The Experts below are selected from a list of 70506 Experts worldwide ranked by ideXlab platform
Martin J Pearson - One of the best experts on this subject based on the ideXlab platform.
-
whisker ratslam applied to 6d Object Identification and spatial localisation
Conference on Biomimetic and Biohybrid Systems, 2018Co-Authors: Mohammed Salman, Martin J PearsonAbstract:The problem of tactile Object Identification has a strong connection with the problem of Simultaneous Localization and Mapping (SLAM) in a physical 6-dimensional environment. Here we introduce our preliminary results describing the performance of our RatSLAM-inspired 6D SLAM algorithm dubbed Whisker-RatSLAM, which is used to map and localize a whisker-array relative to the surface of an Object. We show that our approach can successfully localize using the physical and simulation data sets taken from an active array of artificial whiskers as they explore a range of household Objects. We also demonstrate the ability of Whisker-RatSLAM to be used for Object Identification.
-
Living Machines - Whisker-RatSLAM Applied to 6D Object Identification and Spatial Localisation
Biomimetic and Biohybrid Systems, 2018Co-Authors: Mohammed Salman, Martin J PearsonAbstract:The problem of tactile Object Identification has a strong connection with the problem of Simultaneous Localization and Mapping (SLAM) in a physical 6-dimensional environment. Here we introduce our preliminary results describing the performance of our RatSLAM-inspired 6D SLAM algorithm dubbed Whisker-RatSLAM, which is used to map and localize a whisker-array relative to the surface of an Object. We show that our approach can successfully localize using the physical and simulation data sets taken from an active array of artificial whiskers as they explore a range of household Objects. We also demonstrate the ability of Whisker-RatSLAM to be used for Object Identification.
Mike J. Dixon - One of the best experts on this subject based on the ideXlab platform.
-
The influence of visual and nonvisual attributes in visual Object Identification.
Journal of the International Neuropsychological Society : JINS, 2006Co-Authors: Tom A. Schweizer, Mike J. DixonAbstract:To elucidate the role of visual and nonvisual attribute knowledge on visual Object Identification, we present data from three patients, each with visual Object Identification impairments as a result of different etiologies. Patients were shown novel computer-generated shapes paired with different labels referencing known entities. On test trials they were shown the novel shapes alone and had to identify them by generating the label with which they were formerly paired. In all conditions the same triad of computer-generated shapes were used. In one condition, the labels (banjo, guitar, violin) referenced entities that were both visually similar and similar in terms of their nonvisual attributes within semantics. In separate conditions we used labels (e.g., spike, straw, pencil or snorkel, cane, crowbar) that referenced entities that were similar in terms of their visual attributes but were dissimilar in terms of their nonvisual attributes. The results revealed that nonvisual attribute information profoundly influenced visual Object Identification. Our patients performed significantly better when attempting to identify shape triads whose labels referenced Objects with distinct nonvisual attributes versus shape triads whose labels referenced Objects with similar nonvisual attributes. We conclude that the nonvisual aspects of meaning must be taken into consideration when assessing visual Object Identification impairments.
Mohammed Salman - One of the best experts on this subject based on the ideXlab platform.
-
whisker ratslam applied to 6d Object Identification and spatial localisation
Conference on Biomimetic and Biohybrid Systems, 2018Co-Authors: Mohammed Salman, Martin J PearsonAbstract:The problem of tactile Object Identification has a strong connection with the problem of Simultaneous Localization and Mapping (SLAM) in a physical 6-dimensional environment. Here we introduce our preliminary results describing the performance of our RatSLAM-inspired 6D SLAM algorithm dubbed Whisker-RatSLAM, which is used to map and localize a whisker-array relative to the surface of an Object. We show that our approach can successfully localize using the physical and simulation data sets taken from an active array of artificial whiskers as they explore a range of household Objects. We also demonstrate the ability of Whisker-RatSLAM to be used for Object Identification.
-
Living Machines - Whisker-RatSLAM Applied to 6D Object Identification and Spatial Localisation
Biomimetic and Biohybrid Systems, 2018Co-Authors: Mohammed Salman, Martin J PearsonAbstract:The problem of tactile Object Identification has a strong connection with the problem of Simultaneous Localization and Mapping (SLAM) in a physical 6-dimensional environment. Here we introduce our preliminary results describing the performance of our RatSLAM-inspired 6D SLAM algorithm dubbed Whisker-RatSLAM, which is used to map and localize a whisker-array relative to the surface of an Object. We show that our approach can successfully localize using the physical and simulation data sets taken from an active array of artificial whiskers as they explore a range of household Objects. We also demonstrate the ability of Whisker-RatSLAM to be used for Object Identification.
Mikhail N. Sokolov - One of the best experts on this subject based on the ideXlab platform.
-
Tactile sensing for Object Identification based on hetero-core fiber optics
Sensors and Actuators A: Physical, 2016Co-Authors: Hiroshi Yamazaki, Michiko Nishiyama, Kazuhiro Watanabe, Mikhail N. SokolovAbstract:Abstract This paper describes a human-like tactile sensing method for Object Identification using a tactile sensor based on hetero-core fiber optics. The sensor performs for detecting tactile information in such ways both of gentle and heavy touch with the contact force applied ranging from 0.0 N to 5.3 N. The proposed method for Object Identification is intended to measure several types of tactile impressions such as surface features and physical characteristics in both scanning and pushing motions. It is found that the fabricated tactile sensor can detect surface features such as arranged bump dots and two types of textured fabrics by the sensor scanning on the surface. Moreover, it is confirmed that the sensor can measure the physical characteristics of touched materials, including the hardness in the range from 5° to 80° according to the Shore hardness A scale, as well as viscoelastic properties by assessing the temporal variation of the sensor response during stress relaxation.
Mark A. Ganter - One of the best experts on this subject based on the ideXlab platform.
-
Matching surface signatures for Object Identification
1997Co-Authors: Adnan A. Y. Mustafa, Linda G. Shapiro, Mark A. GanterAbstract:In this paper we describe a surface matching approach that integrates both curvature and color information for Object Identification. Local features called surface signatures are employed for matching. Surface signatures are statistical features that are uniform for a uniform surface. Two types of signatures are employed; color signatures and curvature signatures. Tests conducted on Objects of various curvature and colors have produced encouraging results, where over 90% of the surfaces tested matched correctly to their model counterparts.
-
CAIP - Object Identification with Surface Signatures
Computer Analysis of Images and Patterns, 1997Co-Authors: Adnan A. Y. Mustafa, Linda G. Shapiro, Mark A. GanterAbstract:In this paper we describe a model-based Object Identification system. Given a set of 3D Objects and a scene containing one or more of these Objects, the system identifies which Objects appear in the scene by matching surface signatures. Surface signatures are statistical features which are uniform for a uniform surface. Two types of surfaces are employed; curvature signatures and spectral signatures. Furthermore, the system employs an inexpensive acquisition setup consisting of a single CCD camera and two light sources. The system has been tested on 95 observed-surfaces and 77 Objects of varying degrees of curvature and color with good results.
