Abstract
Nowadays, the object detection techniques have been developed rapidly for different applications, ranging from remote sensing to autonomous vehicles. We demonstrate identification of object open angle and direction using machine learning (ML) algorithms based on received light beam’s intensity profiles. Compared with previous optical orbital-angular-momentum (OAM) spectrum system and other related works, our proposed technique only uses a single-shot image, and can efficiently reduce the complexity of hardware implementation. Specifically, we verify the reliability of the simulation results experimentally for 14 open angles and 32 directions. Experimental result shows that convolutional neural network (CNN) outperforms the other traditional ML algorithms, such as decision tree (DT), k-nearest neighbor algorithm (KNN), and support vector machine (SVM). As one of the variant of CNN, MobileNet (MN) has relatively simplified iteration algorithm than VGG-like net. It reduces the computational power, while still maintaining high accuracy for identification issues.
Highlights
When an object is interrogated by a light beam, its characteristics can be identified by the intensity or phase information of the deviation from the original incidental beam [1]
Spatial light modulator (SLM) and power meter are indispensable to acquire the Orbital angular momentum (OAM) spectrum, and the process takes a lot of time and efforts
We propose to use a reference Gaussian beam to simplify the OAM spectrum system for object identification mission using several machine learning (ML) methods
Summary
When an object is interrogated by a light beam, its characteristics can be identified by the intensity or phase information of the deviation from the original incidental beam [1]. For free space object detection issues, proposed systems require additional phase information of the OAM beams, and complex OAM spectrum analysis is usually required [5]–[8]. Comparing with previous OAM spectrum analysis system, our work could reduce the hardware implementation complexity, and potentially serve for remote sensing and real-time object feature detection. CONCEPT In general, Fig. 1(a) depicts the common concept of previously demonstrated object identification techniques using SLMs and power monitor [6] In such systems, complex OAM spectrum analysis is needed to monitor rotation objects by acquiring additional phase information of the interrogated OAM beam. To improve the detection accuracy, some works used the interference of two OAM beams, which is even more complicated [7] Overall, none of these techniques can identify images in bulk. Where (x, y, α, θ ) is a deformation of the Heaviside step function in the polar coordinate system, which is used to emulate the object
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
