Edge detection for online image processing of a vision guide pick and place robot

Qul'am, Hasta Muzana; Dewi, Tresna; Risma, Pola; Oktarina, Yurni; Permatasari, Dewi

doi:10.1109/icecos47637.2019.8984522

Cited by 6 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…R. Kumar et al [9] developed the image processing algorithm for a pick-and-place robotic arm to sort objects based on their types and coordinates. H. M. Qul'am et al [10] discussed the use of the edge detection method as visual input for a 4 DOF robot manipulator tasked with picking and placing a tomato among three other objects. S. Chakole and N. Ukani [11] Described and explained a vision-based pick-andplace robot using an industrial ABB IRB 140 robot and a web camera.…”

Section: Related Workmentioning

confidence: 99%

Smart Robot Vision for a Pick and Place Robotic System

Mohammed¹,

AL-Khafaji²,

Abbas³

2023

ETJ

View full text Add to dashboard Cite

The movement of the 5 DOF robotic arm was controlled through the geometric approach in inverse kinematics analysis  HSV color space, a series of filters (M edian, Bilateral, and Gaussian), and the drawcontour method to discover objects' colors, shapes, and centroid were implemented.  The shapes and colors of the objects in different lighting conditions ranging from 5 to 7000 lux with an accuracy of 93.83% were discovered.The main contribution of this paper is to develop an innovative algorithm to accurately detect and identify the shape and color of objects under various light intensities and find their location to be manipulated by a pick-and-place robotic arm. Workpieces of various shapes and colors are dispersed on the robot's work plane and manipulated according to its specifications. The proposed algorithm utilizes the HSV color model to distinguish between different object colors and shapes. The S channel is used to detect the shapes of objects. After that, a series of filters (M edian, Bilateral, and Gaussian) are applied to reduce the noise of the segmented image to make the process of discovering the shap e and coordinates of the objects successful. The draw-contour method is used to discover the object's shapes. After the shape of the object is discovered, the centroid coordinates are calculated. After extensive testing on 354 images that are captured in various lighting conditions in the range of (5-7000 lux), the overall system performance of 93.83% is achieved, and the average execution time is 2.21s. Finally, we had a dependable flexible automatic pick and place system that could correctly detect and identify the objects based on their features.

show abstract

Section: Related Workmentioning

confidence: 99%

Smart Robot Vision for a Pick and Place Robotic System

Mohammed¹,

AL-Khafaji²,

Abbas³

2023

ETJ

View full text Add to dashboard Cite

show abstract

“…Image segmentation [5][14], blob analysis [10][19] [20], and edge detection [16]- [18] are among the standard method used for image processing. This paper proposes applying these methods for fruit detection, searches the fastest processing of those methods to detect and isolate the object, and overcomes the problems of occlusion and vegetation.…”

Section: Introductionmentioning

confidence: 99%

Image Processing Application on Automatic Fruit Detection for Agriculture Industry

Dewi¹,

Rusdianasari²,

Kusumanto³

et al. 2022

Atlantis Highlights in Engineering

Self Cite

View full text Add to dashboard Cite

The robot brings automation to every sector of human life, including agriculture. Automation in agriculture might be the solution to get a higher quality harvest and less dependency on human farming. The most suitable type of robot for harvesting is an arm robot manipulator. The harvesting robot needs "eye" to "see" the crop/fruit to be harvested. The detection is made possible by using image processing to get the fruit position. The fruit position is the input for a visual servoing robot. The image processing needs to be simple and effective to ensure less computational time to facilitate the limited memory of the available microcontroller. This paper proposes three image processing methods, i.e., image segmentation, edge detection, and blob analysis. The processes were conducted in SCILAB, and three fruit were used as the model, i.e., oranges, grapes, and tomato cherry. The results showed that all the fruit are detected and isolated by the vegetation background.

show abstract