With the rapid development of automation technology, unmanned aerial vehicles (UAV) have been widely used to assist troops in long-distance combat missions. However, considering that the UAV needs to keep flying and maintain a certain distance from the target, face detection using UAV usually achieves poor results, which hinders the application of the face recognition technology in UAV systems. We proposed an improved Mish-L2-multitask convolutional neural network (MTCNN) model based on MTCNN model to further improve the accuracy of small-size face detection. First, the maximum pooling layer of the P-Net CNN was removed. Second, a regularization term was added to the crossentropy loss function. Finally, the activation functions exerted in three subneural networks of MTCNN model were replaced with Mish activation functions. The result shows that the proposed Mish-L2-MTCNN model could improve the accuracy of small-size face detection efficiently under the UAV view. Comparing with the result obtained from the original MTCNN model, the accuracy was improved by 3.62%, and the missing rate was evidently reduced. This work can provide methodological guidance for the development of a UAV-based face recognition system in the real airborne scenario and guarantee the validity and efficiency of the system. The study can also guide further research concerning the detection effect in the cases of side face and half mask.
The size of the field of uncertainty (FOU) is an important performance indicator of spatial optical communication systems and is closely related to the line-of-sight (LOS) pointing accuracy. Considering the aircraft-ground laser communication as the research background, the initial pointing angle of the LOS of communication is obtained using the coordinate transformation matrix, and the factors that affect the LOS pointing accuracy error are analyzed. The Kalman filtering technique is introduced into the LOS pointing system to complete system modeling and simulation analysis. The simulation results show that the position, attitude angle, and other data fluctuations of global positioning system/inertial navigation system composite systems can be smoothed effectively by adding a Kalman filter to the LOS pointing system, and the prediction function of the filter can reduce the influence of dynamic lag. The proposed approach improves the accuracy of the LOS pointing, reduces the size of the FOU, and provides reference and guidance for the design of space optical communication systems.
In space optical communications, it is important to obtain the most efficient performance of line of sight (LOS) pointing system. The errors of position (latitude, longitude, and altitude), attitude angles (pitch, yaw, and roll), and installation angle among a different coordinates system are usually ineluctable when assembling and running an aircraft optical communication terminal. These errors would lead to pointing errors and make it difficult for the LOS system to point to its terminal to establish a communication link. The LOS pointing technology of an aircraft optical communication system has been researched using a transformation matrix between the coordinate systems of two aircraft terminals. A method of LOS calibration has been proposed to reduce the pointing error. In a flight test, a successful 144-km link was established between two aircrafts. The position and attitude angles of the aircraft have been obtained to calculate the pointing angle in azimuth and elevation provided by using a double-antenna GPS/INS system. The size of the field of uncertainty (FOU) and the pointing accuracy are analyzed based on error theory, and it has been also measured using an observation camera installed next to the optical LOS. Our results show that the FOU of aircraft optical communications is 10 mrad without a filter, which is the foundation to acquisition strategy and scanning time.
Before the star sensor completes the attitude measurement task with the launch of the spacecraft, it must be calibrated on the ground. In order to meet the requirements of high precision star sensor calibration, according to some specific problems of optical structure of conventional ground calibration equipment in response to large aperture, long focal length and wide spectrum requirements, an off-axis collimator was designed as a collimating optical system, and the image quality was evaluated, and mechanical structure of the off-axis collimator was also designed in detail. Control technology of star brightness was researched and analyzed, and a set of lighting control system is designed. Analysis and test results show that a variety of seven consecutive magnitudes can be simulated by the lighting control system, and the simulated error between neighboring magnitudes is less than 8‰, to meet the current high precision star sensor calibration technical requirements.
Free space laser communication system is composed of laser communication subsystem and Acquisition Pointing and Tracking(APT) subsystem. Laser communication subsystem achieves high rate dates transmission, multiple-axis ATP subsystem accomplish rapid, high acquisition probability and high precision, dynamic tracking. In this paper the structure and principle of typical laser communication system was described briefly at first, and link transmission and system noise characteristic, background light performance, SNR requisition are analyzed about Coarse Pointing Assembly(CPA) links. In order to satisfy demand of acquisition probability, System designation is optimized and important component is selected.
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.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
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.