An approximation based algorithm for minimum bounding rectangle computation

Kala, Jules Raymond; Viriri, Serestina; Tapamo, Jules-Raymond

doi:10.1109/icastech.2014.7068101

Cited by 7 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To simplify the issue we studied, as illustrated in Fig. 4, the 2D projection model of an obstacle is represented as a 6-tuple < rec, c, v, l, w, β >, where rec denotes the convex polygon's minimum bounding rectangle which can be found by using algorithm in literature [23], c is the center point of rec, we also let it denote the obstacle and the convex polygon, l and w respectively denote the length and width of rec, v = {v j } j=1•••J denotes all vertices of the convex polygon c, β represents the rotation angle of the straight line formed by these two vertices with maximum Euler distance.…”

Section: B 2d Projection Model Of Obstaclementioning

confidence: 99%

Unraveling Impact of Critical Sensor Density on Occlusion Coverage of Partial Targets for Directional Sensor Networks

Liu,

Cao,

Liu

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Coverage is a prominent indicator for measuring the quality of service in directional sensor networks. From the perspective of energy and deployment costs, full coverage may be expensive or unrealistic, partial coverage can operate more energy-efficient by scheduling working status of sensors. In certain practical application scenarios, irregular obstacles like trees, mountains, buildings, and vehicles, which have adverse influence on QoC, often exist in the field of interest (FoI). Meanwhile, due to sensors may fall near the border of the FoI, it also has effect on the coverage contribution. In this paper, we assume that sensors are randomly deployed in a square FoI with irregular shape obstacles existence, and introduce the concept of occlusion coverage of partial targets. Afterwards, we take the border effects into account and derive the critical sensor density for achieving an expected coverage ratio with a high probability. Finally, we conduct a series of simulation experiments to verify the accuracy between simulation results and numerical results, and take analysis of mean absolute error between them. The results show that our method has good performance on estimating critical sensor density.INDEX TERMS directional sensor networks, target coverage, critical sensor density, irregular obstacles, border effects

show abstract

Section: B 2d Projection Model Of Obstaclementioning

confidence: 99%

Unraveling Impact of Critical Sensor Density on Occlusion Coverage of Partial Targets for Directional Sensor Networks

Liu,

Cao,

Liu

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…To overcome these limitations, deep learning provided practical solutions to some of the most challenging problems in recent years. Deep learning can automatically extract features and has great advantages over traditional image processing methods [5][6][7]. It has been successfully used to detect defects in apples, cucumbers, and carrots [8].…”

Section: Introductionmentioning

confidence: 99%

Defect Detection and Size Grading of Harvested Japanese Yam Using Computer Vision Technology

2023

AJALS

View full text Add to dashboard Cite

Root crop yield estimate and harvest technology, especially Japanese Yam harvest production, has a high demand for intelligent automation systems. This paper develops a Japanese Yam quality grading system based on computer vision and deep learning, which can automatically detect the shape and quality of Japanese Yam and grade the size of harvested. Specifically, based on Shuffle-Net and transfer learning, a lightweight deep learning model (CDD Net) was constructed to detect surface and shape defects of Japanese Yam. It's methods were also proposed based on minimum bounding rectangle (MBR) fitting and convex polygon approximation. Experimental results showed that the detection accuracy of the proposed CDD Net was 98.94% for binary classification (normal and defective) and 92.92% for multi-class classification (normal, curve, fork root, fracture), and demonstrated good performance both in time efficiency and detection accuracy. The size accuracy of MBR fitting and convex polygon approximation was 92.8% and 95.1% respectively. This study provides a practical method for defect detection and size grading, which has great potential for application in yield estimation of root crops.

show abstract