Capsovision Inc.

Dinoplusai Holdings Limited

Tong Wu

Kang-Huai Wang

Chung Kuang Chin

Clifford M Gold

Yujie Hu

Xiaosong Wang

Zongwei Zhu

Steven Sertillange

Yick Kei Wong

Embodiments described herein provide a mission-critical artificial intelligence (AI) processor (MAIP), which includes an instruction buffer, processing circuitry, a data buffer, command circuitry, and communication circuitry. During operation, the instruction buffer stores a first hardware instruction and a second hardware instruction. The processing circuitry executes the first hardware instruction, which computes an intermediate stage of an AI model. The data buffer stores data generated from executing the first hardware instruction. The command circuitry determines that the second hardware instruction is a hardware-initiated store instruction for transferring the data from the data buffer. Based on the hardware-initiated store instruction, the communication circuitry transfers the data from the data buffer to a memory device of a computing system, which includes the mission-critical processor, via a communication interface.

Mission-critical AI processor with record and replay support

Systems and methods are provided for motion detection and capture control of video data from a capsule camera system having an on-board storage. The capsule camera system moves through the GI tract under the action of peristalsis and records images of the intestinal walls. The capsule's movement is episodic and jerky. The capacity of the on-board storage is limited. In order to avoid unnecessary capture of images when the capsule camera moves very slowly or stalls, motion detection technique is utilized to help control image capture. Furthermore, an adaptive capture control is disclosed that automatically adjusts the threshold level of capture control to maintain proper image capture. The invented capture control also conserves precious battery power by eliminating capture of unnecessary images when the capsule camera moves too slowly or stalls. The present invention of image capture control and threshold update is also applicable to a capsule camera system having a wireless transmitter instead of an on-board storage.

Image capture control for in vivo autonomous camera

Growing community of inventors

Fremont, CA, United States of America

Tong Wu