A 360° continuous detection system based on visual elimination of image rotation was designed to meet the requirement of high precision and full working interval continuous detection of the image tile index of a vehicle's commander panoramic sight. The system will drive the rotation value and visual measurement value for comparison measurement. The high precision motor and encoder output the angle and the PID algorithm is used to control the motor rotation speed to ensure the accurate positioning of the detected angle; Combined with sub-image processing and visual measurement , 360° continuous detection of image elimination rotation is realized. The experimental results show that the system can satisfy the 360° continuous detection of the image tile index of a vehicle's commander panoramic sight, eliminate the problem of extreme value out-of-tolerance, and improve the image stabilization accuracy of the sight system of a vehicle's commander panoramic sight.
On the research of traditional diopter measuring method with dioptrometer, a new approach for automatic testing of diopter is proposed. The new way took place of hand operation of dioptrometer by high resolution camera and improved mountain climbing algorithm of rapid autofocus combining rough and fine adjustment. It can improve testing efficiency and accuracy from ±0.2 diopters to ±0.008 diopters which can meet the need of accuracy and efficiency for flow line of production.
The computing power of the image processor of the handheld viewing system is usually low, which brings some difficulties to the image processing. In this article, an infrared image target detection system is built with the RV1126 development board as the core. Compared with visible light, infrared image has the characteristics of low resolution and blurred details of small targets. According to the above characteristics, conventional image processing algorithms are difficult to deploy to embedded infrared image target detection systems. Therefore, this article uses SSD neural network to train the infrared target detection model, and converts the model into an infrared target detection model that can be deployed on RV1126 development board through Rknn. The actual test shows the SSD target detection network can achieve intelligent target detection and recognition on the RV1126-based embedded platform in the infrared image target detection.
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.