Subpixel Analysis of MODIS Imagery Time Series using Transfer Learning and Relative Calibration

Transfer learning reuses a pre-trained model on a new related problem, which can be useful for monitoring large areas such as the Amazon biome. A given object must have similar spectral characteristics in the data used for this type of analysis, which can be achieved using relative calibration techniques. In this article, we present a relative calibration process in multitemporal images and evaluate its impacts on a subpixel classification process. MODIS images from the Amazon region, collected between 2013 and 2017, were relatively calibrated using a 2012 image as reference and classified by transfer learning. Classifications of calibrated and uncalibrated images were compared with data from the PRODES project, focusing on forest areas. A great variation was observed in the spectral responses of the forest class, even in images of proximate dates and from the same sensor. These variations significantly impacted the land cover classifications in the subpixel, with cases of agreement between the uncalibrated data maps and PRODES of 0%. For calibrated data, the agreement values ​​were greater than 70%. The results indicate that the method used, although quite simple, is adequate and necessary for the subpixel classification of MODIS images by transfer learning.

MEASUREMENT ACCURACY ON 3D POINT CLOUD GENERATED USING MULTISPECTRAL IMAGERY BY DIFFERENT CALIBRATION METHODS

The state-of-the-art lightweight multispectral cameras are widely used for low altitude remote sensing, also can be exploited as a tool for close-range photogrammetry application. The acquired imagery can be used for generating the 3D model using Structure-from-Motion/ Multi-view Stereo (SfM/MVS) processing software. In photogrammetry, camera calibration is an essential step for accurate measurement. The parameter of the camera system can be estimated using photogrammetric self-calibration bundle-adjustment, or by automatic and straightforward calibration procedure developed by computer vision (CV) community. When using SfM/MVS photogrammetry software, the pre-calibration value is not required, as the algorithm calculates the parameter as a part of point cloud construction process. Nevertheless, processing with the uncalibrated image is only suitable when no metric accuracy required in the modelling project. This paper aims to evaluate the measurement accuracy on generated 3D point cloud based on different estimated parameter method. The evaluation of measurement accuracy started by estimates the camera’s interior parameter using two different approaches; photogrammetric self-calibration bundle-adjustment and computer vision calibration. The estimated parameter from both methods then imported into commercial SfM/MVS software to construct the 3D point cloud. The point cloud also generated using uncalibrated images and used for measurement accuracy assessment. All parameters applied to the same datasets involved three different check-fields. Two accuracy assessments were performed by comparing the check-points and check-distance extracted with the total station measurement. As a result, the point cloud generated using photogrammetric approach provides the most accurate result on both assessments. While the automatic on-the-job self-calibration shows inconsistent results.

Three-Dimensional Face Reconstruction Using Multi-View-Based Bilinear Model

Face reconstruction is a popular topic in 3D vision system. However, traditional methods often depend on monocular cues, which contain few feature pixels and only use their location information while ignoring a lot of textural information. Furthermore, they are affected by the accuracy of the feature extraction method and occlusion. Here, we propose a novel facial reconstruction framework that accurately extracts the 3D shapes and poses of faces from images captured at multi-views. It extends the traditional method using the monocular bilinear model to the multi-view-based bilinear model by incorporating the feature prior constraint and the texture constraint, which are learned from multi-view images. The feature prior constraint is used as a shape prior to allowing us to estimate accurate 3D facial contours. Furthermore, the texture constraint extracts a high-precision 3D facial shape where traditional methods fail because of their limited number of feature points or the mostly texture-less and texture-repetitive nature of the input images. Meanwhile, it fully explores the implied 3D information of the multi-view images, which also enhances the robustness of the results. Additionally, the proposed method uses only two or more uncalibrated images with an arbitrary baseline, estimating calibration and shape simultaneously. A comparison with the state-of-the-art monocular bilinear model-based method shows that the proposed method has a significantly higher level of accuracy.