With a piece of far-field diffraction image, the purpose of reconstruction an object can be achieved by the Coherent Diffraction Imaging (CDI) method under some certain conditions. Practically, the far-field diffraction images captured by the optical system are not always matched well with the phase retrieval algorithms, which frequently leads to lower resolution of the reconstructed object image. However, we find that the gray distortion of the power spectrum has a great impact on the object reconstruction, and even a good phase retrieve algorithm can not reconstruct the object. Based on experiment and simulation results, we find that the spatial power spectrum pattern gray-level distortion has much influence on the CDI reconstruction, and the acquired pattern distortion rate should be less than 0.1. When the gray-level distortion is less than 0.1, clear object can be reconstructed in fewer iterations. The reconstruction algorithm is fault-tolerant to the distortion of power spectrum. The convergence speed of the algorithm can be accelerated through giving an upper bound of gray-level distortion. This result provides a reference for other researches in CDI to avoid the convergence stagnation caused by the distortion of spatial power spectrum collected by experiments.
Person detection, tracking and following is a key enabling technology for mobile robots in many human–robot interaction applications. In this article, we present a system which is composed of visual human detection, video tracking and following. The detection is based on YOLO(You only look once), which applies a single convolution neural network(CNN) to the full image, thus can predict bounding boxes and class probabilities directly in one evaluation. Then the bounding box provides initial person position in image to initialize and train the KCF(Kernelized Correlation Filter), which is a video tracker based on discriminative classifier. At last, by using a stereo 3D sparse reconstruction algorithm, not only the position of the person in the scene is determined, but also it can elegantly solve the problem of scale ambiguity in the video tracker. Extensive experiments are conducted to demonstrate the effectiveness and robustness of our human detection and tracking system.
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.