DEEP LEARNING FOR CODED TARGET DETECTION

Abstract. Coded targets are physical optical markers that can be easily identified in an image. Their detection is a critical step the process of camera calibration. A wide range coded was developed to date. The differ their decoding algorithms. main limitation existing methods low robustness new backgrounds and illumination conditions. Modern deep learning recognition-based algorithms demonstrate exciting progress object performance low-light conditions or environments. This paper focused on development convolutional network for automatic recognition sub-pixel estimation centers.