Pedestrian Obstacle Detection via Acoustic and Visual Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing smartphone applications fail to provide real-time warnings to distracted users who are approaching obstacles while using their devices, as they rely on passive methods that do not work during active tasks or in environments where background changes are not allowed, leading to a higher risk of collisions.
Innovation Solution
A computer-implemented system using a mobile app, BumpAlert, which employs a motion estimator, acoustic detector, and motion filter to identify obstacles by emitting and detecting acoustic signals, and a visual detector to confirm object presence through camera image data, generating alerts when obstacles are within a certain distance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If passive methods are used to detect obstacles by showing rear camera view in background, then device complexity is reduced, but reliability of obstacle detection is insufficient because it cannot actively alert users in real time when focused on tasks
Solution Approach 1:
The system segments the detection function into multiple independent modules: acoustic detector for sound-based obstacle detection, visual detector for camera-based detection, and motion filter for processing data from both sensors. This segmentation allows each module to specialize in specific detection tasks while maintaining overall system reliability without requiring a monolithic complex system.
Solution Approach 2:
The patent merges acoustic detection and visual detection capabilities into a unified obstacle detection system. The motion filter combines data from both acoustic and visual detectors to make comprehensive obstacle identification, improving reliability by cross-validating detections from multiple sensor types rather than relying on a single detection method.
2Ease of operation
If background changes are not allowed in applications like games, then ease of operation is improved, but obstacle detection capability is lost because passive methods cannot work when background is fixed
Solution Approach 1:
The system replaces the mechanical approach of changing background images (which requires user interaction and breaks immersion in games) with acoustic field-based detection. The acoustic detector emits sound waves that reflect off obstacles, providing detection capability without modifying the visual background, thus maintaining ease of operation while ensuring detection reliability.
Solution Approach 2:
Sound waves serve as an intermediary medium between the device and obstacles. Instead of directly manipulating the visual background to detect obstacles, the system uses acoustic waves as a mediator that can penetrate through the fixed background of games and other applications to detect obstacles in the environment, resolving the conflict between usability and detection capability.
3Measurement precision
If acoustic signals are emitted and detected to determine distance to objects, then measurement precision of distance is improved, but use of energy increases due to continuous sensor operation
Solution Approach 1:
The acoustic detector operates periodically rather than continuously, emitting sound waves at intervals to detect obstacles. The motion filter processes acoustic and visual data at regular time intervals, updating obstacle detection results periodically. This periodic operation maintains measurement precision for distance measurement while significantly reducing energy consumption compared to continuous sensor operation.
Solution Approach 2:
The system performs preliminary actions by pre-processing sensor data and pre-establishing detection thresholds before actual obstacle detection is needed. The motion filter pre-processes acoustic and visual signals to identify potential obstacles, allowing the main detection function to operate more efficiently with lower energy consumption while maintaining precision through the pre-established processing framework.
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
Effectively alerts users in real-time of nearby obstacles, reducing the risk of collisions by utilizing readily available smartphone sensors and providing accurate distance measurements, even in noisy environments, while minimizing false positives through fusion of acoustic and visual detection.
Implementation Method 1
The acoustic detector is also interfaced with a microphone in the handheld computing device and operates to detect the acoustic signals reflected by objects proximate to the handheld computing device. In response to detected acoustic signals, the acoustic detector determines distance to a given object using timing between the emitted acoustic signals and the detected acoustic signals.
Data Source
AI summary
Studies have shown that using smartphones while walking increases the probability of pedestrians colliding with obstacles. Techniques are presented for providing real-time warnings to distracted users of smartphones. The techniques are implemented by an application which makes use of sensors commonly found in most smartphone. By estimating distances to nearby objects using acoustic signals, a generalized solution is achieved without requiring any prior knowledge of the user's environment. The process can be enhanced by using images acquired from the phone's rear camera.