Panu Srestasathiern

Learn More
1077-3142/$ see front matter 2011 Elsevier Inc. A doi:10.1016/j.cviu.2011.07.004 ⇑ Corresponding author. E-mail addresses: srestasathiern.1@osu.ed (A. Yilmaz). This paper introduces a new representation for planar objects which is invariant to projective transformation. Proposed representation relies on a new shape basis which we refer to(More)
The paper presents an agricultural monitoring system developed for Thailand. Various species of plants have been directly observed from the agricultural fields which mainly consist of economic crops of Thailand such as rice, cassava, rubber, sugar cane, corn, etc. An equipment used to obtain the data is called field server, which has been installed at the(More)
This paper presents a novel method for extrinsic parameters estimation of a single line scan LiDAR and a camera. Using a checkerboard, the calibration setup is simple and practical. Particularly, the proposed calibration method is based on resolving geometry of the checkerboard that visible to the camera and the LiDAR. The calibration setup geometry is(More)
In this paper, a software program is developed to monitor rice growing stages. Images are required as input data for the software. Using field server equipment, the images are obtained from two rice fields located in Suphanburi and Roi Et provinces, Thailand. Each daily image covers approximately 100 &#x00D7; 100 m<sup>2</sup> recorded by 720 &#x00D7; 480(More)
This paper introduces a method for the recognition planar objects under projective geometry. Our method is based on a similarity measure invariant to projective transform. The proposed similarity measure utilizes the distribution of the projective relations between the conic section pairs, which are estimated from the object’s shape. We conjecture that(More)
Index generation for satellite image is an important task for retrieving satellite image in data warehouse. The goal of index generation is to find a polygon that represents the geographic image area. Using too many vertices for satellite images index can decrease retrieval speed. Therefore, the aim of this research is to develop an algorithm for generating(More)
Object segmentation on remotely-sensed images: aerial (or very high resolution, VHS) images and satellite (or high resolution, HR) images, has been applied to many application domains, especially road extraction in which the segmented objects are served as a mandatory layer in geospatial databases. Several attempts in applying deep convolutional neural(More)
In 2012, GISTDA has launched a sensor network project for monitoring agricultural fields in every region of Thailand. Integration of digital camera and weather sensors, Field Server (FS) is used to collect two types of data; image and weather condition. In this study, time-series images acquired from the rice field are used for computing and understanding(More)