Environment Recognition System With Distance-Adaptive Noise Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing environment recognition systems for automatic berthing systems are hindered by optical noises such as waves and splashes, leading to inaccurate detection of obstacles and unreliable navigation of watercraft to berthing spaces.
Innovation Solution
An environment recognition system with a variable noise cutting process that adjusts the threshold level based on distance to detect genuine obstacles by filtering out low-intensity noise signals, using a lidar and camera system to create accurate 3-D and 2-D maps for reliable navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a suitable threshold value process or filtering process is applied to eliminate optical noises, then the reliability of noise elimination is improved, but the resolution power for environment recognition deteriorates
Solution Approach 1:
The patent applies dynamics by making the noise cutting degree variable rather than fixed. The controller adjusts the noise cutting degree dynamically based on the distance between the watercraft and detected objects. Near objects receive stronger noise cutting to eliminate water surface noises, while distant objects receive weaker noise cutting to preserve detection accuracy. This dynamic adjustment resolves the contradiction between reliable noise elimination and maintaining resolution power.
Solution Approach 2:
The patent applies local quality by applying different noise cutting degrees to different spatial regions. Objects at different distances from the watercraft receive different levels of noise filtering. The system selectively applies strong noise cutting only to nearby regions where water surface noises are most problematic, while maintaining weaker noise cutting for distant regions where genuine obstacles need to be detected with high precision.
2Reliability
If strong noise cutting is applied to eliminate water surface noises, then the reliability of obstacle detection is improved, but the detection accuracy of genuine obstacles deteriorates
Solution Approach 1:
The system dynamically adjusts the noise cutting degree based on object distance. For nearby objects where water surface noises dominate, strong noise cutting is applied to improve detection reliability. For distant objects where genuine obstacles are more likely to be detected, weaker noise cutting is applied to maintain detection accuracy. This dynamic approach resolves the contradiction between reliability and accuracy.
Solution Approach 2:
The patent changes the parameter of noise cutting degree based on the distance parameter to objects. By making the noise cutting parameter variable rather than constant, the system can optimize both reliability and accuracy for different spatial zones. The controller modifies the threshold parameters adaptively, applying stronger filtering when needed for reliability while preserving weaker filtering for accuracy-critical regions.
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 system effectively filters out noise, enabling accurate detection of berthing spaces and obstacles, ensuring reliable navigation of watercraft to selected berthing spaces.
Implementation Method 1
a lidar system is employed for avoiding obstacles and navigating the ship to the designated docking spot
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An environment recognition system, comprising: an environment recognition device that is configured to transmit electromagnetic wave in a predetermined direction to generate a detection signal corresponding to objects existing in an environment; and a main controller 21 that generates a recognition signal corresponding to the detection signal, wherein the main controller is provided with a variable noise cutting circuit for the detection signal, and configured to change a property of the noise cutting circuit according to a distance to each object to be detected.