Active Computer Vision by Cooperative Focus and Stereo

Krotkov, Eric

doi:10.1007/978-1-4613-9663-5

Cited by 224 publications

(112 citation statements)

References 0 publications

Supporting

Mentioning

109

Contrasting

Unclassified

Order By: Relevance

“…Various search strategies have been developed. The Fibonacci search is the best-known algorithm [5], which guarantees that the maximum of the criterion function is found within a known number of iterations depending only on the dynamic focus range. The hill-climbing search divides the procedure into two stages: out-of-focus region (coarse) search and focused region (fine) search.…”

Section: A Auto-focusing Techniquesmentioning

confidence: 99%

“…Fig. 1 depicts typical responses of the conventional Laplacian sharpness measure [5] for low (2.28×) and high (245× and 1500×) magnification sequences collected at uniformly sampled focus positions. Sharpness measures are the metric of choice when it comes to quantifying the degree of focus of an image.…”

Section: Introductionmentioning

confidence: 99%

“…Sharpness measures are widely used in auto-focusing systems, where they serve as evaluation functions to direct the search for the best camera focus [5,8]. Most of the measures perform global operations where the variations caused by noise, especially in smooth areas, are considered as sharpness content and usually result in artificially elevated sharpness values.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Extreme Zoom Surveillance: System Design and Image Restoration

Yao¹,

Abidi²,

Abidi³

2007

JMM

View full text Add to dashboard Cite

Abstract-Applications of digital imaging with extreme zoom are traditionally found in astronomy and wild life monitoring. More recently, the need for such capabilities has extended to long range surveillance and wide area monitoring such as forest fires, harbors, and waterways. In this paper, we present a number of sensor arrangements for such applications, focusing on optical setups, auto-focusing mechanisms, and image deblurring techniques. Considering both the speed of convergence and robustness to image degradations induced by high system magnifications and long observation distances, we introduce an auto-focusing algorithm based on sequential search with a variable step size. We derive the transition criteria following maximum likelihood (ML) estimation for the selection of suitable step sizes. The efficiency of the proposed algorithm is illustrated in real-time auto-focusing and tracking of faces from distances of 50m~300m.We also develop an image restoration algorithm for high magnification imaging systems, where an adaptive sharpness measure is employed as a cost function to guide the fine search for an optimal point spread function (PSF) for image deblurring. Experimental results demonstrate a considerably enhanced robustness to image noise and artifacts and ability to select the optimum PSF, producing superior restored images.

show abstract

Section: A Auto-focusing Techniquesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Extreme Zoom Surveillance: System Design and Image Restoration

Yao¹,

Abidi²,

Abidi³

2007

JMM

View full text Add to dashboard Cite

show abstract

“…The required parameters can be obtained through analysis of the physical characteristics of the sensor and through calibration (see, for example, [10,20,19,21]). A typical set of curves showing the dependency of the detection probability and of the range variance on the distance to the target being imaged is given in Fig.…”

Section: Stochastic Sensor Modelsmentioning

confidence: 99%

“…Aloimonos suggests that the composition of information from multiple views can be used to handle several ill-posed problems in Computer Vision [1]. Related research includes the development of recursive estimation procedures for robot perception [20,15,18]; methods for active sensor control, where specific parameters of the sensor system (such as camera aperture, focal distance, or sensor placement) can be changed under computer control [19,25]; development of theoretical foundations for coordination, integration and control of sensor systems [8,17,16]; and generation of optimal and adaptive sensing strategies [7,6,25].…”

Section: Introductionmentioning

confidence: 99%