Ms. Haili Wang Profile

Haili Wang

SPIE Involvement:

Author

Publications (2)

This will count as one of your downloads.

You will have access to both the presentation and article (if available).

DOWNLOAD NOW

This content is available for download via your institution's subscription. To access this item, please sign in to your personal account.

Email or Username Forgot your username?

Password Forgot your password?

Show

Keep me signed in

No SPIE account? Create an account

Proceedings Article | 15 January 2025 Open Access

Image harmonization algorithm based on improved BargainNet

Yujie Feng, Haili Wang, Liang Zhang

Proceedings Volume 13513, 1351338 (2025) https://doi.org/10.1117/12.3047935

KEYWORDS: Convolution, Image compression, Feature extraction, Structural design, Signal to noise ratio, Network architectures, Mathematical optimization, Ablation

Read Abstract +

Aiming at the problem of poor harmonization effect of images with excessive foreground background differences, an improved image harmonization method based on BargainNet model is designed. Firstly, the original structure of the generator is designed as a secondary sampling structure, and the secondary feature extraction is performed on the upsampled feature map, which optimizes the harmonization effect of the image with too large foreground background difference. Secondly, the feature pyramid network structure is combined with the jump connection structure of the generator, and the jump connection pyramid structure is designed to fuse the features of different scales. Finally, considering that the jump-connected pyramid structure increases the number of parameters of the network, the RSGC (Residual Structure with Ghost Convolution) module is designed to optimize the network's ability to express features and effectively reduce the number of parameters of the network. The optimized model is validated on the HVIDIT image harmonization dataset, and the mean square error (MSE) of the harmonized image generated by the improved network reaches 28.64, and the peak signal to noise ratio (PSNR) reaches 37.41dB, which significantly improves the harmonization effect.

DOWNLOAD PAPER

Proceedings Article | 19 June 2017 Paper

Action description using point clouds

Wenping Liu, Yongfeng Jiang, Haili Wang, Liang Zhang

Proceedings Volume 10443, 104430X (2017) https://doi.org/10.1117/12.2280342

KEYWORDS: Feature extraction, Cameras, Image acquisition, Video, RGB color model, Signal processing, Information security, 3D acquisition

Read Abstract +

An action description method named as Motion History Point Cloud (MHPC) is proposed in this paper. MHPC compresses an action into a three-dimensional point cloud in which depth information is required. In MHPC, the spatial coordinate channels are used to record the motion foreground, and the color channels are used to record the temporal variation. Due to containing depth information, MHPC can depict an action more meticulous than Motion History Image (MHI). MHPC can serve as a pre-processed input for various classification methods, such as Bag of Words and Deep Learning. An action recognition scheme is provided as an application example of MHPC. In this scheme, Harris3D detector and Fast Point Feature Histogram (FPFH) are used to extract and describe features from MHPC. Then, Bag of Words and multiple classification Support Vector Machine (SVM) are used to do action recognition. The experiments show that rich features can be extracted from MHPC to support the subsequent action recognition even after downsampling. The feasibility and effectiveness of MHPC are also verified by comparing the above scheme with two similar methods.

My Library

You currently do not have any folders to save your paper to! Create a new folder below.

Folder Name

Folder Description

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks. You are receiving this notice because your organization may not have SPIE eBooks access.*

*Shibboleth/Open Athens users─please sign in to access your institution's subscriptions.

To obtain this item, you may purchase the complete book in print or electronic format on SPIE.org.

ORGANIZATIONAL
Sign in with credentials provided by your organization.

Organizational Username

Organizational Password

Show/Hide Password

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members:

Non-members: ADD TO CART

Keywords/Phrases

Search In:

Publication Years