Animation Scene Object Recognition and Modeling Based on Computer Vision Technology

被引：0

作者：

Shen Z. ^{[1
]}

Zhang W. ^{[2
]}

机构：

[1] Art College, Chongqing Technology and Business University, Chongqing

[2] School of Animation And Digital Film, Chongqing Engineering Institute, Chongqing

来源：

Computer-Aided Design and Applications | 2024年 / 21卷 / S15期

关键词：

Animation Scenes; CAD Modeling; Computer Vision Technology; Deep Learning; Object Recognition;

D O I：

10.14733/cadaps.2024.S15.16-34

中图分类号：

学科分类号：

摘要：

Based on computer vision technology, this article proposes a computer-aided design (CAD) modeling method for animation scene objects based on recognition. It conducts a series of experiments to verify the effectiveness and practicality of this method. This method aims to automatically and accurately recognize objects from animation scenes and generate corresponding CAD models using object recognition algorithms and CAD modeling techniques. To achieve this goal, the article first uses the Convolutional Neural Network (CNN) algorithm for object recognition and obtains the boundary information of the object. Then, CAD modeling uses boundary information based on recognition to generate CAD models similar to real objects. The performance of the system was assessed through a series of experiments. The results show that this method has a high accuracy in object recognition, with an essential accuracy of over 93%, and can accurately extract boundary information of objects. The gap between the generated CAD model and the real object is small in CAD modeling, and the modeling accuracy is high. Moreover, the system's running time is within an acceptable range, proving the system's efficiency. This method can provide animators with an automated CAD modeling tool, reducing the time and effort costs of manual modeling and improving modeling accuracy. © 2024 U-turn Press LLC.

引用

页码：16 / 34

页数：18

共 20 条

[1] Baimukashev D., Zhilisbayev A., Kuzdeuov A., Oleinikov A., Fadeyev D., Makhataeva Z., Varol H.-A., Deep learning-based object recognition using physically-realistic synthetic depth scenes, Machine Learning and Knowledge Extraction, 1, 3, pp. 883-903, (2019)
[2] Barreto J.-C.-D.-L., Cardoso A., Lamounier J.-E.-A., Silva P.-C., Silva A.-C., Designing virtual reality environments through an authoring system based on CAD floor plans: A methodology and case study applied to electric power substations for supervision, Energies, 14, 21, (2021)
[3] Gong M., Analysis of architectural decoration esthetics based on VR technology and machine vision, Soft Computing, 25, 18, pp. 12477-12489, (2021)
[4] Guo Q., Ma G., Exploration of human-computer interaction system for product design in virtual reality environment based on computer-aided technology, Computer-Aided Design & Applications, 19, pp. 87-98, (2022)
[5] Hercog D., Bencak P., Vincetic U., Lerher T., Product assembly assistance system based on pick-to-light and computer vision technology, Sensors, 22, 24, (2022)
[6] Jing Y., Song Y., Application of 3D reality technology combined with CAD in animation modeling design, Computer-Aided Design and Applications, 18, pp. 164-175, (2020)
[7] Kapusi T.-P., Erdei T.-I., Husi G., Hajdu A., Application of deep learning in the deployment of an industrial scara machine for real-time object detection, Robotics, 11, 4, (2022)
[8] Li L., Application of cubic b-spline curve in computer-aided animation design, Computer-Aided Design and Applications, 18, pp. 43-52, (2020)
[9] Li L., Li T., Animation of virtual medical system under the background of virtual reality technology, Computational Intelligence, 38, 1, pp. 88-105, (2022)
[10] Li X., Cao R., Feng Y., Chen K., Yang B., Fu C.-W., Heng P.-A., A sim-to-real object recognition and localization framework for industrial robotic bin picking, IEEE Robotics and Automation Letters, 7, 2, pp. 3961-3968, (2022)

← 1 2 →