Mr. Hao Wu Profile

Hao Wu

at State Key Lab. of Complex Electromagnetic Environment Effects on Electronics and Information System

SPIE Involvement:

Author

Publications (3)

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 | 23 July 2022 Paper

Remote sensing image target detection based on YOLOv5 network

Hao Wu, Li Shui, Chong Zhang, Bingfa Miao

Proceedings Volume 12277, 1227711 (2022) https://doi.org/10.1117/12.2617304

KEYWORDS: Target recognition, Target detection, Detection and tracking algorithms, Remote sensing, Neck, Convolution, Visualization, Unmanned aerial vehicles, Image processing, Image enhancement

Read Abstract +

An improved target recognition algorithm based on YOLOv5 network was proposed to solve the problem of low accuracy of target recognition due to the complex background of remote sensing image, small difference between target classes and multiple and dense targets which in the target detection task of optical remote sensing image taken from the overhead angle.The algorithm improves the target recognition by changing the visual activation function, loss function and improving the structure of feature pyramid network (FPN). Firstly, the original YOLOv5 network structure is analyzed that the key technologies of input, Backbone, neck and output are introduced. The LeakyReLU activation function has been changed to FReLU which has the ability to adaptively obtain the local context of the image and is simple in form that improving the spatial sensitivity in the activation function. PIOU loss function is used to replace common CIOU and GIOU that rotation parameters are added to better detect rotating and dense objects. Feature Pyramid Grids (FPG) are introduced that the Feature scale space is represented as a regular grid with parallel bottom-up paths which fused by multi-directional horizontal connections. The single path feature pyramid network is improved by significantly improving its performance at similar computational cost. Experimental results show that under the same training conditions, compared with the original YOLOv5 network, the improved YOLOv5 network converges the training results faster, and the average recognition rate of the training model increases by 5%. Through the test set verification that the recognition accuracy of all kinds of images has been improved which the average accuracy has reached 0.702, 7% higher than the original YOLOv5 network.

Proceedings Article | 18 December 2019 Paper

Research on dynamic-angle measurement method for machine vision

Hao Wu, Wensheng Li, Shuaitao Han

Proceedings Volume 11341, 113410B (2019) https://doi.org/10.1117/12.2540332

KEYWORDS: Artillery, Mathematical modeling, Machine vision, Ranging, Analytical research, Error analysis, Measurement devices, Optical tracking, Distance measurement, Detection and tracking algorithms

Read Abstract +

On the basis of analyzing the research status of spatial angle measurement methods and devices at home and abroad, a new spatial angle measurement method based on photoelectric tracking platform is proposed. The photoelectric tracking platform is installed on the target through rigid connection of mechanical structure to establish the spatial coordinate relationship between the target and the photoelectric tracking platform, and between the photoelectric tracking platform and the earth. When the spatial angle of the target changes, the tracking angle of the cooperative target plate by the photoelectric tracking platform can be used to calculate the spatial angle change of the measured target through the spatial coordinate transformation relationship between the platform and the target. Taking the measurement accuracy of artillery adjustment as an example that the spatial coordinate system is established. The mathematical model of spatial rotation angle of the measurement method is established by utilizing the coordinate transformation relationship between the measured object, cooperative target and photoelectric tracking platform. The photoelectric tracking platform, miniaturized high-precision turntable and cooperative target plate are used to construct the simulation experiment of the measurement of the spatial rotation angle of the artillery barrel. The mathematical model of spatial rotation angle is used to calculate the experimental results and analyze the experimental errors. It is proved that the mathematical model of spatial rotation angle for this method which is effective for measuring the spatial rotation angle such as the accuracy of artillery adjusting and so on.

Proceedings Article | 18 January 2019 Paper

Image tracking technology for dynamic angle measurement of machine vision

Hao Wu, Yong Zhang, Weiming Wang, Minghua Si, Xin Li

Proceedings Volume 10839, 1083903 (2019) https://doi.org/10.1117/12.2504771

KEYWORDS: Servomechanisms, Detection and tracking algorithms, Image processing, Machine vision, Target detection, Cameras, Distance measurement

Read Abstract +

In order to realize high-precision measurement of spatial dynamic angle, a spatial dynamic angle measurement method based on machine vision is proposed. A high-precision two-axis servo system is installed onto the measured target. When the spatial angle of the measured target is changed, the servo system outputs the pitch angle and the azimuth angle by identifying and tracking the cooperative target。According to the spatial coordinate system transformation，the angle change value of the measured target can be obtained. The measurement accuracy of the spatial angle will be influenced by the accuracy of the tracking cooperative target with the servo system. A cross-patterned target board is designed based on the measured distance and the imaging system. Several major algorithms of detection are summarized. Their merits and demerits are analyzed by identifying and locating the center of captured image. The captured images are compared by the servo system controlled with these algorithms. The measurement results are solved by spatial coordinate transformation. According to the experimental results, a fast detection algorithm of target center in the real-time image processing is selected. High accuracy and good real-time performance of this method in processing the target image is demonstrated by calculating and comparing the results of each image processing algorithm, which satisfies the measured requirement of space dynamic angle.

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