Multi-device Object Tracking via Local Feature Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Computer vision multi-device tracking systems face challenges with privacy concerns, power issues, communication link issues, and latency problems during data transfer, and often have limited configurability for object detection and tracking.
Innovation Solution
A method and apparatus for multi-device object tracking and localization that involves transmitting request messages with target object images or features to a set of devices within a target area, receiving response messages containing location and pose information, and determining positional information such as direction and distance to the target object, using a processor and transceiver, with the option to apply trained models for improved detection and tracking accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If data is transferred from devices to server for object tracking, then recognition information and tracking information can be provided, but privacy issues arise and power consumption increases
Solution Approach 1:
The patent extracts and processes only the essential features needed for object tracking (such as object characteristics, location, and movement patterns) while leaving sensitive personal data on the local device. This allows the server to receive minimal necessary information for tracking purposes without compromising privacy, thus resolving the contradiction between detection accuracy and privacy protection.
Solution Approach 2:
The patent segments the object tracking system into local processing (feature extraction) and remote processing (tracking coordination) components. By dividing the data processing tasks, the system achieves accurate object detection through local analysis while minimizing data transfer to the server, thereby reducing power consumption and protecting privacy.
2Measurement precision
If data is transferred from devices to server, then object tracking information can be obtained, but latency issues and communication link issues occur
Solution Approach 1:
The patent performs preliminary feature extraction and object identification locally on the device before transferring data to the server. This preliminary processing reduces the amount and complexity of data that needs to be transferred, thereby minimizing communication latency while maintaining tracking accuracy.
Solution Approach 2:
The patent transfers only the essential partial information needed for tracking (such as extracted features and minimal metadata) rather than complete raw data. This partial data transfer approach maintains sufficient tracking accuracy while significantly reducing communication time and bandwidth requirements.
3Adaptability or versatility
If devices are configured to detect and track a variety of objects, then recognition capability is improved, but the configuration may be inaccessible to user modification
Solution Approach 1:
The patent implements a dynamic configuration system where the object detection parameters and tracking settings can be adjusted in real-time based on user needs and environmental conditions. The system allows users to modify detection categories, sensitivity levels, and tracking priorities through accessible interfaces, making the versatile detection capabilities adaptable to specific user requirements.
4Measurement precision
If multiple devices are used for tracking, then detection accuracy is improved, but device complexity increases
Solution Approach 1:
The patent merges the tracking functions of multiple devices under a unified server coordination system. The server consolidates data from multiple devices, harmonizes their detection results, and provides centralized control, thereby achieving improved detection accuracy through multi-device collaboration while managing system complexity through unified architecture.
Data Source
AI summary
Methods, systems, and devices for multi-device object tracking and localization are described. A device may transmit a request message associated with a target object to a set of devices within a target area. The request message may include an image of the target object, a feature of the target object, or at least a portion of a trained model associated with the target object. Subsequently, the device may receive response messages from the set of devices based on the request message. The response messages may include a portion of a captured image including the target object, location information of the devices, a pose of the devices, or temporal information of the target object detected within the target area by the devices. In some examples, the device may determine positional information with respect to the target object based on the one or more response messages.