Ambarella‘s patent involves an apparatus with an interface, light projector, and processor to generate depth maps using structured light patterns. The technology detects face sizes, determines scale ratios, and downscales images for accurate depth pixel generation, preventing block match failures. GlobalData’s report on Ambarella gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Ambarella, Cloud gaming was a key innovation area identified from patents. Ambarella's grant share as of January 2024 was 87%. Grant share is based on the ratio of number of grants to total number of patents.

Depth mapping using structured light pattern projection

Source: United States Patent and Trademark Office (USPTO). Credit: Ambarella Inc

A recently granted patent (Publication Number: US11880992B2) discloses an innovative apparatus designed for facial recognition technology. The apparatus includes an interface for receiving pixel data, a structured light projector to generate a structured light pattern, and a processor that processes the pixel data in video frames with the structured light pattern. The processor performs computer vision operations to detect the size of a face area in the video frames, determines a scale ratio based on the face area size, extracts the structured light pattern, generates a downscaled structured light image, and produces a depth map using the downscaled structured light image and a downscaled reference image. The downscaled structured light image is created with a sufficient number of depth pixels to prevent block match failure, ensuring accurate depth calculations for applications like liveness detection.

Furthermore, the apparatus's unique downscale operation reduces the number of calculations required to generate the depth map, optimizing processing efficiency. The scale ratio is dynamically adjusted based on the face area size, enabling the depth map to be created at various resolutions corresponding to the size of the face area. This adaptive approach ensures consistent face depth resolution, simplifying post-processing operations like liveness detection. The downscaled structured light image maintains the aspect ratio of the structured light pattern after a cropping operation, enhancing accuracy in facial recognition applications. Overall, the patented apparatus offers a sophisticated solution for facial depth mapping with improved efficiency and accuracy, making it a valuable addition to the field of computer vision technology.

To know more about GlobalData’s detailed insights on Ambarella, buy the report here.

Premium Insights

From

The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.

GlobalData

GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.