditional physical education, such as the difficulty to identifying the effectiveness of physical education curriculum and low level of repetitive exercise content. In order to solve this problem and improve the curriculum quality of current middle school physical education courses, a motion capture algorithm based on convolutional neural network and long-term memory network is proposed, and a student physical activity capture model is constructed based on the fusion algorithm. In the performance comparison test of the fusion algorithm proposed in this study, the loss value and accuracy of this fusion algorithm are 0.045 and 0.921, respectively, significantly superior to the comparison algorithm. Then in the empirical analysis, the accuracy rate of this motion capture algorithm model proposed in this study for students' walking posture recognition in physical education courses is 91.5%, which is better than the comparative capture method. This motion capture algorithm can accurately capture the physical activities of students in physical education courses, which has practical application significance.

show abstract