Oriented Bounding Box Tool Gesture Interface
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing interface tools for defining bounding boxes around objects in images, especially oriented bounding boxes, are inefficient and require multiple adjustments, making the labeling process time-consuming and complex, especially when dealing with tilted or rotated objects.
Innovation Solution
A virtual tool that allows users to define bounding boxes using a 'one-shot' gesture, where a first input point defines a corner, a movement input sets the edge angle, and a second input point defines the opposite corner, automatically generating the bounding box with optimized orientation, reducing the need for subsequent adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional interface tools are used to define oriented bounding boxes, then the bounding box orientation can be defined, but the labeling process becomes time-consuming and complex requiring multiple adjustments
Solution Approach 1:
The system performs preliminary computation of the bounding box orientation and parameters based on the gesture input trajectory before the user completes the selection. The processor calculates the oriented bounding box parameters (rotation angle, center position, dimensions) in advance during the gesture drawing phase, so that when the gesture is completed, the bounding box is immediately rendered in the correct orientation without requiring subsequent adjustments or iterative refinement.
2Ease of manufacture
If traditional interface tools are used to define bounding boxes, then the bounding box can be created, but multiple adjustments are required making the process complex
Solution Approach 1:
The system replaces traditional mechanical interaction methods (clicking corners, manually rotating, dragging edges) with a gesture-based input system. The gesture input device captures continuous trajectory data that directly translates to bounding box parameters through computational processing, eliminating the need for multiple discrete adjustment operations and simplifying the user interaction model.
Solution Approach 2:
The system automatically computes and adjusts the bounding box parameters based on the gesture input trajectory without requiring user intervention for each adjustment. The processor self-adjusts the bounding box orientation, position, and dimensions by interpreting the gesture path, making the tool self-sufficient and reducing the cognitive load on the user.
3Measurement precision
If oriented bounding boxes are used to define object orientation, then accurate representation of tilted objects is achieved, but the labeling task complexity increases
Solution Approach 1:
The system changes the parameter representation method by deriving bounding box parameters (rotation angle, center coordinates, width, height) directly from the continuous trajectory of the gesture input rather than from discrete corner points. This parameter transformation approach maintains precise orientation representation while simplifying the operational process, as the gesture naturally encodes all necessary parameters in a single continuous motion.
Data Source
AI summary
Systems and methods for an improved bounding box tool. The system can have processors configured to display a user interface on a display of a device, the user interface displaying image data. The processor can activate a virtual tool to define a bounding box. The processor can receive a first input data point at a first location relative to the image data. This can be defined by actuation of the input device. The processor can receive a movement input in a direction relative to the first location. The movement input can be defined by movement commands from the input device. The processor can receive a second input data point at a second location relative to the image data. The second input data point can be triggered by a second actuation of the input device. The processor can display, at the user interface, a graphical object representing the bounding box as an overlay of the image data. The bounding box can have corners defined by the first location and the second location. Edges (and angles thereof) of the bounding box can be defined by the direction of the movement input.