Underwater Depth Perception with Onboard Multi-Sensor Computing
Solution Overview
Problem
Existing underwater depth perception technologies rely heavily on remote computing, leading to delays and insufficient real-time feedback, and often lack detail and specificity, making navigation and object detection challenging.
Innovation Solution
Implementing systems with multiple image sensors or a combination of an image sensor and a complementary sensor, along with onboard computing systems, to provide real-time underwater depth perception and enhance navigation capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple sensors of varying types are used for underwater depth perception, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent combines multiple image sensors (e.g., stereo cameras, multi-view cameras) into an integrated depth perception system. By merging multiple sensors that capture images from different positions or angles, the system achieves accurate depth measurement without requiring disparate sensor types, thus improving precision while managing complexity through unified processing architecture
Solution Approach 2:
The image sensors are designed to serve multiple functions: capturing color images, extracting depth information, and providing spatial awareness. This multi-functionality allows a single sensor type to replace what would traditionally require multiple specialized sensors, reducing overall system complexity while maintaining measurement precision
2Device complexity
If remote computing is used for depth perception processing, then device complexity is reduced, but response time increases
Solution Approach 1:
The computing task is segmented between onboard processing and remote processing. Critical real-time functions such as depth map generation and immediate collision detection are performed onboard using dedicated hardware accelerators, while less time-sensitive analysis and long-term data processing are handled remotely. This segmentation enables real-time response for navigation-critical functions while maintaining system simplicity
Solution Approach 2:
A local computing unit or edge computing device serves as an intermediary between the sensors and remote cloud processing. This intermediary performs preliminary processing of sensor data, extracting essential depth information locally before transmitting processed results to remote systems, thereby reducing communication delays and enabling real-time navigation decisions
Data Source
AI summary
Systems described herein use either multiple image sensors or one image sensor and a complementary sensor to provide underwater depth perception. The systems include a computing system that provides the underwater depth perception based on data sensed by the multiple image sensors or the one image sensor and the complementary sensor. The systems can include a submersible device (such as a submersible mobile machine) that includes a holder configured to hold the one image sensor. The holder can be configured to hold the computing system in addition to the one image sensor. And, in some embodiments, the holder is configured to hold the complementary sensor in addition to the computing system and the one image sensor. Alternatively, in some embodiments, the holder is configured to hold the multiple image sensors. And, the holder can be configured to hold the computing system in addition to the multiple image sensors.