Cloud-Based Vision System for Blind Spot Video Coverage

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users of portable devices, such as mobile phones and automobiles, face challenges in obtaining real-time video feeds of areas outside their field of view, which can lead to safety issues like entering unknown environments or reversing into blind spots without adequate visual information.

Innovation Solution

A system that allows devices to request and receive real-time video streams from other devices within a network, using a cloud-based peer-to-peer communication method, by specifying the location and desired angle of the region of interest, and selecting cameras with matching views to provide live video feeds.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If a user requests real-time video streams from multiple cameras to view areas outside their field of view, then the user receives comprehensive visual information, but the bandwidth consumption increases significantly

Engineering Contradiction:
Improvevisual informationVSAvoidbandwidth consumption
Core Design Contradiction:
Loss of informationVSLoss of energy

Solution Approach 1:

The system applies local quality by selectively transmitting video streams only from cameras that capture regions of interest, rather than broadcasting from all cameras. Each camera's video stream is evaluated based on whether its field of view contains relevant areas, and only matching streams are transmitted to the requesting device, optimizing bandwidth usage while maintaining comprehensive visual coverage.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system uses partial action by transmitting only the necessary portion of video data - specifically, only video streams from cameras whose fields of view intersect with requested regions of interest. This avoids the excessive transmission of all available camera feeds, reducing bandwidth consumption while still providing complete visual information about areas outside the user's field of view.

Inventive Principle:
Principle #16Partial or excessive action

2Loss of information

If the system transmits video streams from all available cameras, then complete coverage is achieved, but the device complexity and processing requirements increase

Engineering Contradiction:
Improvevideo coverageVSAvoidsystem complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The system performs preliminary action by pre-determining which cameras should transmit video streams based on their field of view characteristics and the requested regions of interest. This selection process occurs before video transmission begins, allowing the system to establish an optimized set of active cameras that will provide complete coverage without requiring complex real-time decision-making during operation.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If cameras with overlapping fields of view transmit video streams, then redundant visual information is provided, but bandwidth is wasted

Engineering Contradiction:
Improvevisual information reliabilityVSAvoidbandwidth usage
Core Design Contradiction:
ReliabilityVSLoss of energy

Solution Approach 1:

The system applies local quality by evaluating each camera's specific contribution to the requested regions of interest. Even when cameras have overlapping fields of view, the system determines which cameras should transmit based on whether they provide unique or necessary coverage of specific areas, rather than简单地 excluding all overlapping cameras. This ensures reliable visual information while avoiding redundant bandwidth consumption.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP3479585B1Cloud based vision
Publication Date: 2021.12.15 QUALCOMM INC
  • EP3479585B1 patent drawingFigure 1
  • EP3479585B1 patent drawingFigure 2
  • EP3479585B1 patent drawingFigure 3

AI summary

A method for receiving a real-time video feed of a region of interest includes generating, at a processor of a first device, a request for a real-time video stream of the region of interest. The request indicates a location of the region of interest. The method also includes transmitting the request to one or more other devices via a network to query whether another device is situated to capture a portion of the region of interest. The method also includes receiving the real-time video stream of the region of interest from a second device of the one or more other devices. The second device includes a camera having a field of view that includes at least a portion of the region of interest.