In this paper, we present a novel method for 3D geometric scene graph generation using range sensors and RGB cameras. We initially detect instance-wise keypoints with a YOLOv8s model to compute 6D pose estimates of kn...
详细信息
We present the hardware design, software architecture, and core algorithms of Herb 2.0, a bimanual mobile manipulator developed at the Personal robotics Lab at Carnegie Mellon University, Pittsburgh, PA. We have devel...
详细信息
2D gel electrophoresis (2DGE) plays an important role in proteomics. It can separate proteins effectively with their pI values and molecular weights. Proteomics researchers needed to identify interested protein spots ...
详细信息
ISBN:
(纸本)9780791802977
2D gel electrophoresis (2DGE) plays an important role in proteomics. It can separate proteins effectively with their pI values and molecular weights. Proteomics researchers needed to identify interested protein spots by examining the gel. This is time - consuming and labor extensive. It is desired that the computer can analyze the proteins automatically by first detecting and quantifying the protein spots in the digitized 2DGE images. In our work, we will investigate the use of the watershed algorithm in segmenting the protein spots from the varying background. However, the watershed algorithm often produces an over-segmented result. So, we will introduce the notion of fuzzy relations to improve the segmentation result.
Sub-surface and buried landmines, with the surrounding environment constitute a complex system with variable characteristics. Infrared thermography techniques are attractive candidates for this kind of applications. T...
详细信息
ISBN:
(纸本)9781424456536
Sub-surface and buried landmines, with the surrounding environment constitute a complex system with variable characteristics. Infrared thermography techniques are attractive candidates for this kind of applications. They can be used from a considerable standoff distance to provide information on several mine properties, and they can also rapidly survey large areas. This paper presents a robust method for landmine detection and recognition. It uses the mean-shift algorithm to segment the acquired infrared image. The segmented image retains pixels associated with mines together with background clutters. To determine which pixels represent the mines, a second phase of segmentation is applied to the output of the mean-shift algorithm by using a self-organizing maps (SOM) algorithm. Depending on the resulted cluster intensity variations, the chips extracted from the segmented image are processed to extract mine signatures. After that, the extracted signatures are scanned horizontally. vertically, and diagonally to build a cluster intensity variation profile. This profile is statistically compared with the known mine signature profiles *** proposed system is applied on series of time variant mid-wave infrared images (MWIR), and the test result show that the system can effectively recognize the mines with low false alarm rate.
Sub-surface and buried landmines, with the surrounding environment constitute a complex system with variable characteristics. Infrared thermography techniques are attractive candidates for this kind of applications. T...
详细信息
ISBN:
(纸本)9781424456536;9781424456543
Sub-surface and buried landmines, with the surrounding environment constitute a complex system with variable characteristics. Infrared thermography techniques are attractive candidates for this kind of applications. They can be used from a considerable standoff distance to provide information on several mine properties, and they can also rapidly survey large areas. This paper presents a robust method for landmine detection and recognition. It uses the mean-shift algorithm to segment the acquired infrared image. The segmented image retains pixels associated with mines together with background clutters. To determine which pixels represent the mines, a second phase of segmentation is applied to the output of the mean-shift algorithm by using a self-organizing maps (SOM) algorithm. Depending on the resulted cluster intensity variations, the chips extracted from the segmented image are processed to extract mine signatures. After that, the extracted signatures are scanned horizontally, vertically, and diagonally to build a cluster intensity variation profile. This profile is statistically compared with the known mine signature profiles v. The proposed system is applied on series of time variant mid-wave infrared images (MWIR), and the test result show that the system can effectively recognize the mines with low false alarm rate.
Self-localization in dynamic environments is a central problem in mobile robotics and is well studied in the literature. One of the most popular methods is the Monte Carlo Localization algorithm (MCL). Many deployed s...
详细信息
This paper is concerned with the evolution development of the fuzzy neural networks. The learning procedures in such networks consists of two main development phases. First the network is evolutionary constructed thro...
详细信息
This paper is concerned with the evolution development of the fuzzy neural networks. The learning procedures in such networks consists of two main development phases. First the network is evolutionary constructed through the use of evolutionary strategies and evolutionary programming. The second phase of the design of the network is aimed at its refinement and optimize the objective parameters to adapt to the nonlinear changes of the input *** are two main optimization mechanisms working concurrently : structural development and paramertric refinement mechnisms using the integrated approach based on evolutionary programming and the evolution *** evolutionary -based leaning has been compared with the gradient-based *** proposed technique is applied for controlling nonlinear dynamics of a multilink robot system. Extensive simulations have been performed, aimed at investigating the adaptive capability, tracking performance and the convergence properties of the proposed evolutionary model with respect to variety of situations. The results are remarkable compared with the fuzzy and neural networks optimized using gradient-based learning.
暂无评论