In order to solve the problems of serious electromagnetic interference, high cost and long detection time of radar-optoelectronic traditional airport runways Foreign Objects Debris Detection(FOD) system, a novel assistant identification detection architecture was proposed which based on the photoelectric system without radar. Automatic recognition algorithm was present which based on yolov4, it is to improve the efficiency and accuracy of the FOD identification. The manual detection intervention of professional personnel was reduced, and the occurrence of missed detection and false detection was avoided. A novel data augmentation method is proposed to guarantee the performance of the system in the case of a small number of samples. The experimental results show that the system has been strong robustness in different complex scenes, the comprehensive detection rate of FOD is higher than 95%, and the recognition efficiency and accuracy are greatly improved compared with the traditional convolutional neural network(CNN).
The high-energy laser weapon is famous for its unique advantage of speed-of-light response which was considered as an ideal weapon against Unmanned Aerial Vehicle(UAV). However, due to the high energy laser reflection effect, the pixel gray distribution of the frame image will be changed drastically, and therefore the miss distance signal will be interfered strongly when the high energy laser irradiating on the UAV, which seriously affects precision of object tracking in practical application. The traditional “centroid method” or “template matching method” have been difficult to meet the requirements of high precision miss distance which was less than 1pixel(RMS) under the reflected light interfering. In order to developing operational effectiveness of weapon system, G-DS(Gray weighted factor-Diamond Search method) algorithm was proposed which combined with gray weighted factor based on self-learning mechanism. It has been studied for the characteristics of UAV images by field experiment. The results show that G-DS algorithm is low-latency(less than 5ms), which can reduce time complexity compared with the traditional ME algorithm, furthermore, G-DS algorithm was robust based on local motion vector of the block, which can improve ability of target detection and recognition compared with the traditional “centroid method” or “template matching method”. Hence, G-DS algorithm was beneficial to the engineering of high-energy laser weapon.
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.