Learn More
Portable devices for first-person camera views will play a central role in future interactive systems. One necessary step for feasible human-computer guided activities is gesture recognition, preceded by a reliable hand segmentation from egocentric vision. In this work we provide a novel hand segmentation algorithm based on Random Forest superpixel(More)
By means of catecholamine fluorescence histochemistry in combination with quantitative microfluorimetry the effects of luteinizing hormone-releasing hormone (LH-RH) has been studied on the amine levels and turnover in discrete catecholamine (CA) nerve terminal populations in the hypothalamus of the hypophysectomized male rat. LH-RH highly selectively(More)
By means of receptor autoradiography using the dopamine (DA) receptor radioligands [3H]cis(z)-flupenthixol ([3H]FLU), [3H]spiperone, [3H]N-propyl-norapomorphine and amino-6,7-dihydroxy-1,2,3,4-tetrahydronaphtalene-2-(5,8[3H]) in combination with a microdensitometrical analysis indications have been obtained for the existence of a DA receptor of the D-1 type(More)
Three-dimensional object recognition on range data and 3D point clouds is becoming more important nowadays. Since many real objects have a shape that could be approximated by simple primitives, robust pattern recognition can be used to search for primitive models. For example, the Hough transform is a well-known technique which is largely adopted in 2D(More)
This paper presents the development of the lightweight hydraulic quadruped robot MiniHyQ. To the authors' best knowledge, MiniHyQ is the lightest and smallest hydraulic quadruped robot that has been built so far. MiniHyQ is a fully torque controlled robot. It has reconfigurable leg configurations. It has wide joint range of motion and an onboard compact(More)
We present a real-time SLAM system that combines an improved version of the Iterative Closest Point (ICP) and inertial dead reckoning to localize our dynamic quadrupedal machine in a local map. Despite the strong and fast motions induced by our 80 kg hydraulic legged robot, the SLAM system is robust enough to keep the position error below 5% within the(More)
Agile robot locomotion on rough terrain is highly dependent on the ability to perceive the environment. In this paper, we show how the interaction between a reactive control framework and an online mapping system can significantly improve the trotting performance on irregular terrain. In particular, this new locomotion controller increases the stability of(More)
  • 1