Jeehoon Park

Vision-based AGV Parking System

This paper proposes an efficient method to locate the automated guided vehicle (AGV) into a specific parking position using artificial visual landmark and vision-based algorithm. The landmark has comer features and a HSI color arrangement for robustness against illuminant variation. The landmark is attached to left of a parking spot under a crane. For parking, an AGV detects the landmark with CCD camera fixed to the AGV using Harris comer detector and matching descriptors of the comer features. After detecting the landmark, the AGV tracks the landmark using pyramidal Lucas-Kanade feature tracker and a refinement process. Then, the AGV decreases its speed and aligns its longitudinal position with the center of the landmark. The experiments showed the AGV parked accurately at the parking spot with small standard deviation of error under bright illumination and dark illumination.

AGV parking system using artificial visual landmark

This paper proposes an efficient method to locate the automated guided vehicle (AGV) into the parking position using artificial visual landmark. For automated transshipment system in container terminals, the port AGV is used to transport containers autonomously and efficiently. To co-operate with the transfer crane, accurate guiding and positioning system is required. Using computer vision algorithms that detect and track the object from the video streams, we extract the exact position and relative distance with respect to the parking position. The artificial landmark is designed for effective detection based on corner feature and color information. After detection phase finds the position of the landmark in the captured image, tracking phase follows the trace of the landmark in the successive image sequences. Tracking phase consists of two stages, estimation and refinement steps. Optical flow vector around the detected point in the current image is calculated by pyramidal Lucas-Kanade feature tracker, and it is used to estimate the current position of the landmark. Then, the refinement step uses some features of the landmark as references to correct the estimated position of the object. Whole process is performed in HSI color space so that the system can be robust to illuminant variation. Experiments show reliable results of parking movement of the AGV. Our approach is simple, effective and robust.

ANOTHER LOOK AT GROSS–STARK UNITS OVER THE NUMBER FIELD ℚ

We provide another description of the Gross–Stark units over the rational field ℚ (studied in [B. Gross, p-Adic L-series at s = 0, J. Fac. Sci. Univ. Tokyo28(3) (1981) 979–994]) which is essentially a Gauss sum, using a p-adic multiplicative integral of the p-adic Kubota–Leopoldt distribution, and give a simplified proof of the Ferrero–Greenberg theorem (see [B. Ferrero and R. Greenberg, On the behavior of p-adic L-functions at s = 0, Invent. Math.50(1) (1978/79) 91–102]) for p-adic Hurwitz zeta functions. This is a precise analog for ℚ of Darmon–Dasguptas work on elliptic units for real quadratic fields (see [H. Darmon and S. Dasgupta, Elliptic units for real quadratic fields, Ann. of Math. (2)163(1) (2006) 301–346]).

AGV parking system based on tracking landmark

This paper presents an efficient method that locates the automated guided vehicle (AGV) into a specific position using vision-based system. For an automated transshipment system in the container terminal, it is necessary for the AGV to recognize the current position of the transfer crane, so that the port AGV locates itself into the working area of the crane. Using an artificially designed landmark attached on the crane, the vehicle detects and tracks the position of the landmark from the video stream through CCD camera fixed to the vehicle. The AGV calculates its position from the position of landmark in the image and control the velocity to align with the crane. The detection method is based on the local features of the landmark such as edges, corners, and color information. After detecting the landmark the vehicle tracks the trace of the target using Condensation algorithm and refinement stage. Detecting and tracking steps are performed in HSI color space to reduce the effect of illumination. Experiment shows reasonable results.