17933941. Sensor Cropped Video Image Stabilization (VIS) simplified abstract (Apple Inc.)

Sensor Cropped Video Image Stabilization (VIS)

Organization Name

Apple Inc.

Inventor(s)

Patrick A. Carroll of Scotts Valley CA (US)

Ajay Ramesh of San Jose CA (US)

Ashwini Dwarakanath of Cupertino CA (US)

David A. Silverstein of Palo Alto CA (US)

David R. Pope of Campbell CA (US)

Michael W. Tao of San Jose CA (US)

Terence N. Tam of Santa Clara CA (US)

Vitanshu Sharma of Cupertino CA (US)

Sensor Cropped Video Image Stabilization (VIS) - A simplified explanation of the abstract

This abstract first appeared for US patent application 17933941 titled 'Sensor Cropped Video Image Stabilization (VIS)

Simplified Explanation

Devices, methods, and non-transitory program storage devices are disclosed herein to perform predictive image sensor cropping operations to improve the performance of video image stabilization operations, especially for high resolution image sensors. According to some embodiments, the techniques include, for each of one or more respective images of a first plurality of images: obtaining image information corresponding to one or more images in the first plurality of images captured prior to the respective image; predicting, for the respective image, an image sensor cropping region to be read out from the first image sensor; and then reading out, into a memory, a first cropped version of the respective image comprising only the predicted image sensor cropping region for the respective image. Then, a first video may be produced based, at least in part, on the first cropped versions of the one or more respective images of the first plurality of images.

• Predictive image sensor cropping operations to enhance video image stabilization for high resolution image sensors
• Obtain image information for images captured prior to the current image
• Predict image sensor cropping region for the current image
• Read out a cropped version of the current image into memory
• Produce a video based on the cropped versions of the images

Potential Applications

This technology can be applied in:

• Video recording devices
• Surveillance systems
• Drones and aerial photography

Problems Solved

• Improved video image stabilization
• Enhanced performance for high resolution image sensors

Benefits

• Higher quality stabilized videos
• Efficient use of memory and processing resources

Potential Commercial Applications

Optimizing video recording devices for professional use

Possible Prior Art

There may be prior art related to image cropping techniques for video stabilization, but specific examples are not provided in this abstract.

Unanswered Questions

=== How does this technology compare to traditional image stabilization methods? Traditional image stabilization methods typically involve post-processing techniques to reduce shakiness in videos. This technology, on the other hand, focuses on predictive image sensor cropping to improve stabilization during the capture process. By cropping the image based on predicted sensor regions, it aims to provide more efficient and effective stabilization in real-time.

=== What impact does this technology have on battery life in devices? Since predictive image sensor cropping can optimize the processing and memory usage during video capture, it may potentially lead to improved battery life in devices by reducing the computational load required for stabilization. However, the actual impact on battery life would depend on various factors such as the device's overall power consumption and usage patterns.

Original Abstract Submitted

Devices, methods, and non-transitory program storage devices are disclosed herein to perform predictive image sensor cropping operations to improve the performance of video image stabilization operations, especially for high resolution image sensors. According to some embodiments, the techniques include, for each of one or more respective images of a first plurality of images: obtaining image information corresponding to one or more images in the first plurality of images captured prior to the respective image; predicting, for the respective image, an image sensor cropping region to be read out from the first image sensor; and then reading out, into a memory, a first cropped version of the respective image comprising only the predicted image sensor cropping region for the respective image. Then, a first video may be produced based, at least in part, on the first cropped versions of the one or more respective images of the first plurality of images.