In-Vehicle Pointing Recognition for Moving Target Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional technologies struggle to accurately identify target objects pointed to by a vehicle occupant due to deviations between intended and actual pointing directions, especially when the vehicle is in motion, making it difficult to pinpoint specific objects.
Innovation Solution
A data processing device that includes a vehicle location detecting unit, occupant recognition unit, estimation unit, and object recognition unit to efficiently identify target objects by setting a designated region based on the relationship between the occupant's pointing direction and the vehicle's facing direction, utilizing voice recognition to narrow down candidates, and adjusting the region size based on vehicle speed and direction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If the vehicle is traveling, then the system can provide navigation and location services, but the positional relation between the target object and the vehicle changes every second, causing deviation between the user's intended direction and the actual pointing direction
Solution Approach 1:
The patent applies dynamics by making the designated region adaptive and changeable based on vehicle speed and pointing direction. The region is not fixed but dynamically adjusts its size and shape according to real-time vehicle conditions, allowing the system to accommodate the changing positional relations during vehicle motion while maintaining accurate target identification
Solution Approach 2:
The patent changes parameters by adjusting the size and shape of the designated region based on vehicle speed and pointing direction angles. By varying these geometric parameters dynamically, the system compensates for the deviation caused by vehicle motion, transforming a static pointing problem into a dynamically adjustable solution
2Measurement precision
If the system uses a fixed small designated region based on pointing direction, then the measurement precision is high, but the target object cannot be identified when the vehicle is moving and the positional relation changes
Solution Approach 1:
The designated region transitions from a fixed static shape to a dynamic adaptive region that changes based on vehicle speed and pointing direction. This dynamic adjustment allows the system to maintain measurement precision while adapting to motion conditions, solving the contradiction between precision and adaptability
Solution Approach 2:
The system changes the parameters of the designated region (size, shape, orientation) based on vehicle speed and pointing angle. This parameter adjustment allows the region to expand or contract appropriately, maintaining precision for stationary targets while becoming more adaptable for moving vehicle conditions
3Measurement precision
If the system narrows down target object candidates to one specific object, then the identification accuracy is high, but it becomes difficult to identify the intended target when the vehicle is moving and multiple objects pass by
Solution Approach 1:
The system performs preliminary action by pre-defining the designated region based on the occupant's pointing direction and vehicle parameters before the vehicle reaches the target object. This advance preparation allows the system to have candidate objects ready for identification, reducing the time needed when the vehicle is in motion and multiple objects are passing by
Solution Approach 2:
The system uses feedback by continuously monitoring the vehicle's position, speed, and the occupant's pointing direction to adjust the designated region in real-time. This feedback mechanism ensures that the correct target object is identified even when multiple objects are in proximity, maintaining accuracy while reducing identification time through continuous optimization
Data Source
AI summary
A data processing device and method that detect a location and direction of a vehicle, recognize an action by an occupant of the vehicle in the form of pointing outside the vehicle, estimate a likely designated region indicated by the occupant that is based on the recognition results and the vehicle location, recognize a target object candidate from the designated region indicated by the occupant; and output information regarding the target object candidate. The size of the designated region is differentiated based on the relationship between the direction pointed at by the occupant and the direction of the vehicle.


