Performance Evalution of 3D Keypoint Detectors and Descriptors for Plants Health Classification

Azimi, Shiva; Lall, Brejesh; Gandhi, Tapan Kumar

doi:10.23919/mva.2019.8758002

Cited by 9 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the field of three-dimensional (3D) measurement, a number of methods have been proposed [16]- [19]. Besides, the obtained 3D point cloud or depth image are utilized for various robotic applications involving robot vision, such as bin-picking [11], [20], prediction of reaching motion [21], [22], 3D keypoint detection [23], [24], 3D feature description [25], segmentation [26], [27], and SLAM [28]. An example of the representative three-dimensional measurement method is the light-section method, in which 3D measurement is performed by projecting a line of light and measuring its reflected light.…”

Section: Related Workmentioning

confidence: 99%

Optimal Projection Pattern for Active Visual Servoing (AVS)

Arai,

Miyamoto,

Kobayashi

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Visual servo control uses images that are obtained by a camera for robotic control. This study focuses on the problem of positioning a target object using a robotic manipulator with image-based visual servo (IBVS) control. To perform the positioning task, the image-based visual servoing requires visual features that can be extracted from the appearance of the target object. Therefore, a positioning error tends to increase especially for textureless objects, such as industrial parts. Since it is difficult to extract differences in the visual features between current and goal images. To solve these problems, this paper presents a novel visual servoing named "Active Visual Servoing." Active Visual Servoing (AVS) projects patterned light onto the target object using a projector. The design of the projection pattern affects the positioning error. AVS uses an optimal pattern that is theoretically derived and maximizes differences between current and goal images. The experimental results show that the proposed active visual servoing method reduces the positioning error by more than 97% compared to conventional image-based visual servoing.

show abstract

Section: Related Workmentioning

confidence: 99%

Optimal Projection Pattern for Active Visual Servoing (AVS)

Arai,

Miyamoto,

Kobayashi

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The reason why we select ISS as a 3D keypoint detection method is that performance of ISS is better than conventional ones, such as Harris3D, Lowe3D, curvature, and so on. Besides, as shown in [27], ISS is one of the most common and recent 3D keypoints detectors. Fig.…”

Section: Numerical Experimentsmentioning

confidence: 99%

“…The advantages of a 3D keypoint-based approach are widely recognized. Hence many types of 3D keypoint detection methods and 3D feature description algorithms have been proposed [21]- [26] and recently performance comparison among these methods have been performed [27], [28]. Each method of detecting 3D keypoint defines a 3D keypoint based on the local shape and provides an algorithm to detect it.…”

Section: Introductionmentioning

confidence: 99%

FAst Detection Algorithm for 3D Keypoints (FADA-3K)

2020

View full text Add to dashboard Cite

3D keypoint is widely used for object recognition and pose estimation with a 3D point cloud since it has robustness against measurement noise and occlusion. Many sets of 3D keypoints' definitions and the corresponding detection methods of 3D keypoints have been proposed. It is essentially important to select suitable 3D keypoint depending on a target object, scene situation, and 3D measurement system. While there have been a lot of useful methods for detecting 3D keypoints, detecting time is an issue, especially for real-time applications, such as robot vision. The detecting of 3D keypoints tends to entail a trade-off between computation time and the robustness of the 3D keypoint. To solve these problems, we propose a FAst Detection Algorithm for 3D keypoints named FADA-3K. A user can select one of the suitable 3D keypoints and the corresponding detection method which has been already proposed since FADA-3K can be implemented as an add-on of the existing detection methods. Numerical experiments show that FADA-3K can achieve about nine times faster detection than conventional approaches to detecting 3D keypoints. INDEX TERMS 3D keypoint, point cloud processing, robot vision, robotic bin-picking.

show abstract

“…These methods require 3D models of target objects and 6D pose estimation of the objects for robotic bin-picking. With the development of technology of three-dimensional measurements [12][13][14][15], a lot of techniques for pose estimation algorithms with 3D point cloud have been proposed, such as 3D feature [7,[16][17][18][19], 3D keypoint detection [20,21], segmentation [22,23], and Iterative Closest Point (ICP) [24], have been proposed. With the perfect knowledge of the object's 6D pose, the robot can grasp the object with pre-designed grasp configurations.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-based Fast Grasp Planning for Robotic Bin-picking by Small Data Set without GPU

Arai¹,

Zhao²,

Purnomo³

et al. 2021

Preprint

View full text Add to dashboard Cite

<div>This paper proposes a deep learning-based fast grasp detection method with a small dataset for robotic bin-picking. We consider the problem of grasping stacked up mechanical parts on a planar workspace using a parallel gripper. In this paper, we use a deep neural network to solve the problem with a single depth image. To reduce the computation time, we propose an edge-based algorithm to generate potential grasps. Then, a convolutional neural network (CNN) is applied to evaluate the robustness of all potential grasps for bin-picking. Finally, the proposed method ranks them and the object is grasped by using the grasp with the highest score. In bin-picking experiments, we evaluate the proposed method with a 7-DOF manipulator using textureless mechanical parts with complex shapes. The success ratio of grasping is 97%, and the average computation time of CNN inference is less than 0.23[s] on a laptop PC without a GPU array. In addition, we also confirm that the proposed method can be applied to unseen objects which are not included in the training dataset. </div>

show abstract

Performance Evalution of 3D Keypoint Detectors and Descriptors for Plants Health Classification

Cited by 9 publications

References 18 publications

Optimal Projection Pattern for Active Visual Servoing (AVS)

Optimal Projection Pattern for Active Visual Servoing (AVS)

FAst Detection Algorithm for 3D Keypoints (FADA-3K)

Deep Learning-based Fast Grasp Planning for Robotic Bin-picking by Small Data Set without GPU

Contact Info

Product

Resources

About