TOF Image Processing With Shadow Compensation for Accurate Distance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

TOF cameras face accuracy issues in measuring distances due to objects obstructing light from reaching certain parts of the scene, leading to inaccuracies in distance data, particularly in applications like automatic milking systems.

Innovation Solution

An image processor adjusts distance data by using a lookup table to compensate for light sources that do not reach certain points, employing reverse ray-tracing to identify shadowing objects, and applying adaptation amounts based on light source combinations, enhancing accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If TOF camera measures distance using light reflection, then distance measurement is achieved, but accuracy deteriorates when objects obstruct light paths

Engineering Contradiction:
Improvedistance measurement accuracyVSAvoidlight obstruction by objects
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary identification of shadowing objects and pre-calculates compensation values before final distance measurement. By detecting objects that block light paths and determining their shadow regions in advance, the system can apply appropriate compensation to distance measurements in these regions, thereby maintaining accuracy despite light obstruction.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system introduces an intermediary compensation mechanism between the raw distance measurement and the final result. By calculating adaptation amounts based on shadowing object detection and light source geometry, the system mediates the effect of light obstruction, transforming inaccurate shadowed measurements into corrected accurate distance data.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Area of stationary object

If multiple light sources are used to illuminate the scene, then coverage is improved, but complexity of compensating for partial obstructions increases

Engineering Contradiction:
Improveillumination coverageVSAvoidcompensation calculation complexity
Core Design Contradiction:
Area of stationary objectVSDevice complexity

Solution Approach 1:

The system segments the scene into regions affected by different light sources and processes compensation for each light source independently. By calculating adaptation amounts for each light source separately based on its specific obstruction pattern, then combining these segmented results, the system manages the complexity of multiple light sources through systematic division of the compensation task.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system applies partial compensation actions by focusing computational resources only on regions shadowed by specific objects rather than processing the entire scene uniformly. By identifying and compensating only for the specific adaptation amounts needed in shadowed regions, the system avoids excessive computation while maintaining accuracy where it matters most.

Inventive Principle:
Principle #16Partial or excessive action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The solution provides high-accuracy distance data even in scenes with obstructing objects, improving the precision of milking robot operations by accurately determining teat positions for teat cup attachment.

Implementation Method 1

A TOF camera is a range imaging system that employs time-of-flight techniques to resolve distance between the camera and imaged objects for each point of the image. The TOF camera measures the round trip time of an artificial light signal provided by a laser or a light emitting diode (LED).

Methodology Applied
Scientific EffectTime of flight: Time of Flight

Implementation Method 2

The TOF camera measures the round trip time of an artificial light signal provided by a laser or a light emitting diode (LED).

Methodology Applied
Scientific EffectLight reflection: Reflection

Data Source

PatentEP4229443B1Image processor and computer-implemented image processing method
Publication Date: 2025.08.13 DELAVAL HLDG AB
  • EP4229443B1 patent drawingFigure 1~4
  • EP4229443B1 patent drawingFigure 5a~7
  • EP4229443B1 patent drawingFigure 8~10

AI summary

An image processor (140) obtains image data (Dimg) registered by a time-of-flight, TOF, imaging system (110). The image data (Dimg) represents a scene (100) illuminated by at least two light sources (121, 122, 123, 124) calibrated to enable the image pro-cessor (140) to include distance data in the image data (Dimg), which distance data expresses respective distances from the TOF imaging system (110) to points on imaged objects. The image processor (140) determines if a shadow effect exists by which at least one first object (TC) in the scene (100) obstructs light from at least one light source (121, 122, 123, 124) of the at least two light sources (121, 122, 123, 124) from reaching at least one part of at least one second object in the scene (100) and be reflected there from into the TOF imaging system (110). If it is determined that the shadow effect exists, the image processor (140) adjusts the distance data to compensate for the at least one light source (121, 122, 123, 124) whose light did not reach the at least one part of the at least one second object.