1,721,114 research outputs found
Novel 3-DOF Simulated Annealing-Based Haptic Rendering Algorithm
No full textHaptic rendering requires high sampling rates and a quasi-instantaneous, ultra-low latency, response. Existing algorithms for collision detection are sequential in nature and are difficult to parallelize. A novel 3-DOF haptic rendering algorithm has been developed based on the simulated annealing algorithm. The simulated annealing algorithm is applied to find the collision between the haptic interface point and the virtual object. When there is no collision, the shortest distance between the haptic interface point and the virtual object will be returned. To test the haptic rendering algorithm basic geometric shapes have been used to confirm the feasibility of the developed algorithm. When choosing suitable object-dependent values for the simulated annealing parameters it becomes clear that the average update frequency reaches well above the desired update frequency of at least 1 kHz, including both the collision detection as well as the constraint-based force response, while obtaining high-fidelity force feedback. Finally, the simulated annealing algorithm lends itself perfectly for the development of dedicated hardware implementations to achieve massive parallel execution for different parts of the simulated annealing algorithm, which further increases the update frequency. Due to this increase in update frequency it will be possible to run the simulated annealing algorithm multiple times within one haptic loop (i.e. 1 kHz) and find multiple contact points simultaneously
Novel 3-DOF Simulated Annealing-Based Haptic Rendering Algorithm
No full textHaptic rendering requires high sampling rates and a quasi-instantaneous, ultra-low latency, response. Existing algorithms for collision detection are sequential in nature and are difficult to parallelize. A novel 3-DOF haptic rendering algorithm has been developed based on the simulated annealing algorithm. The simulated annealing algorithm is applied to find the collision between the haptic interface point and the virtual object. When there is no collision, the shortest distance between the haptic interface point and the virtual object will be returned. To test the haptic rendering algorithm basic geometric shapes have been used to confirm the feasibility of the developed algorithm. When choosing suitable object-dependent values for the simulated annealing parameters it becomes clear that the average update frequency reaches well above the desired update frequency of at least 1 kHz, including both the collision detection as well as the constraint-based force response, while obtaining high-fidelity force feedback. Finally, the simulated annealing algorithm lends itself perfectly for the development of dedicated hardware implementations to achieve massive parallel execution for different parts of the simulated annealing algorithm, which further increases the update frequency. Due to this increase in update frequency it will be possible to run the simulated annealing algorithm multiple times within one haptic loop (i.e. 1 kHz) and find multiple contact points simultaneously
SoC and FPGA Oriented High-quality Stereo Vision System
No full textStereo matching is a crucial step for acquiring depth information from stereo images. However, it is still challenging to achieve good performance in both speed and accuracy for various stereo vision applications. In this paper, a hardware-compatible stereo matching algorithm is proposed; its associated hardware implementation is also presented. The proposed algorithm can produce high-quality disparity maps with the use of mini-census transform, segmentation-based adaptive support weight and effective refinement. Moreover, the proposed implementation is optimized as a fully pipelined and scalable hardware system. The proposed design is evaluated based on the Middlebury benchmarks and the average overall error rate is 6.10%. The experimental results indicate that the accuracy is competitive with some state-of-art software implementations.The research in this paper was sponsored in part by the Belgian FWO (Flemish Research Council) and the Chinese MOST (Ministry of Science and Technology) bilateral cooperation project number G.0524.13
Low-cost real-time stereo vision hardware with binary confidence metric and disparity refinement
No full textThis paper presents a real-time stereo vision System-on-Chip (SoC) architecture for a depth-field generation processor as required in 3D TV applications. Dense Stereo Vision is a complex problem and uses many resources to achieve a high quality depth image. To reduce the needed resources, this architecture divides the problem into two parts: first a rough depth map is constructed using a segmentation based SAD window comparison, second a disparity refinement module identifies false matches and replaces them.Research sponsored in part by BOF (Bijzonder Onderzoeksfonds) UHasselt, Flanders FWO (Fonds voor Wetenschappelijk Onderzoek) and Chinese MOST (Ministry of Science and Technology) project number G.A.063.10
Cloud-based Collaboration Platform for Orthognatic Surgical Planning
No full textMany medical departments use several multi-disciplinary technologies to support the planning of the surgery. For complex operations a collaboration between different experts can improve
the success rate, but the tools are mostly on-premises software and limit the good cooperation. In this case, the orthognathic and dental surgery uses 3D and CT scans to plan the surgery beforehand by making use of 3D image processing, visualization and planning tools. We researched the possibility to create an online cloud-based platform to run the currently used surgical planning tools to improve the collaboration between several experts. We achieved multiple two-factor authentication user logins for security, simultaneous surgical planning sessions for collaboration and lightweight multi-platform support for existing technologies
Automatic identification and reconstruction of the right phrenic nerve on computed tomography
No full textAutomatic Identification and Reconstruction of the Right Phrenic Nerve on Computed Tomography
No full textAn automatic computer algorithm was successfully constructed, enabling identification and reconstruction of the right phrenic nerve on high resolution coronary computed tomography scans. This could lead to a substantial reduction in the incidence of phrenic nerve paralysis during pulmonary vein isolation using ballon techniques
Automatic identification and reconstruction of the right phrenic nerve on computed tomography
No full textReflections on enhancing interaction in surface computing using real-world objects
No full textThe popularity of interactive surfaces has increased significantly in the past years. The development of several interactive surfaces has stimulated research on interaction techniques, group collaboration, information visualization techniques, technology alternatives, ... Furthermore, a number of applications were realized, mostly focusing on sorting (e.g. pictures), planning (e.g. agenda's, projects, GIS), sketching, brainstorming or games. Here, touch input and gestures form the principal method of interaction, whereas additional input devices are rather seldom used. On the other hand, a number of researchers have been working on tangible user interfaces (TUI) in the past decade. Their research has led to quite some innovative interfaces in a wide range of application areas. Working with tangible I/O objects is experienced as quite intuitive, notwithstanding the fact that many objects are newly created artifacts. These objects have form factors of their real-world counterpart (if any) and thus help facilitating embodied interaction. A research challenge, situated at the crossroads of tangible user interfaces and interactive surfaces, is the interaction with real-world objects on interactive surfaces. Since affordances and behavior of real-world objects are familiar to the target audience of an application (and hence can substantially improve user experience), it should be beneficial to use real world objects in applications of surface computing
Fine-Grained Channel Pruning for Deep Residual Neural Networks
No full textPruning residual neural networks is a challenging task due to the constraints induced by cross layer connections. Many existing approaches assign channels connected by skip-connections to the same group and prune them simultaneously, limiting the pruning ratio on those troublesome filters. Instead, we propose a Fine-grained Channel Pruning (FCP) method that allows any channels to be pruned independently. To avoid the misalignment problem between convolution and skip connection , we always keep the residual addition operations alive. Thus we can obtain a novel efficient residual architecture by removing any unimportant channels without the alignment constraint. Besides classification, We further apply FCP on residual models for image super-resolution, which is a low-level vision task. Extensive experimental results show that FCP can achieve better performance than other state-of-the-art methods in terms of parameter and computation cost. Notably, on CIFAR-10, FCP reduces more than 78% FLOPs on ResNet-56 with no accuracy drop. Moreover, it achieves more than 48% FLOPs reduction on MSR-ResNet with negligible performance degradation
- …
