The Polynomial Texture Map framework (PTM) extends the simple model of image formation from the Lambertian variant of Photometric Stereo (PST) to more general reflectances and to more complex-shaped surfaces. It forms an alternative method for apprehending object colour, albedo, and surface normals. Here we consider solving such a model in a robust version, not to date attempted for PTM, with the upshot that both shadows and specularities are identified automatically without the need for any thresholds. Instead of the linear model used in few-source PST for Lambertian surfaces, PTM adopts a higher degree polynomial model. PTM has two aims: interpolation of images for new lighting directions, and recovery of surface properties. Here we show that a robust approach is a good deal more accurate in recovering surface properties. For new-lighting interpolation, we demonstrate that a simple radial basis function interpolation can accurately interpolate specularities as well as attached and cast shadows even with a medium-sized image set, with no need for reflectance sharing across pixels or extremely large numbers of interpolation coefficients.

Polynomial Texture Maps (PTM) [SIGGRAPH 2001] form an alternative method for apprehending surface colour and albedo that extends a simple model of image formation from the Lambertian variant of Photometric Stereo (PST) to more general reflectances. Here we consider solving such a model in a robust version, not to date attempted for PTM. But the main upshot of utilizing robust regression is in the identification of both shadows and specularities automatically, without the need for any thresholds, in a tripartite set of weights for pixels that are labelled as matte, shadow, or specularity. Original images are captured using a hemispherical set of lights, and pixel values across the lighting directions are then labelled as inliers, or outliers of two types. A per-pixel robust regression on luminance is carried out using Least Median of Squares, and automaticallyidentified outlier pixels are labelled as shadows if they are darker than matte and correspondingly, specular outliers are too bright. Inlier identification generates correct values for chromaticity and for surface albedo and thus matte luminance and colour. Then a robust version of PST, using only PTM inliers, improves estimates of normal vectors and albedo recovered. With specular pixel values over the lights in hand we model specularity using a radial basis function (RBF) regression, and non-specular pixel departures from matte using a second RBF set. Then for a new lighting direction, we can readily interpolate both specular content as well as shadows.

Team cognition is an important factor in evaluating and determining team performance. Forming a team with good shared cognition is even more crucial for laparoscopic surgery applications. In this study, we analyzed the eye tracking data of two surgeons during a laparoscopic simulation operation, then performed Cross Recurrence Analysis (CRA) on the recorded data to study the delay behaviour for good performer and poor performer teams. Dual eye tracking data for twenty two dyad teams were recorded during a laparoscopic task and then the teams were divided into good performer and poor performer teams based on the task times. Eventually we studied the delay between two team members for good and poor performer teams. The results indicated that the good performer teams show a smaller delay comparing to poor performer teams. This study is compatible with gaze overlap analysis between team members and therefore it is a good evidence of shared cognition between team members.

No abstract

The task of recognising an object and estimating its 6d pose in a scene has received considerable attention in recent years. The accessibility and low-cost of consumer RGB-D cameras, make object recognition and pose estimation feasible even for small industrial businesses. An example is the industrial assembly line, where a robotic arm should pick a small, textureless and mostly homogeneous object and place it in a designated location. Despite all the recent advancements of object recognition and pose estimation techniques in natural scenes, the problem remains challenging for industrial parts. In this paper, we present a framework to simultaneously recognise the object’s class and estimate its 6d pose from RGB-D data. The proposed model adapts a global approach, where an object and the Region of Interest (ROI) are first recognised from RGB images. The object’s pose is then estimated from the corresponding depth information. We train various classifiers based on extracted Histogram of Oriented Gradient (HOG) features to detect and recognize the objects. We then perform template matching on the point cloud based on surface normal and Fast Point Feature Histograms (FPFH) to estimate the pose of the object. Experimental results show that our system is quite efficient, accurate and robust to illumination and background changes, even for the challenging objects of Tless dataset. 6d pose estimation; 3d object recognition; textureless objects; homogeneous objects