Related papers: Efficient Selection of Disambiguating Actions for …
Active perception describes a broad class of techniques that couple planning and perception systems to move the robot in a way to give the robot more information about the environment. In most robotic systems, perception is typically…
Active learning aims to reduce the high labeling cost involved in training machine learning models on large datasets by efficiently labeling only the most informative samples. Recently, deep active learning has shown success on various…
Semantic tool segmentation in surgical videos is important for surgical scene understanding and computer-assisted interventions as well as for the development of robotic automation. The problem is challenging because different illumination…
We consider the problem of sensor selection for designing observer and filter for continuous linear time invariant systems such that the sensor precisions are minimized, and the estimation errors are bounded by the prescribed…
Recent methods in stereo matching have continuously improved the accuracy using deep models. This gain, however, is attained with a high increase in computation cost, such that the network may not fit even on a moderate GPU. This issue…
Binocular stereo vision is an important branch of machine vision, which imitates the human eye and matches the left and right images captured by the camera based on epipolar constraints. The matched disparity map can be calculated according…
Sensor setups consisting of a combination of 3D range scanner lasers and stereo vision systems are becoming a popular choice for on-board perception systems in vehicles; however, the combined use of both sources of information implies a…
Identification and localization of sounds are both integral parts of computational auditory scene analysis. Although each can be solved separately, the goal of forming coherent auditory objects and achieving a comprehensive spatial scene…
Existing deep active learning algorithms achieve impressive sampling efficiency on natural language processing tasks. However, they exhibit several weaknesses in practice, including (a) inability to use uncertainty sampling with black-box…
Conventionally, human intuition defines vision as a modality of passive optical sensing, relying on ambient light to perceive the environment. However, active optical sensing, which involves emitting and receiving signals, offers unique…
Accurate volume estimation of objects from visual data is a long-standing challenge in computer vision with significant applications in robotics, logistics, and smart health. Existing methods often rely on complex 3D reconstruction…
With the popularity of stereo cameras in computer assisted surgery techniques, a second viewpoint would provide additional information in surgery. However, how to effectively access and use stereo information for the super-resolution (SR)…
We develop a novel algorithm for characterizing Deep Sub-Electron Read Noise (DSERN) image sensors. This algorithm is able to simultaneously compute maximum likelihood estimates of quanta exposure, conversion gain, bias, and read noise of…
Spectropolarimetric reconstructions of the photospheric vector magnetic field are intrinsically limited by the 180$^\circ$-ambiguity in the orientation of the transverse component. So far, the removal of such an ambiguity has required…
Robots that interact with humans in a physical space or application need to think about the person's posture, which typically comes from visual sensors like cameras and infra-red. Artificial intelligence and machine learning algorithms use…
Learning a data-driven spatio-temporal semantic representation of the objects is the key to coherent and consistent labelling in video. This paper proposes to achieve semantic video object segmentation by learning a data-driven…
In this paper we present an alternative method to symbolic segmentation: we approach symbolic segmentation as an algorithm selection problem. That is, let there be a set A of available algorithms for symbolic segmentation, a set of input…
Autonomous driving vehicles and robotic systems rely on accurate perception of their surroundings. Scene understanding is one of the crucial components of perception modules. Among all available sensors, LiDARs are one of the essential…
Robotic task instructions often involve a referred object that the robot must locate (ground) within the environment. While task intent understanding is an essential part of natural language understanding, less effort is made to resolve…
Semantic segmentation is a crucial step in many Earth observation tasks. Large quantity of pixel-level annotation is required to train deep networks for semantic segmentation. Earth observation techniques are applied to varieties of…