- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
New approach to enhancing the performance of cloud-based vision system of mobile robots
摘要： Mobile robots require real-time performance, high computation power, and a shared computing environment. Although cloud computing offers computation power, it may adversely affect real-time performance owing to network lag. The main objective of this study is to allow a mobile robot vision system to reliably achieve real-time constraints using cloud computing. A human cloud mobile robot architecture is proposed as well as a data flow mechanism organized on both the mobile robot and the cloud server sides. Two algorithms are proposed: (i) A real-time image clustering algorithm, applied on the mobile robot side, and (ii) A modified growing neural gas algorithm, applied on the cloud server side. The experimental results demonstrate that there is a 25% to 45% enhancement in the total response time, depending on the communication bandwidth and image resolution. Moreover, better performance in terms of data size, path planning time, and accuracy is demonstrated over other state-of-the-art techniques.
关键词： Computation offloading,Computer vision,3D point cloud,Mobile robot,Stereo vision,Real-time networking,Cloud computing,Cloud robotics
更新于2025-09-23 15:23:52
-
Experimental verification of turbidity tolerance of stereo-vision-based 3D pose estimation system
摘要： This paper presents the verification of the turbidity tolerance of a stereo-vision-based 3D pose estimation system for underwater docking applications. To the best of the authors’ knowledge, no studies have yet been conducted on 3D pose (position and orientation) estimation against turbidity for underwater vehicles. Therefore, the effect of turbidity on the 3D pose estimation performance of underwater vehicles and a method of operating under turbid conditions were studied in this work. A 3D pose estimation method using the real-time multi-step genetic algorithm (RM-GA) proposed by the authors in the previous works shows robust pose estimation performance against changing environmental conditions. This paper discusses how and why the RM-GA is well suited to effective 3D pose estimation, even when turbid conditions disturb visual servoing. The experimental results confirm the performance of the proposed 3D pose estimation system under different levels of turbidity. To demonstrate the practical usefulness of the RM-GA, docking experiments were conducted in a turbid pool and a real sea environment to verify the performance and tolerance of the proposed system under turbid conditions. The experimental results verify the robustness of the system against turbidity, presenting a possible solution to a major problem in the field of robotics.
关键词： Robustness against turbidity,Real-time multi-step genetic algorithm,Sea docking,3D pose estimation,Stereo-vision,Visual servoing
更新于2025-09-23 15:23:52
-
Intelligent Indoor Mobile Robot Navigation Using Stereo Vision
摘要： Majority of the existing robot navigation systems, which facilitate the use of laser range finders, sonar sensors or artificial landmarks, has the ability to locate itself in an unknown environment and then build a map of the corresponding environment. Stereo vision,while still being a rapidly developing technique in the field of autonomous mobile robots, are currently less preferable due to its high implementation cost. This paper aims at describing an experimental approach for the building of a stereo vision system that helps the robots to avoid obstacles and navigate through indoor environments and at the same time remaining very much cost effective. This paper discusses the fusion techniques of stereo vision and ultrasound sensors which helps in the successful navigation through different types of complex environments. The data from the sensor enables the robot to create the two dimensional topological map of unknown environments and stereo vision systems models the three dimension model of the same environment.
关键词： Point clouds,Triangulation,SLAM,Arduino,Stereo vision system
更新于2025-09-23 15:23:52
-
[IEEE 2018 IEEE 12th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC) - Hanoi (2018.9.12-2018.9.14)] 2018 IEEE 12th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC) - Designing Compact Convolutional Neural Network for Embedded Stereo Vision Systems
摘要： Autonomous systems are used in a wide range of domains from indoor utensils to autonomous robot surgeries and self-driving cars. Stereo vision cameras probably are the most flexible sensing way in these systems since they can extract depth, luminance, color, and shape information. However, stereo vision based applications suffer from huge image sizes and computational complexity leading system to higher power consumption. To tackle these challenges, in the first step, GIMME2 stereo vision system [1] is employed. GIMME2 is a high-throughput and cost efficient FPGA-based stereo vision embedded system. In the next step, we present a framework for designing an optimized Deep Convolutional Neural Network (DCNN) for time constraint applications and/or limited resource budget platforms. Our framework tries to automatically generate a highly robust DCNN architecture for image data receiving from stereo vision cameras. Our proposed framework takes advantage of a multi-objective evolutionary optimization approach to design a near-optimal network architecture for both the accuracy and network size objectives. Unlike recent works aiming to generate a highly accurate network, we also considered the network size parameters to build a highly compact architecture. After designing a robust network, our proposed framework maps generated network on a multi/many core heterogeneous System-on-Chip (SoC). In addition, we have integrated our framework to the GIMME2 processing pipeline such that it can also estimate the distance of detected objects. The generated network by our framework offers up to 24x compression rate while losing only 5% accuracy compare to the best result on the CIFAR-10 dataset.
关键词： Deep Convolutional Neural Network,Stereo Vision Systems,Neural Processing Unit,Neural Network Architecture Search
更新于2025-09-23 15:22:29
-
[IEEE 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - Krakow, Poland (2018.10.16-2018.10.18)] 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - Real-Time Stereo Vision for Road Surface 3-D Reconstruction
摘要： Stereo vision techniques have been widely used in civil engineering to acquire 3-D road data. The two important factors of stereo vision are accuracy and speed. However, it is very challenging to achieve both of them simultaneously and therefore the main aim of developing a stereo vision system is to improve the trade-off between these two factors. In this paper, we present a real-time stereo vision system used for road surface 3-D reconstruction. The proposed system is developed from our previously published 3-D reconstruction algorithm where the perspective view of the target image is first transformed into the reference view, which not only increases the disparity accuracy but also improves the processing speed. Then, the correlation cost between each pair of blocks is computed and stored in two 3-D cost volumes. To adaptively aggregate the matching costs from neighbourhood systems, bilateral filtering is performed on the cost volumes. This greatly reduces the ambiguities during stereo matching and further improves the precision of the estimated disparities. Finally, the subpixel resolution is achieved by conducting a parabola interpolation and the subpixel disparity map is used to reconstruct the 3-D road surface. The proposed algorithm is implemented on an NVIDIA GTX 1080 GPU for the real-time purpose. The experimental results illustrate that the reconstruction accuracy is around 3 mm.
关键词： stereo vision,3-D reconstruction,bilateral filtering,subpixel disparity map,real-time
更新于2025-09-23 15:22:29
-
[IEEE 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV) - Singapore, Singapore (2018.11.18-2018.11.21)] 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV) - Fire Geometrical Characteristics Estimation Using a Visible Stereovision System Carried by Unmanned Aerial Vehicle
摘要： In the context of wild?re research and ?ght, there is a need of measuring ?re geometrical characteristics to better understand the phenomena occurring during the propagation, to develop and to improve models in order to anticipate the ?re behavior and to position ?re?ghters and water drops and to protect the population. This paper presents a framework composed by an unmanned aerial vehicle carrying a visible stereo vision system developed in order to estimate the position, rate of spread, height, inclination angle, base width and surface of ?res obtained by experimental burnings at ?eld scale. This research is developed with the ultimate goal to carry out a technological transfer in order to obtain systems that can be used by ?re?ghters.
关键词： UAV (unmanned aerial vehicle),stereo vision,measure,Wild?re,image processing.
更新于2025-09-23 15:22:29
-
Automatic Rectification of the Hybrid Stereo Vision System
摘要： By combining the advantages of 360-degree field of view cameras and the high resolution of conventional cameras, the hybrid stereo vision system could be widely used in surveillance. As the relative position of the two cameras is not constant over time, its automatic rectification is highly desirable when adopting a hybrid stereo vision system for practical use. In this work, we provide a method for rectifying the dynamic hybrid stereo vision system automatically. A perspective projection model is proposed to reduce the computation complexity of the hybrid stereoscopic 3D reconstruction. The rectification transformation is calculated by solving a nonlinear constrained optimization problem for a given set of corresponding point pairs. The experimental results demonstrate the accuracy and effectiveness of the proposed method.
关键词： projection model,hybrid stereo vision,automatic rectification
更新于2025-09-23 15:22:29
-
[Advances in Intelligent Systems and Computing] Intelligent Autonomous Systems 15 Volume 867 (Proceedings of the 15th International Conference IAS-15) || Stereo Vision-Based Optimal Path Planning with Stochastic Maps for Mobile Robot Navigation
摘要： This paper addresses the problem of stereo vision-based environment mapping and optimal path planning for an autonomous mobile robot by using the methodology of getting 3D point cloud from disparity images, its transformation to 2D stochastic navigation map with occupancy grid cell values assigned from the set {obstacle, unoccupied, occupied}. We re-examined and extended this methodology with a combination of A-Star with binary heap algorithms for obstacle avoidance and indoor navigation of the Innopolis autonomous mobile robot with ZED stereo camera.
关键词： Mobile robot navigation,Occupancy grid,Disparity image,Stochastic map,Optimal path planning,Stereo vision
更新于2025-09-23 15:22:29
-
Stereo vision system for human motion analysis in a rehabilitation context
摘要： The present demographic trends point to an increase in aged population and chronic diseases which symptoms can be alleviated through rehabilitation. The applicability of passive 3D reconstruction for motion tracking in a rehabilitation context was explored using a stereo camera. The camera was used to acquire depth and color information from which the 3D position of prede?ned joints was recovered based on: kinematic relationships, anthropometrically feasible lengths and temporal consistency. Finally, a set of quantitative measures were extracted to evaluate the performed rehabilitation exercises. Validation study using data provided by a marker based as ground-truth revealed that our proposal achieved errors within the range of state-of-the-art active markerless systems and visual evaluations done by physical therapists. The obtained results are promising and demonstrate that the developed methodology allows the analysis of human motion for a rehabilitation purpose.
关键词： stereo vision,biomedical engineering,Rehabilitation,human motion tracking
更新于2025-09-23 15:21:21
-
Optical Diagnosis of the Geometry of an Axisymmetric Controlled Nozzle of a Gas-Turbine Engine
摘要： Modern aviation industry solves the problem of developing multifunction engines capable of ?ying both at subsonic and supersonic speeds. An important part in such engines is a variable area nozzle, which allows varying the geometry of the engine exhaust unit and, accordingly, its technical characteristics. This study touches upon an computer vision based optical noncontact method for reconstructing a nozzle shape. The reconstruction requires data recorded by two optical three-dimensional recorders directed toward the inner part of the nozzle when the engine is subjected to ground tests. The diagnosis is complicated by the presence of a hot jet being in the way of the sensor vision, the regime-dependent variation of the nozzle glow brightness, and intense mechanical vibrations. The performed bench tests con?rm the e?ciency of the proposed method. According to their results, in a low-gas regime, the standard deviation of the diagnosed diameters of the exhaust unit and critical sections for each frame does not exceed 0.3% of the corresponding sizes. The data obtained as a result of this diagnosis can be taken into account when upgrading the exhaust unit of the engine and the thrust control system of a gas turbine engine.
关键词： 3D scan,GTE exhaust unit geometry,optical diagnosis,stereo vision,stereo reconstruction,ground tests
更新于2025-09-23 15:21:01