Enhanced Camera Capturing Using Object-Detection-Based Autofocus on Smartphones

Peng, Liang

doi:10.1109/acit-csii-bcd.2016.048

Cited by 6 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Active distance sensing uses active sensors such as radar or structured light to detect the distance between the target and the camera and adjust the focus accordingly. Phase detection uses light field sensors to measure the disparity between the current focus setting and the in focus setting [26,35,5]. Both active distance sensing and phase detection require additional hardware.…”

Section: Autofocusmentioning

confidence: 99%

An End-to-End Autofocus Camera for Iris on the Move

Wang¹,

Zhang²,

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

For distant iris recognition, a long focal length lens is generally used to ensure the resolution of iris images, which reduces the depth of field and leads to potential defocus blur. To accommodate users at different distances, it is necessary to control focus quickly and accurately. While for users in motion, it is expected to maintain the correct focus on the iris area continuously. In this paper, we introduced a novel rapid autofocus camera for active refocusing of the iris area of the moving objects using a focus-tunable lens. Our end-to-end computational algorithm can predict the best focus position from one single blurred image and generate a lens diopter control signal automatically. This scene-based active manipulation method enables real-time focus tracking of the iris area of a moving object. We built a testing bench to collect real-world focal stacks for evaluation of the autofocus methods. Our camera has reached an autofocus speed of over 50 fps. The results demonstrate the advantages of our proposed camera for biometric perception in static and dynamic scenes. The code is available at https://github.com/Debatrix/AquulaCam.

show abstract

Section: Autofocusmentioning

confidence: 99%

An End-to-End Autofocus Camera for Iris on the Move

Wang¹,

Zhang²,

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Increased pixel number and sensor size, as well as the widespread use of back-illuminated (BI) CMOS sensors to increase the fill factor and the signal-to-noise (SNR) performance created highly integrated electronic assemblies. A dedicated image signal processors (ISP) realizes real-time image processing such as denoising [6], autofocus [7] and image stabilization [8]. Together with recent advances in highly optimized objective lenses realized using a concatenation of multiple injection molded aspheric lenses [9], cellphone cameras aim to compete with digital still cameras and even digital single-lens reflex cameras (DSLR) over the last decade [10].…”

Section: Introduction To Modern Smartphonesmentioning

confidence: 99%

The power in your pocket – uncover smartphones for use as cutting-edge microscopic instruments in science and research

Wang

Heintzmann²,

Diederich³

2021

Advanced Optical Technologies

View full text Add to dashboard Cite

Since the development of the first light microscope over 400 years ago, the technology has continuously evolved and established itself as a powerful tool, especially in biology, diagnostics and point-of-care (PoC) applications. The miniaturization of mass-produced actuators and sensors enables the use of technically extremely complex functions in smartphones at a very low price. They can be used to implement modern microscopy methods for use in places where access to such techniques is often very limited. In this review, we show how easy it is to integrate a smartphone into the everyday microscopy-imaging routines of biology research. Such devices have also been used to identify diseases directly at the patient. Furthermore, we demonstrate how constantly increasing computing power in combination with the steadily improving imaging quality of cameras of handheld devices enables the realization of new biomedical imaging methods, which together with commercially available and 3D-printed components make current research available to a broad mass. Examples are smartphone-based super-resolution microscopy (SRM) or task-specific single-board computer-based devices, which can analyze plankton in sea water.

show abstract

Pixel2Field: Single Image Transformation to Physical Field of Sports Videos

Peng

2019

Advances in Visual Computing

View full text Add to dashboard Cite

Enhanced Camera Capturing Using Object-Detection-Based Autofocus on Smartphones

Cited by 6 publications

References 25 publications

An End-to-End Autofocus Camera for Iris on the Move

An End-to-End Autofocus Camera for Iris on the Move

The power in your pocket – uncover smartphones for use as cutting-edge microscopic instruments in science and research

Pixel2Field: Single Image Transformation to Physical Field of Sports Videos

Contact Info

Product

Resources

About