SHAPE RECOVERY AND ERROR CORRECTION BASED ON HYPOTHETICAL CONSTRAINTS BY PARALLEL NETWORK FOR ENERGY MINIMIZATION

1994 ◽  
Vol 08 (02) ◽  
pp. 577-593
Author(s):  
KOH KAKUSHO ◽  
SEIICHIRO DAN ◽  
NORIHIRO ABE ◽  
TADAHIRO KITAHASHI
Keyword(s):  
Energy Minimization ◽  
Shape Recovery ◽  
Three Dimensional ◽  
Input Image ◽  
Model Driven ◽  
Optical Projection ◽  
Monocular Image ◽  
Parallel Network ◽  
3D Shape Recovery ◽  
Additional Constraints

Three-dimensional (3D) shape recovery from a monocular image is the inverse process of optical projection and necessitates the use of additional constraints on 3D features of the objects. We have proposed the method of shape recovery based on some hypothetical constraints and its realization by energy minimization using a parallel network. In this paper, we will discuss an extension of our proposal with the aim of correcting noise and errors in an input image through the process of shape recovery. It is hardly possible to extract edges and vertexes free from noise and errors from a real image. For the robustness of the system, we must provide our system with the ability to correct such noise and errors. In this extension, we can also modulate the inclination of the process toward model-driven or data-driven.

scholarly journals Method for Shape Recovery from Monocular Image Considering Shading.

1996 ◽  
Vol 62 (594) ◽  
pp. 635-643
Author(s):  
Takeshi SETA ◽  
Tetsuji SAITO ◽  
Ryoichi TAKAHASHI
Keyword(s):  
Shape Recovery ◽  
Monocular Image

scholarly journals Automatic building detection and 3D shape recovery from single monocular electro-optic imagery

2007 ◽  
Author(s):  
Daniel A. Lavigne ◽  
Parvaneh Saeedi ◽  
Andrew Dlugan ◽  
Norman Goldstein ◽  
Harold Zwick
Keyword(s):  
Shape Recovery ◽  
Building Detection ◽  
3D Shape ◽  
Electro Optic ◽  
3D Shape Recovery

Human Pose Estimation Based on Multi-resolution Feature Parallel Network for Public Security

2021 ◽  
Vol 7 (5) ◽  
pp. 1049-1058
Author(s):  
Xiangru Tao ◽  
Cheng Xu ◽  
Hongzhe Liu ◽  
Zhibin Gu
Keyword(s):  
Artificial Intelligence ◽  
Pose Estimation ◽  
Production Management ◽  
Estimation Method ◽  
Smoking Behavior ◽  
Input Image ◽  
Human Pose Estimation ◽  
Human Posture ◽  
Parallel Network ◽  
Human Pose

Smoking detection is an essential part of safety production management. With the wide application of artificial intelligence technology in all kinds of behavior monitoring applications, the technology of real-time monitoring smoking behavior in production areas based on video is essential. In order to carry out smoking detection, it is necessary to analyze the position of key points and posture of the human body in the input image. Due to the diversity of human pose and the complex background in general scene, the accuracy of human pose estimation is not high. To predict accurate human posture information in complex backgrounds, a deep learning network is needed to obtain the feature information of different scales in the input image. The human pose estimation method based on multi-resolution feature parallel network has two parts. The first is to reduce the loss of semantic information by hole convolution and deconvolution in the part of multi-scale feature fusion. The second is to connect different resolution feature maps in the output part to generate the high-quality heat map. To solve the problem of feature loss of previous serial models, more accurate human pose estimation data can be obtained. Experiments show that the accuracy of the proposed method on the coco test set is significantly higher than that of other advanced methods. Accurate human posture estimation results can be better applied to the field of smoking detection, and the smoking behavior can be detected by artificial intelligence, and the alarm will be automatically triggered when the smoking behavior is found.

scholarly journals Accurate 3D shape recovery of live cattle with three depth cameras

2019 ◽  
Vol 341 ◽  
pp. 012147 ◽  
Author(s):  
A N Ruchay ◽  
K A Dorofeev ◽  
V V Kalschikov ◽  
V I Kolpakov ◽  
K M Dzhulamanov
Keyword(s):  
Shape Recovery ◽  
Depth Cameras ◽  
3D Shape ◽  
3D Shape Recovery
Sign in / Sign up

Export Citation Format

Share Document