Multi-Focal Obstacle Sensing Using Combined Camera Tracking

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing unmanned vehicle sensing systems face a challenge in balancing the field of view and sight distance when using either a camera with a short focus lens or a long focus lens for obstacle detection and tracking, as a camera with a short focus lens provides a wide field of view but a short sensing distance, while a camera with a long focus lens offers a narrow field of view but a longer sensing distance.

Innovation Solution

A method and device for multi-focal sensing that utilizes both a camera with a long focus lens and a camera with a short focus lens to acquire detection results, perform target tracking, match and combine tracking sequences based on Intersection over Union (IoU) calculations, and incorporate new detection results to create a combined tracking sequence, effectively addressing the trade-off between field of view and sight distance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If a camera with short focus lens is used for obstacle detection and tracking, then the field of view is wide and obstacles are not cut off, but the sensing distance is too short

Engineering Contradiction:
Improvefield of viewVSAvoidsensing distance
Core Design Contradiction:
Area of stationary objectVSLength of stationary object

Solution Approach 1:

The patent combines multiple cameras with different focus lenses (short focus and long focus) into a unified sensing system. The short focus camera provides wide field of view for detecting obstacles within close range, while the long focus camera extends the sensing distance for medium and long distance obstacles. The system merges the detection results from both cameras to achieve comprehensive obstacle coverage across different distances.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The sensing system is designed to perform multiple functions using different camera configurations. The short focus camera handles close-range obstacle detection with wide coverage, while the long focus camera handles medium and long distance detection. This multi-functional approach allows a single system to address various detection scenarios that would otherwise require separate systems.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Length of stationary object

If a camera with long focus lens is used for obstacle detection and tracking, then the sensing distance is long and small obstacles can be detected, but the field of view is narrow

Engineering Contradiction:
Improvesensing distanceVSAvoidfield of view
Core Design Contradiction:
Length of stationary objectVSArea of stationary object

Solution Approach 1:

The patent merges the capabilities of long focus and short focus cameras to compensate for the narrow field of view limitation. The long focus camera provides extended sensing distance and detects small obstacles, while the short focus camera simultaneously provides wide field of view coverage. By combining results from both cameras, the system achieves both long sensing distance and adequate field of view.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent segments the obstacle detection task across multiple cameras with different focus characteristics. The long focus camera is assigned to detect medium and long distance obstacles, while the short focus camera handles close-range obstacles. This segmentation allows each camera to operate in its optimal performance range, and the results are integrated to provide comprehensive coverage.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS11126875B2Method and device of multi-focal sensing of an obstacle and non-volatile computer-readable storage medium
Publication Date: 2021.09.21 APOLLO INTELLIGENT DRIVING (BEIJING) TECHNOLOGY CO LTD
  • US11126875B2 patent drawing
  • US11126875B2 patent drawing
  • US11126875B2 patent drawing

AI summary

A method and device of multi-focal sensing of an obstacle. A method includes acquiring detection results of obstacles at multiple moments by utilizing a camera with long focus lens and a camera with short focus lens; performing a target tracking to the acquired detection results, to obtain at least two tracking sequences, wherein each tracking sequence includes detection results acquired at the multiple moments for a same obstacle; and matching two random tracking sequences of the at least two tracking sequences, and combining the two random tracking sequences into a combined tracking sequence, if the matching is successful.