Single camera-based object detection and tracking for mobile robots

Anderson, J. Keith; Iftekharuddin, Khan M.; Threlkeld, Elizabeth; Montgomery, Brad

doi:10.1117/12.795123

Cited by 2 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The background is based on a reference region, which is defined as a trapezoidal area in front of the camera. In [ 13 ], the same approach is used to model the background and adds tracking of corner features to navigate a mobile robot. In [ 9 ], both a simplified and an incremental version of the background model are presented.…”

Section: Methodsmentioning

confidence: 99%

“…Like the algorithms described in [ 9 , 13 ], we assume that the background may be represented by an appearance model. This is a strong assumption for an outdoor environment; however, it exploits the homogeneity of a row crop field.…”

Section: Methodsmentioning

confidence: 99%

“…In the initial frame, the reference region is defined as a specified region close to the camera, comparable to the methods in [ 9 , 13 ]. In Figure 5 , the initial reference region is shown.…”

Section: Methodsmentioning

confidence: 99%

“…Hence, spatial information alone is not useful for recognizing these regions in the image as an obstacle. Other monocular-based obstacle detection algorithms include appearance-based models [ 9 , 13 ], thresholding in the HSI (hue, saturation and intensity) color space [ 10 ] and relative size [ 14 ].…”

Section: Introductionmentioning

confidence: 99%

“…These approaches are not suitable for moving cameras, since the assumptions for static setups are violated. In [ 9 , 13 ], a background model for moving cameras is presented. Here, the model is based on background appearance and found via histogram methods.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Detection of Bird Nests during Mechanical Weeding by Incremental Background Modeling and Visual Saliency

Steen

Therkildsen

Green³

et al. 2015

Sensors

View full text Add to dashboard Cite

Mechanical weeding is an important tool in organic farming. However, the use of mechanical weeding in conventional agriculture is increasing, due to public demands to lower the use of pesticides and an increased number of pesticide-resistant weeds. Ground nesting birds are highly susceptible to farming operations, like mechanical weeding, which may destroy the nests and reduce the survival of chicks and incubating females. This problem has limited focus within agricultural engineering. However, when the number of machines increases, destruction of nests will have an impact on various species. It is therefore necessary to explore and develop new technology in order to avoid these negative ethical consequences. This paper presents a vision-based approach to automated ground nest detection. The algorithm is based on the fusion of visual saliency, which mimics human attention, and incremental background modeling, which enables foreground detection with moving cameras. The algorithm achieves a good detection rate, as it detects 28 of 30 nests at an average distance of 3.8 m, with a true positive rate of 0.75.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations