Precise Measurement of Position and Attitude Based on Convolutional Neural Network and Visual Correspondence Relationship

Yang, Jiachen; Man, Jiabao; Meng, Xiaofeng; Gao, Xinbo; Lu, Wen; Meng, Qinggang

doi:10.1109/tnnls.2019.2927719

Cited by 12 publications

(7 citation statements)

References 36 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each 2D detection result, the most likely perspective and in-plane rotation were analyzed, and then a series of 6D hypotheses were established to select an optimal one as the result. Recently, Yang et al [161] proposed a method of target pose measurement using CNN. This method directly returned the 6D attitude information of the object, eliminating the template used by the previous methods, which was simpler, faster speed and higher accuracy.…”

Section: F Pose Measurementmentioning

confidence: 99%

“…Aerospace [145] Robot [146] Industrial production [147] Aircraft [148] Vehicle [149] Ocean [150] Monocular-based pose measurement [151] Binocular-based pose measurement [152] Feature descriptors-based pose measurement [153]- [157] Template matching-based pose measurement [158] CNN-based pose measurement [159]- [161] or videos. For example, the most common CCD and CMOS cameras are converted into electronic signals according to different light.…”

Section: A Vision Acquisitionmentioning

confidence: 99%

See 1 more Smart Citation

Visual Perception Enabled Industry Intelligence: State of the Art, Challenges and Prospects

Yang

Wang

Jiang

et al. 2021

IEEE Trans. Ind. Inf.

Self Cite

168

View full text Add to dashboard Cite

Visual perception refers to the process of organizing, identifying and interpreting visual information in environmental awareness and understanding. With the rapid progress of multimedia acquisition technology, research on visual perception has been a hot topic in the academical field and industrial applications. Especially after the introduction of artificial intelligence theory, intelligent visual perception has been widely used to promote the development of industrial production towards intelligence. In this paper, we review the previous research and application of visual perception in different industrial fields such as product surface defect detection, intelligent agricultural production, intelligent driving, image synthesis and event reconstruction. The applications basically cover most of the intelligent visual perception processing technologies. Through this survey, it will provide a comprehensive reference for research on this direction. Finally, this paper also summarizes the current challenges of visual perception and predicts its future development trends.

show abstract

Section: F Pose Measurementmentioning

confidence: 99%

Section: A Vision Acquisitionmentioning

confidence: 99%

Visual Perception Enabled Industry Intelligence: State of the Art, Challenges and Prospects

Yang

Wang

Jiang

et al. 2021

IEEE Trans. Ind. Inf.

Self Cite

168

View full text Add to dashboard Cite

show abstract

“…9. In particular, sub-figure 9 (1) describes the recognition of the target; and 9 (2)(3)(4)(5)(6)(7)(8)(9)(10)(11)(12) show the reaching process towards the target. The joint angles of the robotic arm were adjusted step by step based on the position errors between the hand and target, and the whole process took 11 steps.…”

Section: B Reaching Movement Experimentsmentioning

confidence: 99%

“…The key for a successful vision-based robotic manipulator system with reaching ability is effective hand-eye coordination [1], which uses the information obtained from vision sensors to guide robotic manipulators to reach and manipulate the target objects [2]- [4]. Hand-eye coordination combines the technologies in computer vision and robotics to enhance robotic sensory-motor ability [5]- [7], which plays an important role in industrial assembly robots [8]- [10], mobile exploration robots [11], and robots for education, medical, military, etc [12]. Traditional hand-eye coordination works based on the accurate kinematic calibrations between the robotic hand and vision system, which are usually designed by human engineers [13].…”

Section: Introductionmentioning

confidence: 99%

Visual-Guided Robotic Object Grasping Using Dual Neural Network Controllers

Fang

Chao

Lin

et al. 2021

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

It has been a challenging task for a robotic arm to accurately reach and grasp objects, and much research attention has been attracted. This paper proposes a robotic hand-eye coordination system by simulating the human behavior pattern to achieve a fast and robust reaching ability. This is achieved by two neural-network-based controllers, including a rough reaching movement controller implemented by a pre-trained Radial Basis Function (RBF) for rough reaching movements, and a correction movement controller built from a specifically designed Brain Emotional Nesting Network (BENN) for smooth correction movements. In particular, the proposed BENN is designed with high nonlinear mapping ability, with its adaptive laws derived from the Lyapunov stability theorem; from this, the robust tracking performance and accordingly the stability of the proposed control system are guaranteed by the utilisation of the H ∞ control approach. The proposed BENN is validated and evaluated by a chaos synchronisation simulation, and the overall control system by object grasping tasks through a physical robotic arm in a real-world environment. The experimental results demonstrate the superiority of the proposed control system in reference to those with single neural networks.

show abstract

“…Many researches on detection have begun and have achieved certain achievements. Convolutional neural network (CNN) is the basic model of deep learning, which can reduce the computation using convolution 6,7 . Therefore, algorithms based on CNN are introduced to autonomous driving, such as classification and detection of vehicles and pedestrianscite 8 .…”

Section: Introductionmentioning

confidence: 99%

Vehicle video surveillance system based on image fusion and parallel computing

Liu

Lyu

Gong

2020

Circuit Theory & Apps

View full text Add to dashboard Cite

Summary Autonomous driving has gradually moved towards practical applications in recent years. It is particularly critical to provide reliable real‐time environmental information for autonomous driving systems. At present, vehicle video surveillance systems based on multi‐source video and target detection algorithms can effectively solve these problems. However, the previous vehicle video surveillance systems are often unable to balance the surveillance effect and the surveillance frame rate. Therefore, we will introduce a vehicle video surveillance system based on parallel computing and computer vision in this article. First, multiple fisheye cameras are used to collect surround‐view environmental information. Second, we will use a low‐light camera, infrared thermal imager, and millimeter‐wave radar to provide forward‐view environmental information at night. Correspondingly, we designed the surround‐view image fusion algorithm and the forward‐view image fusion algorithm based on parallel computing. At last, a monocular camera and detection algorithms are used to provide forward‐view detection results. In a word, this vehicle video surveillance system will benefit the practical application of autonomous driving.

show abstract

Precise Measurement of Position and Attitude Based on Convolutional Neural Network and Visual Correspondence Relationship

Cited by 12 publications

References 36 publications

Visual Perception Enabled Industry Intelligence: State of the Art, Challenges and Prospects

Visual Perception Enabled Industry Intelligence: State of the Art, Challenges and Prospects

Visual-Guided Robotic Object Grasping Using Dual Neural Network Controllers

Vehicle video surveillance system based on image fusion and parallel computing

Contact Info

Product

Resources

About